<?xml version="1.0"?>
<net name="onnx_Frontend_IR" version="11">
<layers>
<layer id="0" name="serving_default_args_0" type="Parameter" version="opset1">
<data shape="1,4,512,512" element_type="f32" />
<output>
<port id="0" precision="FP32" names="serving_default_args_0">
<dim>1</dim>
<dim>4</dim>
<dim>512</dim>
<dim>512</dim>
</port>
</output>
</layer>
<layer id="1" name="Relu6__52_max__223" type="Const" version="opset1">
<data element_type="f32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="FP32" names="Relu6__52_max__223" />
</output>
</layer>
<layer id="2" name="Relu6__22_min__132" type="Const" version="opset1">
<data element_type="f32" shape="" offset="4" size="4" />
<output>
<port id="0" precision="FP32" names="Relu6__22_min__132" />
</output>
</layer>
<layer id="3" name="Constant_4" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="8" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="4" name="Constant_5" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="40" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="5" name="Constant_3" type="Const" version="opset1">
<data element_type="f32" shape="" offset="4" size="4" />
<output>
<port id="0" precision="FP32" />
</output>
</layer>
<layer id="6" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0;1" type="Pad" version="opset12">
<data pad_mode="constant" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>4</dim>
<dim>512</dim>
<dim>512</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
<port id="2" precision="I64">
<dim>4</dim>
</port>
<port id="3" precision="FP32" />
</input>
<output>
<port id="4" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0;1">
<dim>1</dim>
<dim>4</dim>
<dim>513</dim>
<dim>513</dim>
</port>
</output>
</layer>
<layer id="7" name="const_fold_opt__375" type="Const" version="opset1">
<data element_type="f32" shape="32, 4, 3, 3" offset="72" size="4608" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__375">
<dim>32</dim>
<dim>4</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="8" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="2, 2" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>4</dim>
<dim>513</dim>
<dim>513</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>4</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="9" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="32" offset="4680" size="128" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>32</dim>
</port>
</output>
</layer>
<layer id="10" name="Constant_12" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="11" name="ShapeOf_18" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="12" name="ShapeOf_10" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="13" name="ShapeOf_11" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="14" name="Constant_13" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="15" name="Subtract_14" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="16" name="Broadcast_15" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="17" name="Concat_19" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="18" name="Reshape_20" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="19" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="20" name="Maximum_24" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="21" name="Relu6__5" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__5:0">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="22" name="const_fold_opt__352" type="Const" version="opset1">
<data element_type="f32" shape="32, 1, 3, 3" offset="4824" size="1152" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__352">
<dim>32</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="23" name="Constant_30" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="5976" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="24" name="ShapeOf_31" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="25" name="Constant_28" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="26" name="Constant_29" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="27" name="VariadicSplit_32" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="28" name="Divide_33" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="29" name="Concat_34" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="30" name="Reshape_35" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="31" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="1, 1" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="32" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="32" offset="6008" size="128" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>32</dim>
</port>
</output>
</layer>
<layer id="33" name="Constant_77" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="34" name="ShapeOf_83" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="35" name="ShapeOf_75" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="36" name="ShapeOf_76" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="37" name="Constant_78" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="38" name="Subtract_79" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="39" name="Broadcast_80" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="40" name="Concat_84" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="41" name="Reshape_85" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="42" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="43" name="Maximum_87" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="44" name="Relu6__7" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__7:0">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="45" name="const_fold_opt__363" type="Const" version="opset1">
<data element_type="f32" shape="16, 32, 1, 1" offset="6136" size="2048" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__363">
<dim>16</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="46" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_1;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>256</dim>
<dim>256</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="47" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_1;" type="Const" version="opset1">
<data element_type="f32" shape="16" offset="8184" size="64" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_1;">
<dim>16</dim>
</port>
</output>
</layer>
<layer id="48" name="Constant_94" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="49" name="ShapeOf_100" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>16</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="50" name="ShapeOf_92" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="51" name="ShapeOf_93" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="52" name="Constant_95" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="53" name="Subtract_96" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="54" name="Broadcast_97" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="55" name="Concat_101" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="56" name="Reshape_102" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>16</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="57" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_1;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>256</dim>
<dim>256</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_1/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_1;2">
<dim>1</dim>
<dim>16</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="58" name="const_fold_opt__345" type="Const" version="opset1">
<data element_type="f32" shape="96, 16, 1, 1" offset="8248" size="6144" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__345">
<dim>96</dim>
<dim>16</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="59" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>256</dim>
<dim>256</dim>
</port>
<port id="1" precision="FP32">
<dim>96</dim>
<dim>16</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="60" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="96" offset="14392" size="384" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>96</dim>
</port>
</output>
</layer>
<layer id="61" name="Constant_109" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="62" name="ShapeOf_115" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>96</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="63" name="ShapeOf_107" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="64" name="ShapeOf_108" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="65" name="Constant_110" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="66" name="Subtract_111" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="67" name="Broadcast_112" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="68" name="Concat_116" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="69" name="Reshape_117" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>96</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="70" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>256</dim>
<dim>256</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>96</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="71" name="Maximum_119" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="72" name="Relu6__10" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__10:0">
<dim>1</dim>
<dim>96</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="73" name="const_fold_opt__348" type="Const" version="opset1">
<data element_type="f32" shape="96, 1, 3, 3" offset="14776" size="3456" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__348">
<dim>96</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="74" name="Constant_125" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="18232" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="75" name="ShapeOf_126" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>96</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="76" name="Constant_123" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="77" name="Constant_124" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="78" name="VariadicSplit_127" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="79" name="Divide_128" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="80" name="Concat_129" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="81" name="Reshape_130" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>96</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>96</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="82" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="2, 2" pads_begin="0, 0" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>256</dim>
<dim>256</dim>
</port>
<port id="1" precision="FP32">
<dim>96</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="83" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;" type="Const" version="opset1">
<data element_type="f32" shape="96" offset="18240" size="384" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;">
<dim>96</dim>
</port>
</output>
</layer>
<layer id="84" name="Constant_172" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="85" name="ShapeOf_178" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>96</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="86" name="ShapeOf_170" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="87" name="ShapeOf_171" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="88" name="Constant_173" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="89" name="Subtract_174" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="90" name="Broadcast_175" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="91" name="Concat_179" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="92" name="Reshape_180" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>96</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="93" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;2">
<dim>1</dim>
<dim>96</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="94" name="Maximum_182" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="95" name="Relu6__12" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__12:0">
<dim>1</dim>
<dim>96</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="96" name="const_fold_opt__337" type="Const" version="opset1">
<data element_type="f32" shape="24, 96, 1, 1" offset="18624" size="9216" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__337">
<dim>24</dim>
<dim>96</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="97" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>96</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>24</dim>
<dim>96</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="98" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;" type="Const" version="opset1">
<data element_type="f32" shape="24" offset="27840" size="96" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;">
<dim>24</dim>
</port>
</output>
</layer>
<layer id="99" name="Constant_189" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="100" name="ShapeOf_195" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>24</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="101" name="ShapeOf_187" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="102" name="ShapeOf_188" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="103" name="Constant_190" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="104" name="Subtract_191" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="105" name="Broadcast_192" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="106" name="Concat_196" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="107" name="Reshape_197" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>24</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="108" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="109" name="const_fold_opt__332" type="Const" version="opset1">
<data element_type="f32" shape="144, 24, 1, 1" offset="27936" size="13824" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__332">
<dim>144</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="110" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>144</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="111" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="144" offset="41760" size="576" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>144</dim>
</port>
</output>
</layer>
<layer id="112" name="Constant_204" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="113" name="ShapeOf_210" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="114" name="ShapeOf_202" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="115" name="ShapeOf_203" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="116" name="Constant_205" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="117" name="Subtract_206" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="118" name="Broadcast_207" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="119" name="Concat_211" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="120" name="Reshape_212" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="121" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="122" name="Maximum_214" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="123" name="Relu6__15" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__15:0">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="124" name="const_fold_opt__394" type="Const" version="opset1">
<data element_type="f32" shape="144, 1, 3, 3" offset="42336" size="5184" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__394">
<dim>144</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="125" name="Constant_220" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="47520" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="126" name="ShapeOf_221" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="127" name="Constant_218" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="128" name="Constant_219" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="129" name="VariadicSplit_222" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="130" name="Divide_223" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="131" name="Concat_224" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="132" name="Reshape_225" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="133" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="1, 1" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="134" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="144" offset="47528" size="576" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;">
<dim>144</dim>
</port>
</output>
</layer>
<layer id="135" name="Constant_267" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="136" name="ShapeOf_273" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="137" name="ShapeOf_265" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="138" name="ShapeOf_266" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="139" name="Constant_268" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="140" name="Subtract_269" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="141" name="Broadcast_270" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="142" name="Concat_274" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="143" name="Reshape_275" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="144" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="145" name="Maximum_277" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="146" name="Relu6__17" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__17:0">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="147" name="const_fold_opt__328" type="Const" version="opset1">
<data element_type="f32" shape="24, 144, 1, 1" offset="48104" size="13824" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__328">
<dim>24</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="148" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>24</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="149" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;" type="Const" version="opset1">
<data element_type="f32" shape="24" offset="61928" size="96" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;">
<dim>24</dim>
</port>
</output>
</layer>
<layer id="150" name="Constant_284" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="151" name="ShapeOf_290" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>24</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="152" name="ShapeOf_282" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="153" name="ShapeOf_283" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="154" name="Constant_285" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="155" name="Subtract_286" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="156" name="Broadcast_287" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="157" name="Concat_291" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="158" name="Reshape_292" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>24</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="159" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_2/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="160" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3;" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3;">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="161" name="const_fold_opt__326" type="Const" version="opset1">
<data element_type="f32" shape="32, 24, 1, 1" offset="62024" size="3072" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__326">
<dim>32</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="162" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="163" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="32" offset="65096" size="128" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;">
<dim>32</dim>
</port>
</output>
</layer>
<layer id="164" name="Constant_1056" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="165" name="ShapeOf_1062" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="166" name="ShapeOf_1054" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="167" name="ShapeOf_1055" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="168" name="Constant_1057" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="169" name="Subtract_1058" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="170" name="Broadcast_1059" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="171" name="Concat_1063" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="172" name="Reshape_1064" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="173" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>32</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="174" name="Relu__65" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__65:0">
<dim>1</dim>
<dim>32</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="175" name="const_fold_opt__323" type="Const" version="opset1">
<data element_type="f32" shape="144, 24, 1, 1" offset="65224" size="13824" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__323">
<dim>144</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="176" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>24</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>144</dim>
<dim>24</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="177" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="144" offset="79048" size="576" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>144</dim>
</port>
</output>
</layer>
<layer id="178" name="Constant_300" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="179" name="ShapeOf_306" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="180" name="ShapeOf_298" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="181" name="ShapeOf_299" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="182" name="Constant_301" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="183" name="Subtract_302" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="184" name="Broadcast_303" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="185" name="Concat_307" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="186" name="Reshape_308" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="187" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_3/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="188" name="Maximum_310" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="189" name="Relu6__20" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__20:0">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="190" name="const_fold_opt__372" type="Const" version="opset1">
<data element_type="f32" shape="144, 1, 3, 3" offset="79624" size="5184" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__372">
<dim>144</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="191" name="Constant_316" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="47520" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="192" name="ShapeOf_317" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="193" name="Constant_314" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="194" name="Constant_315" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="195" name="VariadicSplit_318" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="196" name="Divide_319" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="197" name="Concat_320" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="198" name="Reshape_321" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="199" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="2, 2" pads_begin="0, 0" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="200" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;" type="Const" version="opset1">
<data element_type="f32" shape="144" offset="84808" size="576" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;">
<dim>144</dim>
</port>
</output>
</layer>
<layer id="201" name="Constant_363" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="202" name="ShapeOf_369" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="203" name="ShapeOf_361" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="204" name="ShapeOf_362" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="205" name="Constant_364" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="206" name="Subtract_365" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="207" name="Broadcast_366" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="208" name="Concat_370" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="209" name="Reshape_371" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>144</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="210" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;2">
<dim>1</dim>
<dim>144</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="211" name="Maximum_373" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="212" name="Relu6__22" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__22:0">
<dim>1</dim>
<dim>144</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="213" name="const_fold_opt__343" type="Const" version="opset1">
<data element_type="f32" shape="32, 144, 1, 1" offset="85384" size="18432" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__343">
<dim>32</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="214" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>144</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>144</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="215" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;" type="Const" version="opset1">
<data element_type="f32" shape="32" offset="103816" size="128" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;">
<dim>32</dim>
</port>
</output>
</layer>
<layer id="216" name="Constant_380" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="217" name="ShapeOf_386" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="218" name="ShapeOf_378" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="219" name="ShapeOf_379" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="220" name="Constant_381" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="221" name="Subtract_382" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="222" name="Broadcast_383" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="223" name="Concat_387" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="224" name="Reshape_388" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="225" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="226" name="const_fold_opt__336" type="Const" version="opset1">
<data element_type="f32" shape="192, 32, 1, 1" offset="103944" size="24576" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__336">
<dim>192</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="227" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>192</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="228" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="192" offset="128520" size="768" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>192</dim>
</port>
</output>
</layer>
<layer id="229" name="Constant_395" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="230" name="ShapeOf_401" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="231" name="ShapeOf_393" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="232" name="ShapeOf_394" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="233" name="Constant_396" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="234" name="Subtract_397" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="235" name="Broadcast_398" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="236" name="Concat_402" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="237" name="Reshape_403" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="238" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="239" name="Maximum_405" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="240" name="Relu6__25" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__25:0">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="241" name="const_fold_opt__369" type="Const" version="opset1">
<data element_type="f32" shape="192, 1, 3, 3" offset="129288" size="6912" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__369">
<dim>192</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="242" name="Constant_411" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="136200" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="243" name="ShapeOf_412" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="244" name="Constant_409" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="245" name="Constant_410" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="246" name="VariadicSplit_413" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="247" name="Divide_414" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="248" name="Concat_415" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="249" name="Reshape_416" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="250" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="1, 1" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="251" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="192" offset="136208" size="768" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;">
<dim>192</dim>
</port>
</output>
</layer>
<layer id="252" name="Constant_458" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="253" name="ShapeOf_464" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="254" name="ShapeOf_456" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="255" name="ShapeOf_457" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="256" name="Constant_459" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="257" name="Subtract_460" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="258" name="Broadcast_461" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="259" name="Concat_465" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="260" name="Reshape_466" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="261" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="262" name="Maximum_468" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="263" name="Relu6__27" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__27:0">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="264" name="const_fold_opt__383" type="Const" version="opset1">
<data element_type="f32" shape="32, 192, 1, 1" offset="136976" size="24576" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__383">
<dim>32</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="265" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="266" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;" type="Const" version="opset1">
<data element_type="f32" shape="32" offset="161552" size="128" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;">
<dim>32</dim>
</port>
</output>
</layer>
<layer id="267" name="Constant_475" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="268" name="ShapeOf_481" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="269" name="ShapeOf_473" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="270" name="ShapeOf_474" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="271" name="Constant_476" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="272" name="Subtract_477" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="273" name="Broadcast_478" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="274" name="Concat_482" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="275" name="Reshape_483" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="276" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="277" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5;" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5;">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="278" name="const_fold_opt__319" type="Const" version="opset1">
<data element_type="f32" shape="192, 32, 1, 1" offset="161680" size="24576" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__319">
<dim>192</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="279" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>192</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="280" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="192" offset="186256" size="768" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>192</dim>
</port>
</output>
</layer>
<layer id="281" name="Constant_491" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="282" name="ShapeOf_497" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="283" name="ShapeOf_489" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="284" name="ShapeOf_490" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="285" name="Constant_492" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="286" name="Subtract_493" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="287" name="Broadcast_494" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="288" name="Concat_498" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="289" name="Reshape_499" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="290" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="291" name="Maximum_501" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="292" name="Relu6__30" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__30:0">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="293" name="const_fold_opt__366" type="Const" version="opset1">
<data element_type="f32" shape="192, 1, 3, 3" offset="187024" size="6912" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__366">
<dim>192</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="294" name="Constant_507" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="136200" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="295" name="ShapeOf_508" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="296" name="Constant_505" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="297" name="Constant_506" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="298" name="VariadicSplit_509" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="299" name="Divide_510" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="300" name="Concat_511" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="301" name="Reshape_512" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="302" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="1, 1" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="303" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="192" offset="193936" size="768" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;">
<dim>192</dim>
</port>
</output>
</layer>
<layer id="304" name="Constant_554" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="305" name="ShapeOf_560" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="306" name="ShapeOf_552" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="307" name="ShapeOf_553" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="308" name="Constant_555" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="309" name="Subtract_556" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="310" name="Broadcast_557" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="311" name="Concat_561" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="312" name="Reshape_562" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="313" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="314" name="Maximum_564" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="315" name="Relu6__32" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__32:0">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="316" name="const_fold_opt__381" type="Const" version="opset1">
<data element_type="f32" shape="32, 192, 1, 1" offset="194704" size="24576" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__381">
<dim>32</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="317" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="318" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;" type="Const" version="opset1">
<data element_type="f32" shape="32" offset="219280" size="128" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;">
<dim>32</dim>
</port>
</output>
</layer>
<layer id="319" name="Constant_571" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="320" name="ShapeOf_577" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="321" name="ShapeOf_569" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="322" name="ShapeOf_570" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="323" name="Constant_572" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="324" name="Subtract_573" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="325" name="Broadcast_574" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="326" name="Concat_578" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="327" name="Reshape_579" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="328" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="329" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6;" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_6;">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="330" name="const_fold_opt__384" type="Const" version="opset1">
<data element_type="f32" shape="64, 32, 1, 1" offset="219408" size="8192" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__384">
<dim>64</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="331" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="332" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="227600" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="333" name="Constant_989" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="334" name="ShapeOf_995" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="335" name="ShapeOf_987" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="336" name="ShapeOf_988" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="337" name="Constant_990" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="338" name="Subtract_991" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="339" name="Broadcast_992" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="340" name="Concat_996" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="341" name="Reshape_997" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="342" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="343" name="Relu__57" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__57:0">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="344" name="const_fold_opt__308" type="Const" version="opset1">
<data element_type="f32" shape="192, 32, 1, 1" offset="227856" size="24576" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__308">
<dim>192</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="345" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>192</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="346" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="192" offset="252432" size="768" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>192</dim>
</port>
</output>
</layer>
<layer id="347" name="Constant_587" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="348" name="ShapeOf_593" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="349" name="ShapeOf_585" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="350" name="ShapeOf_586" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="351" name="Constant_588" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="352" name="Subtract_589" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="353" name="Broadcast_590" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="354" name="Concat_594" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="355" name="Reshape_595" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="356" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_5/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="357" name="Maximum_597" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="358" name="Relu6__35" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__35:0">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="359" name="const_fold_opt__391" type="Const" version="opset1">
<data element_type="f32" shape="192, 1, 3, 3" offset="253200" size="6912" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__391">
<dim>192</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="360" name="Constant_603" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="136200" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="361" name="ShapeOf_604" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="362" name="Constant_601" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="363" name="Constant_602" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="364" name="VariadicSplit_605" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="365" name="Divide_606" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="366" name="Concat_607" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="367" name="Reshape_608" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="368" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="2, 2" pads_begin="0, 0" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="369" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;" type="Const" version="opset1">
<data element_type="f32" shape="192" offset="260112" size="768" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;">
<dim>192</dim>
</port>
</output>
</layer>
<layer id="370" name="Constant_650" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="371" name="ShapeOf_656" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="372" name="ShapeOf_648" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="373" name="ShapeOf_649" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="374" name="Constant_651" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="375" name="Subtract_652" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="376" name="Broadcast_653" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="377" name="Concat_657" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="378" name="Reshape_658" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>192</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="379" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1;2">
<dim>1</dim>
<dim>192</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="380" name="Maximum_660" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="381" name="Relu6__37" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__37:0">
<dim>1</dim>
<dim>192</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="382" name="const_fold_opt__395" type="Const" version="opset1">
<data element_type="f32" shape="64, 192, 1, 1" offset="260880" size="49152" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__395">
<dim>64</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="383" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>192</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>192</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="384" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="310032" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="385" name="Constant_667" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="386" name="ShapeOf_673" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="387" name="ShapeOf_665" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="388" name="ShapeOf_666" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="389" name="Constant_668" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="390" name="Subtract_669" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="391" name="Broadcast_670" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="392" name="Concat_674" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="393" name="Reshape_675" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="394" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="395" name="const_fold_opt__370" type="Const" version="opset1">
<data element_type="f32" shape="384, 64, 1, 1" offset="310288" size="98304" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__370">
<dim>384</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="396" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>384</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="397" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="384" offset="408592" size="1536" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>384</dim>
</port>
</output>
</layer>
<layer id="398" name="Constant_682" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="399" name="ShapeOf_688" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="400" name="ShapeOf_680" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="401" name="ShapeOf_681" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="402" name="Constant_683" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="403" name="Subtract_684" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="404" name="Broadcast_685" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="405" name="Concat_689" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="406" name="Reshape_690" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="407" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="408" name="Maximum_692" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="409" name="Relu6__40" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__40:0">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="410" name="const_fold_opt__389" type="Const" version="opset1">
<data element_type="f32" shape="384, 1, 3, 3" offset="410128" size="13824" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__389">
<dim>384</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="411" name="Constant_698" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="423952" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="412" name="ShapeOf_699" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="413" name="Constant_696" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="414" name="Constant_697" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="415" name="VariadicSplit_700" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="416" name="Divide_701" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="417" name="Concat_702" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="418" name="Reshape_703" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="419" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="1, 1" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="420" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="384" offset="423960" size="1536" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;">
<dim>384</dim>
</port>
</output>
</layer>
<layer id="421" name="Constant_745" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="422" name="ShapeOf_751" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="423" name="ShapeOf_743" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="424" name="ShapeOf_744" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="425" name="Constant_746" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="426" name="Subtract_747" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="427" name="Broadcast_748" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="428" name="Concat_752" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="429" name="Reshape_753" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="430" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="431" name="Maximum_755" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="432" name="Relu6__42" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__42:0">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="433" name="const_fold_opt__360" type="Const" version="opset1">
<data element_type="f32" shape="64, 384, 1, 1" offset="425496" size="98304" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__360">
<dim>64</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="434" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="435" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="523800" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="436" name="Constant_762" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="437" name="ShapeOf_768" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="438" name="ShapeOf_760" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="439" name="ShapeOf_761" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="440" name="Constant_763" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="441" name="Subtract_764" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="442" name="Broadcast_765" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="443" name="Concat_769" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="444" name="Reshape_770" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="445" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="446" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8;" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8;">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="447" name="const_fold_opt__353" type="Const" version="opset1">
<data element_type="f32" shape="384, 64, 1, 1" offset="524056" size="98304" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__353">
<dim>384</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="448" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>384</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="449" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="384" offset="622360" size="1536" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>384</dim>
</port>
</output>
</layer>
<layer id="450" name="Constant_778" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="451" name="ShapeOf_784" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="452" name="ShapeOf_776" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="453" name="ShapeOf_777" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="454" name="Constant_779" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="455" name="Subtract_780" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="456" name="Broadcast_781" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="457" name="Concat_785" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="458" name="Reshape_786" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="459" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="460" name="Maximum_788" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="461" name="Relu6__45" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__45:0">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="462" name="const_fold_opt__359" type="Const" version="opset1">
<data element_type="f32" shape="384, 1, 3, 3" offset="623896" size="13824" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__359">
<dim>384</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="463" name="Constant_794" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="423952" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="464" name="ShapeOf_795" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="465" name="Constant_792" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="466" name="Constant_793" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="467" name="VariadicSplit_796" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="468" name="Divide_797" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="469" name="Concat_798" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="470" name="Reshape_799" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="471" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="1, 1" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="472" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="384" offset="637720" size="1536" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;">
<dim>384</dim>
</port>
</output>
</layer>
<layer id="473" name="Constant_841" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="474" name="ShapeOf_847" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="475" name="ShapeOf_839" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="476" name="ShapeOf_840" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="477" name="Constant_842" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="478" name="Subtract_843" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="479" name="Broadcast_844" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="480" name="Concat_848" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="481" name="Reshape_849" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="482" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="483" name="Maximum_851" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="484" name="Relu6__47" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__47:0">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="485" name="const_fold_opt__342" type="Const" version="opset1">
<data element_type="f32" shape="64, 384, 1, 1" offset="639256" size="98304" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__342">
<dim>64</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="486" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="487" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="737560" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="488" name="Constant_858" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="489" name="ShapeOf_864" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="490" name="ShapeOf_856" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="491" name="ShapeOf_857" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="492" name="Constant_859" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="493" name="Subtract_860" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="494" name="Broadcast_861" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="495" name="Concat_865" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="496" name="Reshape_866" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="497" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="498" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9;" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_9;">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="499" name="const_fold_opt__387" type="Const" version="opset1">
<data element_type="f32" shape="384, 64, 1, 1" offset="737816" size="98304" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__387">
<dim>384</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="500" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>384</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="501" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="384" offset="836120" size="1536" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;">
<dim>384</dim>
</port>
</output>
</layer>
<layer id="502" name="Constant_874" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="503" name="ShapeOf_880" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="504" name="ShapeOf_872" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="505" name="ShapeOf_873" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="506" name="Constant_875" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="507" name="Subtract_876" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="508" name="Broadcast_877" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="509" name="Concat_881" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="510" name="Reshape_882" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="511" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="512" name="Maximum_884" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="513" name="Relu6__50" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__50:0">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="514" name="const_fold_opt__355" type="Const" version="opset1">
<data element_type="f32" shape="384, 1, 3, 3" offset="837656" size="13824" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__355">
<dim>384</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="515" name="Constant_890" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="423952" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="516" name="ShapeOf_891" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="517" name="Constant_888" type="Const" version="opset1">
<data element_type="i64" shape="" offset="5984" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="518" name="Constant_889" type="Const" version="opset1">
<data element_type="i64" shape="2" offset="5992" size="16" />
<output>
<port id="0" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="519" name="VariadicSplit_892" type="VariadicSplit" version="opset1">
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64" />
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="520" name="Divide_893" type="Divide" version="opset1">
<data auto_broadcast="numpy" m_pythondiv="true" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="521" name="Concat_894" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>5</dim>
</port>
</output>
</layer>
<layer id="522" name="Reshape_895" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
<port id="1" precision="I64">
<dim>5</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="523" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="GroupConvolution" version="opset1">
<data strides="1, 1" pads_begin="1, 1" pads_end="1, 1" dilations="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="524" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="384" offset="851480" size="1536" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;">
<dim>384</dim>
</port>
</output>
</layer>
<layer id="525" name="Constant_937" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="526" name="ShapeOf_943" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="527" name="ShapeOf_935" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="528" name="ShapeOf_936" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="529" name="Constant_938" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="530" name="Subtract_939" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="531" name="Broadcast_940" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="532" name="Concat_944" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="533" name="Reshape_945" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>384</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="534" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_8/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/models.mbv2_mlsd_tiny.ConvBNReLU_1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="535" name="Maximum_947" type="Maximum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="536" name="Relu6__52" type="Minimum" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32" />
<port id="1" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Relu6__52:0">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="537" name="const_fold_opt__386" type="Const" version="opset1">
<data element_type="f32" shape="64, 384, 1, 1" offset="853016" size="98304" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__386">
<dim>64</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="538" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>384</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>384</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="539" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="951320" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="540" name="Constant_954" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="541" name="ShapeOf_960" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="542" name="ShapeOf_952" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="543" name="ShapeOf_953" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="544" name="Constant_955" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="545" name="Subtract_956" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="546" name="Broadcast_957" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="547" name="Concat_961" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="548" name="Reshape_962" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="549" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10/torch.nn.modules.container.Sequential_conv/torch.nn.modules.conv.Conv2d_2;2">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="550" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10;" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_10;">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="551" name="const_fold_opt__339" type="Const" version="opset1">
<data element_type="f32" shape="64, 64, 1, 1" offset="951576" size="16384" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__339">
<dim>64</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="552" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="553" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="967960" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="554" name="Constant_970" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="555" name="ShapeOf_976" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="556" name="ShapeOf_968" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="557" name="ShapeOf_969" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="558" name="Constant_971" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="559" name="Subtract_972" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="560" name="Broadcast_973" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="561" name="Concat_977" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="562" name="Reshape_978" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="563" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_7/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="564" name="Relu__55" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__55:0">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="565" name="scales__248" type="Const" version="opset1">
<data element_type="f32" shape="4" offset="968216" size="16" />
<output>
<port id="0" precision="FP32" names="scales__248">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="566" name="Resize__233" type="Interpolate" version="opset11">
<data mode="linear_onnx" shape_calculation_mode="scales" coordinate_transformation_mode="half_pixel" nearest_mode="floor" antialias="false" pads_begin="0, 0, 0, 0" pads_end="0, 0, 0, 0" cube_coeff="-0.75" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>32</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Resize__233:0">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="567" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12;2" type="Concat" version="opset1">
<data axis="1" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12;2">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="568" name="const_fold_opt__382" type="Const" version="opset1">
<data element_type="f32" shape="128, 128, 3, 3" offset="968232" size="589824" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__382">
<dim>128</dim>
<dim>128</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="569" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>128</dim>
<dim>128</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="570" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="128" offset="1558056" size="512" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;">
<dim>128</dim>
</port>
</output>
</layer>
<layer id="571" name="Constant_1006" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="572" name="ShapeOf_1012" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="573" name="ShapeOf_1004" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="574" name="ShapeOf_1005" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="575" name="Constant_1007" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="576" name="Subtract_1008" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="577" name="Broadcast_1009" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="578" name="Concat_1013" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="579" name="Reshape_1014" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>128</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="580" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="581" name="Relu__59" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__59:0">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="582" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="583" name="const_fold_opt__315" type="Const" version="opset1">
<data element_type="f32" shape="64, 128, 3, 3" offset="1558568" size="294912" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__315">
<dim>64</dim>
<dim>128</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="584" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>128</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="585" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="1853480" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="586" name="Constant_1023" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="587" name="ShapeOf_1029" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="588" name="ShapeOf_1021" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="589" name="ShapeOf_1022" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="590" name="Constant_1024" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="591" name="Subtract_1025" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="592" name="Broadcast_1026" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="593" name="Concat_1030" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="594" name="Reshape_1031" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="595" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block12/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block13/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="596" name="Relu__61" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__61:0">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="597" name="const_fold_opt__330" type="Const" version="opset1">
<data element_type="f32" shape="32, 64, 1, 1" offset="1853736" size="8192" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__330">
<dim>32</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="598" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="599" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="32" offset="1861928" size="128" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;">
<dim>32</dim>
</port>
</output>
</layer>
<layer id="600" name="Constant_1039" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="601" name="ShapeOf_1045" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="602" name="ShapeOf_1037" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="603" name="ShapeOf_1038" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="604" name="Constant_1040" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="605" name="Subtract_1041" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="606" name="Broadcast_1042" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="607" name="Concat_1046" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="608" name="Reshape_1047" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="609" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.InvertedResidual_4/torch.nn.modules.container.Sequential_conv/torch.nn.modules.batchnorm.BatchNorm2d_3;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="610" name="Relu__63" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__63:0">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
</output>
</layer>
<layer id="611" name="Resize__249" type="Interpolate" version="opset11">
<data mode="linear_onnx" shape_calculation_mode="scales" coordinate_transformation_mode="half_pixel" nearest_mode="floor" antialias="false" pads_begin="0, 0, 0, 0" pads_end="0, 0, 0, 0" cube_coeff="-0.75" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>64</dim>
<dim>64</dim>
</port>
<port id="1" precision="FP32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Resize__249:0">
<dim>1</dim>
<dim>32</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="612" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14;2" type="Concat" version="opset1">
<data axis="1" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>32</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeA_block14;2">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="613" name="const_fold_opt__312" type="Const" version="opset1">
<data element_type="f32" shape="64, 64, 3, 3" offset="1862056" size="147456" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__312">
<dim>64</dim>
<dim>64</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="614" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>64</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="615" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="2009512" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="616" name="Constant_1073" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="617" name="ShapeOf_1079" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="618" name="ShapeOf_1071" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="619" name="ShapeOf_1072" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="620" name="Constant_1074" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="621" name="Subtract_1075" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="622" name="Broadcast_1076" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="623" name="Concat_1080" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="624" name="Reshape_1081" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="625" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="626" name="Relu__67" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__67:0">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="627" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="628" name="const_fold_opt__310" type="Const" version="opset1">
<data element_type="f32" shape="64, 64, 3, 3" offset="2009768" size="147456" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__310">
<dim>64</dim>
<dim>64</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="629" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>64</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="630" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="2157224" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="631" name="Constant_1090" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="632" name="ShapeOf_1096" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="633" name="ShapeOf_1088" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="634" name="ShapeOf_1089" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="635" name="Constant_1091" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="636" name="Subtract_1092" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="637" name="Broadcast_1093" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="638" name="Concat_1097" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="639" name="Reshape_1098" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="640" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="641" name="Relu__69" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__69:0">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="642" name="const_fold_opt__379" type="Const" version="opset1">
<data element_type="f32" shape="64, 64, 3, 3" offset="2157480" size="147456" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__379">
<dim>64</dim>
<dim>64</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="643" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="5, 5" pads_begin="5, 5" pads_end="5, 5" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>64</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="644" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="2304936" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="645" name="Constant_1106" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="646" name="ShapeOf_1112" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="647" name="ShapeOf_1104" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="648" name="ShapeOf_1105" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="649" name="Constant_1107" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="650" name="Subtract_1108" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="651" name="Broadcast_1109" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="652" name="Concat_1113" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="653" name="Reshape_1114" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="654" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="655" name="Relu__71" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__71:0">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="656" name="const_fold_opt__305" type="Const" version="opset1">
<data element_type="f32" shape="64, 64, 3, 3" offset="2305192" size="147456" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__305">
<dim>64</dim>
<dim>64</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="657" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>64</dim>
<dim>64</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="658" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;" type="Const" version="opset1">
<data element_type="f32" shape="64" offset="2452648" size="256" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;">
<dim>64</dim>
</port>
</output>
</layer>
<layer id="659" name="Constant_1122" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="660" name="ShapeOf_1128" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="661" name="ShapeOf_1120" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="662" name="ShapeOf_1121" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="663" name="Constant_1123" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="664" name="Subtract_1124" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="665" name="Broadcast_1125" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="666" name="Concat_1129" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="667" name="Reshape_1130" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>64</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="668" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.activation.ReLU_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeB_block15/torch.nn.modules.container.Sequential_conv1/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.container.Sequential_conv2/torch.nn.modules.conv.Conv2d_0;2">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="669" name="Relu__73" type="ReLU" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="Relu__73:0">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="670" name="const_fold_opt__377" type="Const" version="opset1">
<data element_type="f32" shape="16, 64, 1, 1" offset="2452904" size="4096" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__377">
<dim>16</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="671" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.conv.Conv2d_conv3;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>64</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>64</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="672" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.conv.Conv2d_conv3;" type="Const" version="opset1">
<data element_type="f32" shape="16" offset="2457000" size="64" />
<output>
<port id="0" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.conv.Conv2d_conv3;">
<dim>16</dim>
</port>
</output>
</layer>
<layer id="673" name="Constant_1138" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="674" name="ShapeOf_1144" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>16</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="675" name="ShapeOf_1136" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="676" name="ShapeOf_1137" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="677" name="Constant_1139" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4816" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="678" name="Subtract_1140" type="Subtract" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="679" name="Broadcast_1141" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</output>
</layer>
<layer id="680" name="Concat_1145" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>2</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="681" name="Reshape_1146" type="Reshape" version="opset1">
<data special_zero="false" />
<input>
<port id="0" precision="FP32">
<dim>16</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</output>
</layer>
<layer id="682" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.conv.Conv2d_conv3;2" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>1</dim>
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.conv.Conv2d_conv3;2">
<dim>1</dim>
<dim>16</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="683" name="Constant_1148" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="2457064" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="684" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.conv.Conv2d_conv3;2__267" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>16</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.BlockTypeC_block16/torch.nn.modules.conv.Conv2d_conv3;2__267:0">
<dim>1</dim>
<dim>128</dim>
<dim>128</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="685" name="const_starts__268" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="2457096" size="32" />
<output>
<port id="0" precision="I64" names="const_starts__268">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="686" name="const_ends__269" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="2457128" size="32" />
<output>
<port id="0" precision="I64" names="const_ends__269">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="687" name="Constant_1152" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="4808" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="688" name="ShapeOf_1153" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="689" name="Broadcast_1154" type="Broadcast" version="opset3">
<data mode="numpy" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="690" name="Constant_1158" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="2457160" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="691" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny;3" type="Slice" version="opset8">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>128</dim>
<dim>16</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
<port id="2" precision="I64">
<dim>4</dim>
</port>
<port id="3" precision="I64">
<dim>4</dim>
</port>
<port id="4" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="5" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny;3">
<dim>1</dim>
<dim>128</dim>
<dim>128</dim>
<dim>9</dim>
</port>
</output>
</layer>
<layer id="692" name="Constant_1160" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="2457192" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="693" name="Transpose__271" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>128</dim>
<dim>128</dim>
<dim>9</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="Transpose__271:0">
<dim>1</dim>
<dim>9</dim>
<dim>128</dim>
<dim>128</dim>
</port>
</output>
</layer>
<layer id="694" name="serving_default_output_0_output" type="Interpolate" version="opset11">
<data mode="linear_onnx" shape_calculation_mode="scales" coordinate_transformation_mode="half_pixel" nearest_mode="floor" antialias="false" pads_begin="0, 0, 0, 0" pads_end="0, 0, 0, 0" cube_coeff="-0.75" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>9</dim>
<dim>128</dim>
<dim>128</dim>
</port>
<port id="1" precision="FP32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="serving_default_output_0_output">
<dim>1</dim>
<dim>9</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</output>
</layer>
<layer id="695" name="serving_default_output_0_output/sink_port_0" type="Result" version="opset1" output_names="serving_default_output_0_output">
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>9</dim>
<dim>256</dim>
<dim>256</dim>
</port>
</input>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="189" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="21" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="95" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="72" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="513" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="484" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="461" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="432" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="409" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="381" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="358" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="315" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="292" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="44" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="212" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="240" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="263" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="536" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="146" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="123" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="483" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="512" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="535" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="71" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="94" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="122" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="145" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="262" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="239" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="211" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="43" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="188" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="314" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="291" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="357" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="380" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="408" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="431" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="460" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="20" to-port="0" />
<edge from-layer="3" from-port="0" to-layer="6" to-port="1" />
<edge from-layer="4" from-port="0" to-layer="6" to-port="2" />
<edge from-layer="5" from-port="0" to-layer="6" to-port="3" />
<edge from-layer="6" from-port="4" to-layer="8" to-port="0" />
<edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
<edge from-layer="8" from-port="2" to-layer="12" to-port="0" />
<edge from-layer="8" from-port="2" to-layer="19" to-port="0" />
<edge from-layer="9" from-port="0" to-layer="11" to-port="0" />
<edge from-layer="9" from-port="0" to-layer="18" to-port="0" />
<edge from-layer="10" from-port="0" to-layer="16" to-port="0" />
<edge from-layer="10" from-port="0" to-layer="17" to-port="0" />
<edge from-layer="11" from-port="1" to-layer="17" to-port="1" />
<edge from-layer="12" from-port="1" to-layer="13" to-port="0" />
<edge from-layer="13" from-port="1" to-layer="15" to-port="0" />
<edge from-layer="14" from-port="0" to-layer="15" to-port="1" />
<edge from-layer="15" from-port="2" to-layer="16" to-port="1" />
<edge from-layer="16" from-port="2" to-layer="17" to-port="2" />
<edge from-layer="17" from-port="3" to-layer="18" to-port="1" />
<edge from-layer="18" from-port="2" to-layer="19" to-port="1" />
<edge from-layer="19" from-port="2" to-layer="20" to-port="1" />
<edge from-layer="20" from-port="2" to-layer="21" to-port="1" />
<edge from-layer="21" from-port="2" to-layer="31" to-port="0" />
<edge from-layer="22" from-port="0" to-layer="30" to-port="0" />
<edge from-layer="22" from-port="0" to-layer="24" to-port="0" />
<edge from-layer="23" from-port="0" to-layer="28" to-port="1" />
<edge from-layer="23" from-port="0" to-layer="29" to-port="0" />
<edge from-layer="24" from-port="1" to-layer="27" to-port="0" />
<edge from-layer="25" from-port="0" to-layer="27" to-port="1" />
<edge from-layer="26" from-port="0" to-layer="27" to-port="2" />
<edge from-layer="27" from-port="3" to-layer="28" to-port="0" />
<edge from-layer="27" from-port="4" to-layer="29" to-port="2" />
<edge from-layer="28" from-port="2" to-layer="29" to-port="1" />
<edge from-layer="29" from-port="3" to-layer="30" to-port="1" />
<edge from-layer="30" from-port="2" to-layer="31" to-port="1" />
<edge from-layer="31" from-port="2" to-layer="35" to-port="0" />
<edge from-layer="31" from-port="2" to-layer="42" to-port="0" />
<edge from-layer="32" from-port="0" to-layer="34" to-port="0" />
<edge from-layer="32" from-port="0" to-layer="41" to-port="0" />
<edge from-layer="33" from-port="0" to-layer="39" to-port="0" />
<edge from-layer="33" from-port="0" to-layer="40" to-port="0" />
<edge from-layer="34" from-port="1" to-layer="40" to-port="1" />
<edge from-layer="35" from-port="1" to-layer="36" to-port="0" />
<edge from-layer="36" from-port="1" to-layer="38" to-port="0" />
<edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
<edge from-layer="38" from-port="2" to-layer="39" to-port="1" />
<edge from-layer="39" from-port="2" to-layer="40" to-port="2" />
<edge from-layer="40" from-port="3" to-layer="41" to-port="1" />
<edge from-layer="41" from-port="2" to-layer="42" to-port="1" />
<edge from-layer="42" from-port="2" to-layer="43" to-port="1" />
<edge from-layer="43" from-port="2" to-layer="44" to-port="1" />
<edge from-layer="44" from-port="2" to-layer="46" to-port="0" />
<edge from-layer="45" from-port="0" to-layer="46" to-port="1" />
<edge from-layer="46" from-port="2" to-layer="50" to-port="0" />
<edge from-layer="46" from-port="2" to-layer="57" to-port="0" />
<edge from-layer="47" from-port="0" to-layer="49" to-port="0" />
<edge from-layer="47" from-port="0" to-layer="56" to-port="0" />
<edge from-layer="48" from-port="0" to-layer="54" to-port="0" />
<edge from-layer="48" from-port="0" to-layer="55" to-port="0" />
<edge from-layer="49" from-port="1" to-layer="55" to-port="1" />
<edge from-layer="50" from-port="1" to-layer="51" to-port="0" />
<edge from-layer="51" from-port="1" to-layer="53" to-port="0" />
<edge from-layer="52" from-port="0" to-layer="53" to-port="1" />
<edge from-layer="53" from-port="2" to-layer="54" to-port="1" />
<edge from-layer="54" from-port="2" to-layer="55" to-port="2" />
<edge from-layer="55" from-port="3" to-layer="56" to-port="1" />
<edge from-layer="56" from-port="2" to-layer="57" to-port="1" />
<edge from-layer="57" from-port="2" to-layer="59" to-port="0" />
<edge from-layer="58" from-port="0" to-layer="59" to-port="1" />
<edge from-layer="59" from-port="2" to-layer="70" to-port="0" />
<edge from-layer="59" from-port="2" to-layer="63" to-port="0" />
<edge from-layer="60" from-port="0" to-layer="62" to-port="0" />
<edge from-layer="60" from-port="0" to-layer="69" to-port="0" />
<edge from-layer="61" from-port="0" to-layer="68" to-port="0" />
<edge from-layer="61" from-port="0" to-layer="67" to-port="0" />
<edge from-layer="62" from-port="1" to-layer="68" to-port="1" />
<edge from-layer="63" from-port="1" to-layer="64" to-port="0" />
<edge from-layer="64" from-port="1" to-layer="66" to-port="0" />
<edge from-layer="65" from-port="0" to-layer="66" to-port="1" />
<edge from-layer="66" from-port="2" to-layer="67" to-port="1" />
<edge from-layer="67" from-port="2" to-layer="68" to-port="2" />
<edge from-layer="68" from-port="3" to-layer="69" to-port="1" />
<edge from-layer="69" from-port="2" to-layer="70" to-port="1" />
<edge from-layer="70" from-port="2" to-layer="71" to-port="1" />
<edge from-layer="71" from-port="2" to-layer="72" to-port="1" />
<edge from-layer="72" from-port="2" to-layer="82" to-port="0" />
<edge from-layer="73" from-port="0" to-layer="81" to-port="0" />
<edge from-layer="73" from-port="0" to-layer="75" to-port="0" />
<edge from-layer="74" from-port="0" to-layer="80" to-port="0" />
<edge from-layer="74" from-port="0" to-layer="79" to-port="1" />
<edge from-layer="75" from-port="1" to-layer="78" to-port="0" />
<edge from-layer="76" from-port="0" to-layer="78" to-port="1" />
<edge from-layer="77" from-port="0" to-layer="78" to-port="2" />
<edge from-layer="78" from-port="3" to-layer="79" to-port="0" />
<edge from-layer="78" from-port="4" to-layer="80" to-port="2" />
<edge from-layer="79" from-port="2" to-layer="80" to-port="1" />
<edge from-layer="80" from-port="3" to-layer="81" to-port="1" />
<edge from-layer="81" from-port="2" to-layer="82" to-port="1" />
<edge from-layer="82" from-port="2" to-layer="93" to-port="0" />
<edge from-layer="82" from-port="2" to-layer="86" to-port="0" />
<edge from-layer="83" from-port="0" to-layer="92" to-port="0" />
<edge from-layer="83" from-port="0" to-layer="85" to-port="0" />
<edge from-layer="84" from-port="0" to-layer="90" to-port="0" />
<edge from-layer="84" from-port="0" to-layer="91" to-port="0" />
<edge from-layer="85" from-port="1" to-layer="91" to-port="1" />
<edge from-layer="86" from-port="1" to-layer="87" to-port="0" />
<edge from-layer="87" from-port="1" to-layer="89" to-port="0" />
<edge from-layer="88" from-port="0" to-layer="89" to-port="1" />
<edge from-layer="89" from-port="2" to-layer="90" to-port="1" />
<edge from-layer="90" from-port="2" to-layer="91" to-port="2" />
<edge from-layer="91" from-port="3" to-layer="92" to-port="1" />
<edge from-layer="92" from-port="2" to-layer="93" to-port="1" />
<edge from-layer="93" from-port="2" to-layer="94" to-port="1" />
<edge from-layer="94" from-port="2" to-layer="95" to-port="1" />
<edge from-layer="95" from-port="2" to-layer="97" to-port="0" />
<edge from-layer="96" from-port="0" to-layer="97" to-port="1" />
<edge from-layer="97" from-port="2" to-layer="108" to-port="0" />
<edge from-layer="97" from-port="2" to-layer="101" to-port="0" />
<edge from-layer="98" from-port="0" to-layer="107" to-port="0" />
<edge from-layer="98" from-port="0" to-layer="100" to-port="0" />
<edge from-layer="99" from-port="0" to-layer="106" to-port="0" />
<edge from-layer="99" from-port="0" to-layer="105" to-port="0" />
<edge from-layer="100" from-port="1" to-layer="106" to-port="1" />
<edge from-layer="101" from-port="1" to-layer="102" to-port="0" />
<edge from-layer="102" from-port="1" to-layer="104" to-port="0" />
<edge from-layer="103" from-port="0" to-layer="104" to-port="1" />
<edge from-layer="104" from-port="2" to-layer="105" to-port="1" />
<edge from-layer="105" from-port="2" to-layer="106" to-port="2" />
<edge from-layer="106" from-port="3" to-layer="107" to-port="1" />
<edge from-layer="107" from-port="2" to-layer="108" to-port="1" />
<edge from-layer="108" from-port="2" to-layer="110" to-port="0" />
<edge from-layer="108" from-port="2" to-layer="160" to-port="0" />
<edge from-layer="109" from-port="0" to-layer="110" to-port="1" />
<edge from-layer="110" from-port="2" to-layer="114" to-port="0" />
<edge from-layer="110" from-port="2" to-layer="121" to-port="0" />
<edge from-layer="111" from-port="0" to-layer="113" to-port="0" />
<edge from-layer="111" from-port="0" to-layer="120" to-port="0" />
<edge from-layer="112" from-port="0" to-layer="118" to-port="0" />
<edge from-layer="112" from-port="0" to-layer="119" to-port="0" />
<edge from-layer="113" from-port="1" to-layer="119" to-port="1" />
<edge from-layer="114" from-port="1" to-layer="115" to-port="0" />
<edge from-layer="115" from-port="1" to-layer="117" to-port="0" />
<edge from-layer="116" from-port="0" to-layer="117" to-port="1" />
<edge from-layer="117" from-port="2" to-layer="118" to-port="1" />
<edge from-layer="118" from-port="2" to-layer="119" to-port="2" />
<edge from-layer="119" from-port="3" to-layer="120" to-port="1" />
<edge from-layer="120" from-port="2" to-layer="121" to-port="1" />
<edge from-layer="121" from-port="2" to-layer="122" to-port="1" />
<edge from-layer="122" from-port="2" to-layer="123" to-port="1" />
<edge from-layer="123" from-port="2" to-layer="133" to-port="0" />
<edge from-layer="124" from-port="0" to-layer="126" to-port="0" />
<edge from-layer="124" from-port="0" to-layer="132" to-port="0" />
<edge from-layer="125" from-port="0" to-layer="131" to-port="0" />
<edge from-layer="125" from-port="0" to-layer="130" to-port="1" />
<edge from-layer="126" from-port="1" to-layer="129" to-port="0" />
<edge from-layer="127" from-port="0" to-layer="129" to-port="1" />
<edge from-layer="128" from-port="0" to-layer="129" to-port="2" />
<edge from-layer="129" from-port="4" to-layer="131" to-port="2" />
<edge from-layer="129" from-port="3" to-layer="130" to-port="0" />
<edge from-layer="130" from-port="2" to-layer="131" to-port="1" />
<edge from-layer="131" from-port="3" to-layer="132" to-port="1" />
<edge from-layer="132" from-port="2" to-layer="133" to-port="1" />
<edge from-layer="133" from-port="2" to-layer="144" to-port="0" />
<edge from-layer="133" from-port="2" to-layer="137" to-port="0" />
<edge from-layer="134" from-port="0" to-layer="143" to-port="0" />
<edge from-layer="134" from-port="0" to-layer="136" to-port="0" />
<edge from-layer="135" from-port="0" to-layer="142" to-port="0" />
<edge from-layer="135" from-port="0" to-layer="141" to-port="0" />
<edge from-layer="136" from-port="1" to-layer="142" to-port="1" />
<edge from-layer="137" from-port="1" to-layer="138" to-port="0" />
<edge from-layer="138" from-port="1" to-layer="140" to-port="0" />
<edge from-layer="139" from-port="0" to-layer="140" to-port="1" />
<edge from-layer="140" from-port="2" to-layer="141" to-port="1" />
<edge from-layer="141" from-port="2" to-layer="142" to-port="2" />
<edge from-layer="142" from-port="3" to-layer="143" to-port="1" />
<edge from-layer="143" from-port="2" to-layer="144" to-port="1" />
<edge from-layer="144" from-port="2" to-layer="145" to-port="1" />
<edge from-layer="145" from-port="2" to-layer="146" to-port="1" />
<edge from-layer="146" from-port="2" to-layer="148" to-port="0" />
<edge from-layer="147" from-port="0" to-layer="148" to-port="1" />
<edge from-layer="148" from-port="2" to-layer="152" to-port="0" />
<edge from-layer="148" from-port="2" to-layer="159" to-port="0" />
<edge from-layer="149" from-port="0" to-layer="151" to-port="0" />
<edge from-layer="149" from-port="0" to-layer="158" to-port="0" />
<edge from-layer="150" from-port="0" to-layer="156" to-port="0" />
<edge from-layer="150" from-port="0" to-layer="157" to-port="0" />
<edge from-layer="151" from-port="1" to-layer="157" to-port="1" />
<edge from-layer="152" from-port="1" to-layer="153" to-port="0" />
<edge from-layer="153" from-port="1" to-layer="155" to-port="0" />
<edge from-layer="154" from-port="0" to-layer="155" to-port="1" />
<edge from-layer="155" from-port="2" to-layer="156" to-port="1" />
<edge from-layer="156" from-port="2" to-layer="157" to-port="2" />
<edge from-layer="157" from-port="3" to-layer="158" to-port="1" />
<edge from-layer="158" from-port="2" to-layer="159" to-port="1" />
<edge from-layer="159" from-port="2" to-layer="160" to-port="1" />
<edge from-layer="160" from-port="2" to-layer="176" to-port="0" />
<edge from-layer="160" from-port="2" to-layer="162" to-port="0" />
<edge from-layer="161" from-port="0" to-layer="162" to-port="1" />
<edge from-layer="162" from-port="2" to-layer="173" to-port="0" />
<edge from-layer="162" from-port="2" to-layer="166" to-port="0" />
<edge from-layer="163" from-port="0" to-layer="172" to-port="0" />
<edge from-layer="163" from-port="0" to-layer="165" to-port="0" />
<edge from-layer="164" from-port="0" to-layer="170" to-port="0" />
<edge from-layer="164" from-port="0" to-layer="171" to-port="0" />
<edge from-layer="165" from-port="1" to-layer="171" to-port="1" />
<edge from-layer="166" from-port="1" to-layer="167" to-port="0" />
<edge from-layer="167" from-port="1" to-layer="169" to-port="0" />
<edge from-layer="168" from-port="0" to-layer="169" to-port="1" />
<edge from-layer="169" from-port="2" to-layer="170" to-port="1" />
<edge from-layer="170" from-port="2" to-layer="171" to-port="2" />
<edge from-layer="171" from-port="3" to-layer="172" to-port="1" />
<edge from-layer="172" from-port="2" to-layer="173" to-port="1" />
<edge from-layer="173" from-port="2" to-layer="174" to-port="0" />
<edge from-layer="174" from-port="1" to-layer="612" to-port="0" />
<edge from-layer="175" from-port="0" to-layer="176" to-port="1" />
<edge from-layer="176" from-port="2" to-layer="180" to-port="0" />
<edge from-layer="176" from-port="2" to-layer="187" to-port="0" />
<edge from-layer="177" from-port="0" to-layer="186" to-port="0" />
<edge from-layer="177" from-port="0" to-layer="179" to-port="0" />
<edge from-layer="178" from-port="0" to-layer="185" to-port="0" />
<edge from-layer="178" from-port="0" to-layer="184" to-port="0" />
<edge from-layer="179" from-port="1" to-layer="185" to-port="1" />
<edge from-layer="180" from-port="1" to-layer="181" to-port="0" />
<edge from-layer="181" from-port="1" to-layer="183" to-port="0" />
<edge from-layer="182" from-port="0" to-layer="183" to-port="1" />
<edge from-layer="183" from-port="2" to-layer="184" to-port="1" />
<edge from-layer="184" from-port="2" to-layer="185" to-port="2" />
<edge from-layer="185" from-port="3" to-layer="186" to-port="1" />
<edge from-layer="186" from-port="2" to-layer="187" to-port="1" />
<edge from-layer="187" from-port="2" to-layer="188" to-port="1" />
<edge from-layer="188" from-port="2" to-layer="189" to-port="1" />
<edge from-layer="189" from-port="2" to-layer="199" to-port="0" />
<edge from-layer="190" from-port="0" to-layer="198" to-port="0" />
<edge from-layer="190" from-port="0" to-layer="192" to-port="0" />
<edge from-layer="191" from-port="0" to-layer="197" to-port="0" />
<edge from-layer="191" from-port="0" to-layer="196" to-port="1" />
<edge from-layer="192" from-port="1" to-layer="195" to-port="0" />
<edge from-layer="193" from-port="0" to-layer="195" to-port="1" />
<edge from-layer="194" from-port="0" to-layer="195" to-port="2" />
<edge from-layer="195" from-port="4" to-layer="197" to-port="2" />
<edge from-layer="195" from-port="3" to-layer="196" to-port="0" />
<edge from-layer="196" from-port="2" to-layer="197" to-port="1" />
<edge from-layer="197" from-port="3" to-layer="198" to-port="1" />
<edge from-layer="198" from-port="2" to-layer="199" to-port="1" />
<edge from-layer="199" from-port="2" to-layer="210" to-port="0" />
<edge from-layer="199" from-port="2" to-layer="203" to-port="0" />
<edge from-layer="200" from-port="0" to-layer="202" to-port="0" />
<edge from-layer="200" from-port="0" to-layer="209" to-port="0" />
<edge from-layer="201" from-port="0" to-layer="207" to-port="0" />
<edge from-layer="201" from-port="0" to-layer="208" to-port="0" />
<edge from-layer="202" from-port="1" to-layer="208" to-port="1" />
<edge from-layer="203" from-port="1" to-layer="204" to-port="0" />
<edge from-layer="204" from-port="1" to-layer="206" to-port="0" />
<edge from-layer="205" from-port="0" to-layer="206" to-port="1" />
<edge from-layer="206" from-port="2" to-layer="207" to-port="1" />
<edge from-layer="207" from-port="2" to-layer="208" to-port="2" />
<edge from-layer="208" from-port="3" to-layer="209" to-port="1" />
<edge from-layer="209" from-port="2" to-layer="210" to-port="1" />
<edge from-layer="210" from-port="2" to-layer="211" to-port="1" />
<edge from-layer="211" from-port="2" to-layer="212" to-port="1" />
<edge from-layer="212" from-port="2" to-layer="214" to-port="0" />
<edge from-layer="213" from-port="0" to-layer="214" to-port="1" />
<edge from-layer="214" from-port="2" to-layer="225" to-port="0" />
<edge from-layer="214" from-port="2" to-layer="218" to-port="0" />
<edge from-layer="215" from-port="0" to-layer="217" to-port="0" />
<edge from-layer="215" from-port="0" to-layer="224" to-port="0" />
<edge from-layer="216" from-port="0" to-layer="222" to-port="0" />
<edge from-layer="216" from-port="0" to-layer="223" to-port="0" />
<edge from-layer="217" from-port="1" to-layer="223" to-port="1" />
<edge from-layer="218" from-port="1" to-layer="219" to-port="0" />
<edge from-layer="219" from-port="1" to-layer="221" to-port="0" />
<edge from-layer="220" from-port="0" to-layer="221" to-port="1" />
<edge from-layer="221" from-port="2" to-layer="222" to-port="1" />
<edge from-layer="222" from-port="2" to-layer="223" to-port="2" />
<edge from-layer="223" from-port="3" to-layer="224" to-port="1" />
<edge from-layer="224" from-port="2" to-layer="225" to-port="1" />
<edge from-layer="225" from-port="2" to-layer="227" to-port="0" />
<edge from-layer="225" from-port="2" to-layer="277" to-port="0" />
<edge from-layer="226" from-port="0" to-layer="227" to-port="1" />
<edge from-layer="227" from-port="2" to-layer="231" to-port="0" />
<edge from-layer="227" from-port="2" to-layer="238" to-port="0" />
<edge from-layer="228" from-port="0" to-layer="237" to-port="0" />
<edge from-layer="228" from-port="0" to-layer="230" to-port="0" />
<edge from-layer="229" from-port="0" to-layer="235" to-port="0" />
<edge from-layer="229" from-port="0" to-layer="236" to-port="0" />
<edge from-layer="230" from-port="1" to-layer="236" to-port="1" />
<edge from-layer="231" from-port="1" to-layer="232" to-port="0" />
<edge from-layer="232" from-port="1" to-layer="234" to-port="0" />
<edge from-layer="233" from-port="0" to-layer="234" to-port="1" />
<edge from-layer="234" from-port="2" to-layer="235" to-port="1" />
<edge from-layer="235" from-port="2" to-layer="236" to-port="2" />
<edge from-layer="236" from-port="3" to-layer="237" to-port="1" />
<edge from-layer="237" from-port="2" to-layer="238" to-port="1" />
<edge from-layer="238" from-port="2" to-layer="239" to-port="1" />
<edge from-layer="239" from-port="2" to-layer="240" to-port="1" />
<edge from-layer="240" from-port="2" to-layer="250" to-port="0" />
<edge from-layer="241" from-port="0" to-layer="249" to-port="0" />
<edge from-layer="241" from-port="0" to-layer="243" to-port="0" />
<edge from-layer="242" from-port="0" to-layer="247" to-port="1" />
<edge from-layer="242" from-port="0" to-layer="248" to-port="0" />
<edge from-layer="243" from-port="1" to-layer="246" to-port="0" />
<edge from-layer="244" from-port="0" to-layer="246" to-port="1" />
<edge from-layer="245" from-port="0" to-layer="246" to-port="2" />
<edge from-layer="246" from-port="4" to-layer="248" to-port="2" />
<edge from-layer="246" from-port="3" to-layer="247" to-port="0" />
<edge from-layer="247" from-port="2" to-layer="248" to-port="1" />
<edge from-layer="248" from-port="3" to-layer="249" to-port="1" />
<edge from-layer="249" from-port="2" to-layer="250" to-port="1" />
<edge from-layer="250" from-port="2" to-layer="254" to-port="0" />
<edge from-layer="250" from-port="2" to-layer="261" to-port="0" />
<edge from-layer="251" from-port="0" to-layer="253" to-port="0" />
<edge from-layer="251" from-port="0" to-layer="260" to-port="0" />
<edge from-layer="252" from-port="0" to-layer="259" to-port="0" />
<edge from-layer="252" from-port="0" to-layer="258" to-port="0" />
<edge from-layer="253" from-port="1" to-layer="259" to-port="1" />
<edge from-layer="254" from-port="1" to-layer="255" to-port="0" />
<edge from-layer="255" from-port="1" to-layer="257" to-port="0" />
<edge from-layer="256" from-port="0" to-layer="257" to-port="1" />
<edge from-layer="257" from-port="2" to-layer="258" to-port="1" />
<edge from-layer="258" from-port="2" to-layer="259" to-port="2" />
<edge from-layer="259" from-port="3" to-layer="260" to-port="1" />
<edge from-layer="260" from-port="2" to-layer="261" to-port="1" />
<edge from-layer="261" from-port="2" to-layer="262" to-port="1" />
<edge from-layer="262" from-port="2" to-layer="263" to-port="1" />
<edge from-layer="263" from-port="2" to-layer="265" to-port="0" />
<edge from-layer="264" from-port="0" to-layer="265" to-port="1" />
<edge from-layer="265" from-port="2" to-layer="276" to-port="0" />
<edge from-layer="265" from-port="2" to-layer="269" to-port="0" />
<edge from-layer="266" from-port="0" to-layer="275" to-port="0" />
<edge from-layer="266" from-port="0" to-layer="268" to-port="0" />
<edge from-layer="267" from-port="0" to-layer="274" to-port="0" />
<edge from-layer="267" from-port="0" to-layer="273" to-port="0" />
<edge from-layer="268" from-port="1" to-layer="274" to-port="1" />
<edge from-layer="269" from-port="1" to-layer="270" to-port="0" />
<edge from-layer="270" from-port="1" to-layer="272" to-port="0" />
<edge from-layer="271" from-port="0" to-layer="272" to-port="1" />
<edge from-layer="272" from-port="2" to-layer="273" to-port="1" />
<edge from-layer="273" from-port="2" to-layer="274" to-port="2" />
<edge from-layer="274" from-port="3" to-layer="275" to-port="1" />
<edge from-layer="275" from-port="2" to-layer="276" to-port="1" />
<edge from-layer="276" from-port="2" to-layer="277" to-port="1" />
<edge from-layer="277" from-port="2" to-layer="279" to-port="0" />
<edge from-layer="277" from-port="2" to-layer="329" to-port="0" />
<edge from-layer="278" from-port="0" to-layer="279" to-port="1" />
<edge from-layer="279" from-port="2" to-layer="290" to-port="0" />
<edge from-layer="279" from-port="2" to-layer="283" to-port="0" />
<edge from-layer="280" from-port="0" to-layer="282" to-port="0" />
<edge from-layer="280" from-port="0" to-layer="289" to-port="0" />
<edge from-layer="281" from-port="0" to-layer="288" to-port="0" />
<edge from-layer="281" from-port="0" to-layer="287" to-port="0" />
<edge from-layer="282" from-port="1" to-layer="288" to-port="1" />
<edge from-layer="283" from-port="1" to-layer="284" to-port="0" />
<edge from-layer="284" from-port="1" to-layer="286" to-port="0" />
<edge from-layer="285" from-port="0" to-layer="286" to-port="1" />
<edge from-layer="286" from-port="2" to-layer="287" to-port="1" />
<edge from-layer="287" from-port="2" to-layer="288" to-port="2" />
<edge from-layer="288" from-port="3" to-layer="289" to-port="1" />
<edge from-layer="289" from-port="2" to-layer="290" to-port="1" />
<edge from-layer="290" from-port="2" to-layer="291" to-port="1" />
<edge from-layer="291" from-port="2" to-layer="292" to-port="1" />
<edge from-layer="292" from-port="2" to-layer="302" to-port="0" />
<edge from-layer="293" from-port="0" to-layer="301" to-port="0" />
<edge from-layer="293" from-port="0" to-layer="295" to-port="0" />
<edge from-layer="294" from-port="0" to-layer="299" to-port="1" />
<edge from-layer="294" from-port="0" to-layer="300" to-port="0" />
<edge from-layer="295" from-port="1" to-layer="298" to-port="0" />
<edge from-layer="296" from-port="0" to-layer="298" to-port="1" />
<edge from-layer="297" from-port="0" to-layer="298" to-port="2" />
<edge from-layer="298" from-port="3" to-layer="299" to-port="0" />
<edge from-layer="298" from-port="4" to-layer="300" to-port="2" />
<edge from-layer="299" from-port="2" to-layer="300" to-port="1" />
<edge from-layer="300" from-port="3" to-layer="301" to-port="1" />
<edge from-layer="301" from-port="2" to-layer="302" to-port="1" />
<edge from-layer="302" from-port="2" to-layer="313" to-port="0" />
<edge from-layer="302" from-port="2" to-layer="306" to-port="0" />
<edge from-layer="303" from-port="0" to-layer="305" to-port="0" />
<edge from-layer="303" from-port="0" to-layer="312" to-port="0" />
<edge from-layer="304" from-port="0" to-layer="311" to-port="0" />
<edge from-layer="304" from-port="0" to-layer="310" to-port="0" />
<edge from-layer="305" from-port="1" to-layer="311" to-port="1" />
<edge from-layer="306" from-port="1" to-layer="307" to-port="0" />
<edge from-layer="307" from-port="1" to-layer="309" to-port="0" />
<edge from-layer="308" from-port="0" to-layer="309" to-port="1" />
<edge from-layer="309" from-port="2" to-layer="310" to-port="1" />
<edge from-layer="310" from-port="2" to-layer="311" to-port="2" />
<edge from-layer="311" from-port="3" to-layer="312" to-port="1" />
<edge from-layer="312" from-port="2" to-layer="313" to-port="1" />
<edge from-layer="313" from-port="2" to-layer="314" to-port="1" />
<edge from-layer="314" from-port="2" to-layer="315" to-port="1" />
<edge from-layer="315" from-port="2" to-layer="317" to-port="0" />
<edge from-layer="316" from-port="0" to-layer="317" to-port="1" />
<edge from-layer="317" from-port="2" to-layer="321" to-port="0" />
<edge from-layer="317" from-port="2" to-layer="328" to-port="0" />
<edge from-layer="318" from-port="0" to-layer="327" to-port="0" />
<edge from-layer="318" from-port="0" to-layer="320" to-port="0" />
<edge from-layer="319" from-port="0" to-layer="325" to-port="0" />
<edge from-layer="319" from-port="0" to-layer="326" to-port="0" />
<edge from-layer="320" from-port="1" to-layer="326" to-port="1" />
<edge from-layer="321" from-port="1" to-layer="322" to-port="0" />
<edge from-layer="322" from-port="1" to-layer="324" to-port="0" />
<edge from-layer="323" from-port="0" to-layer="324" to-port="1" />
<edge from-layer="324" from-port="2" to-layer="325" to-port="1" />
<edge from-layer="325" from-port="2" to-layer="326" to-port="2" />
<edge from-layer="326" from-port="3" to-layer="327" to-port="1" />
<edge from-layer="327" from-port="2" to-layer="328" to-port="1" />
<edge from-layer="328" from-port="2" to-layer="329" to-port="1" />
<edge from-layer="329" from-port="2" to-layer="345" to-port="0" />
<edge from-layer="329" from-port="2" to-layer="331" to-port="0" />
<edge from-layer="330" from-port="0" to-layer="331" to-port="1" />
<edge from-layer="331" from-port="2" to-layer="335" to-port="0" />
<edge from-layer="331" from-port="2" to-layer="342" to-port="0" />
<edge from-layer="332" from-port="0" to-layer="334" to-port="0" />
<edge from-layer="332" from-port="0" to-layer="341" to-port="0" />
<edge from-layer="333" from-port="0" to-layer="339" to-port="0" />
<edge from-layer="333" from-port="0" to-layer="340" to-port="0" />
<edge from-layer="334" from-port="1" to-layer="340" to-port="1" />
<edge from-layer="335" from-port="1" to-layer="336" to-port="0" />
<edge from-layer="336" from-port="1" to-layer="338" to-port="0" />
<edge from-layer="337" from-port="0" to-layer="338" to-port="1" />
<edge from-layer="338" from-port="2" to-layer="339" to-port="1" />
<edge from-layer="339" from-port="2" to-layer="340" to-port="2" />
<edge from-layer="340" from-port="3" to-layer="341" to-port="1" />
<edge from-layer="341" from-port="2" to-layer="342" to-port="1" />
<edge from-layer="342" from-port="2" to-layer="343" to-port="0" />
<edge from-layer="343" from-port="1" to-layer="567" to-port="0" />
<edge from-layer="344" from-port="0" to-layer="345" to-port="1" />
<edge from-layer="345" from-port="2" to-layer="356" to-port="0" />
<edge from-layer="345" from-port="2" to-layer="349" to-port="0" />
<edge from-layer="346" from-port="0" to-layer="355" to-port="0" />
<edge from-layer="346" from-port="0" to-layer="348" to-port="0" />
<edge from-layer="347" from-port="0" to-layer="353" to-port="0" />
<edge from-layer="347" from-port="0" to-layer="354" to-port="0" />
<edge from-layer="348" from-port="1" to-layer="354" to-port="1" />
<edge from-layer="349" from-port="1" to-layer="350" to-port="0" />
<edge from-layer="350" from-port="1" to-layer="352" to-port="0" />
<edge from-layer="351" from-port="0" to-layer="352" to-port="1" />
<edge from-layer="352" from-port="2" to-layer="353" to-port="1" />
<edge from-layer="353" from-port="2" to-layer="354" to-port="2" />
<edge from-layer="354" from-port="3" to-layer="355" to-port="1" />
<edge from-layer="355" from-port="2" to-layer="356" to-port="1" />
<edge from-layer="356" from-port="2" to-layer="357" to-port="1" />
<edge from-layer="357" from-port="2" to-layer="358" to-port="1" />
<edge from-layer="358" from-port="2" to-layer="368" to-port="0" />
<edge from-layer="359" from-port="0" to-layer="367" to-port="0" />
<edge from-layer="359" from-port="0" to-layer="361" to-port="0" />
<edge from-layer="360" from-port="0" to-layer="365" to-port="1" />
<edge from-layer="360" from-port="0" to-layer="366" to-port="0" />
<edge from-layer="361" from-port="1" to-layer="364" to-port="0" />
<edge from-layer="362" from-port="0" to-layer="364" to-port="1" />
<edge from-layer="363" from-port="0" to-layer="364" to-port="2" />
<edge from-layer="364" from-port="3" to-layer="365" to-port="0" />
<edge from-layer="364" from-port="4" to-layer="366" to-port="2" />
<edge from-layer="365" from-port="2" to-layer="366" to-port="1" />
<edge from-layer="366" from-port="3" to-layer="367" to-port="1" />
<edge from-layer="367" from-port="2" to-layer="368" to-port="1" />
<edge from-layer="368" from-port="2" to-layer="372" to-port="0" />
<edge from-layer="368" from-port="2" to-layer="379" to-port="0" />
<edge from-layer="369" from-port="0" to-layer="371" to-port="0" />
<edge from-layer="369" from-port="0" to-layer="378" to-port="0" />
<edge from-layer="370" from-port="0" to-layer="377" to-port="0" />
<edge from-layer="370" from-port="0" to-layer="376" to-port="0" />
<edge from-layer="371" from-port="1" to-layer="377" to-port="1" />
<edge from-layer="372" from-port="1" to-layer="373" to-port="0" />
<edge from-layer="373" from-port="1" to-layer="375" to-port="0" />
<edge from-layer="374" from-port="0" to-layer="375" to-port="1" />
<edge from-layer="375" from-port="2" to-layer="376" to-port="1" />
<edge from-layer="376" from-port="2" to-layer="377" to-port="2" />
<edge from-layer="377" from-port="3" to-layer="378" to-port="1" />
<edge from-layer="378" from-port="2" to-layer="379" to-port="1" />
<edge from-layer="379" from-port="2" to-layer="380" to-port="1" />
<edge from-layer="380" from-port="2" to-layer="381" to-port="1" />
<edge from-layer="381" from-port="2" to-layer="383" to-port="0" />
<edge from-layer="382" from-port="0" to-layer="383" to-port="1" />
<edge from-layer="383" from-port="2" to-layer="394" to-port="0" />
<edge from-layer="383" from-port="2" to-layer="387" to-port="0" />
<edge from-layer="384" from-port="0" to-layer="386" to-port="0" />
<edge from-layer="384" from-port="0" to-layer="393" to-port="0" />
<edge from-layer="385" from-port="0" to-layer="391" to-port="0" />
<edge from-layer="385" from-port="0" to-layer="392" to-port="0" />
<edge from-layer="386" from-port="1" to-layer="392" to-port="1" />
<edge from-layer="387" from-port="1" to-layer="388" to-port="0" />
<edge from-layer="388" from-port="1" to-layer="390" to-port="0" />
<edge from-layer="389" from-port="0" to-layer="390" to-port="1" />
<edge from-layer="390" from-port="2" to-layer="391" to-port="1" />
<edge from-layer="391" from-port="2" to-layer="392" to-port="2" />
<edge from-layer="392" from-port="3" to-layer="393" to-port="1" />
<edge from-layer="393" from-port="2" to-layer="394" to-port="1" />
<edge from-layer="394" from-port="2" to-layer="396" to-port="0" />
<edge from-layer="394" from-port="2" to-layer="446" to-port="0" />
<edge from-layer="395" from-port="0" to-layer="396" to-port="1" />
<edge from-layer="396" from-port="2" to-layer="400" to-port="0" />
<edge from-layer="396" from-port="2" to-layer="407" to-port="0" />
<edge from-layer="397" from-port="0" to-layer="399" to-port="0" />
<edge from-layer="397" from-port="0" to-layer="406" to-port="0" />
<edge from-layer="398" from-port="0" to-layer="405" to-port="0" />
<edge from-layer="398" from-port="0" to-layer="404" to-port="0" />
<edge from-layer="399" from-port="1" to-layer="405" to-port="1" />
<edge from-layer="400" from-port="1" to-layer="401" to-port="0" />
<edge from-layer="401" from-port="1" to-layer="403" to-port="0" />
<edge from-layer="402" from-port="0" to-layer="403" to-port="1" />
<edge from-layer="403" from-port="2" to-layer="404" to-port="1" />
<edge from-layer="404" from-port="2" to-layer="405" to-port="2" />
<edge from-layer="405" from-port="3" to-layer="406" to-port="1" />
<edge from-layer="406" from-port="2" to-layer="407" to-port="1" />
<edge from-layer="407" from-port="2" to-layer="408" to-port="1" />
<edge from-layer="408" from-port="2" to-layer="409" to-port="1" />
<edge from-layer="409" from-port="2" to-layer="419" to-port="0" />
<edge from-layer="410" from-port="0" to-layer="418" to-port="0" />
<edge from-layer="410" from-port="0" to-layer="412" to-port="0" />
<edge from-layer="411" from-port="0" to-layer="416" to-port="1" />
<edge from-layer="411" from-port="0" to-layer="417" to-port="0" />
<edge from-layer="412" from-port="1" to-layer="415" to-port="0" />
<edge from-layer="413" from-port="0" to-layer="415" to-port="1" />
<edge from-layer="414" from-port="0" to-layer="415" to-port="2" />
<edge from-layer="415" from-port="3" to-layer="416" to-port="0" />
<edge from-layer="415" from-port="4" to-layer="417" to-port="2" />
<edge from-layer="416" from-port="2" to-layer="417" to-port="1" />
<edge from-layer="417" from-port="3" to-layer="418" to-port="1" />
<edge from-layer="418" from-port="2" to-layer="419" to-port="1" />
<edge from-layer="419" from-port="2" to-layer="430" to-port="0" />
<edge from-layer="419" from-port="2" to-layer="423" to-port="0" />
<edge from-layer="420" from-port="0" to-layer="422" to-port="0" />
<edge from-layer="420" from-port="0" to-layer="429" to-port="0" />
<edge from-layer="421" from-port="0" to-layer="427" to-port="0" />
<edge from-layer="421" from-port="0" to-layer="428" to-port="0" />
<edge from-layer="422" from-port="1" to-layer="428" to-port="1" />
<edge from-layer="423" from-port="1" to-layer="424" to-port="0" />
<edge from-layer="424" from-port="1" to-layer="426" to-port="0" />
<edge from-layer="425" from-port="0" to-layer="426" to-port="1" />
<edge from-layer="426" from-port="2" to-layer="427" to-port="1" />
<edge from-layer="427" from-port="2" to-layer="428" to-port="2" />
<edge from-layer="428" from-port="3" to-layer="429" to-port="1" />
<edge from-layer="429" from-port="2" to-layer="430" to-port="1" />
<edge from-layer="430" from-port="2" to-layer="431" to-port="1" />
<edge from-layer="431" from-port="2" to-layer="432" to-port="1" />
<edge from-layer="432" from-port="2" to-layer="434" to-port="0" />
<edge from-layer="433" from-port="0" to-layer="434" to-port="1" />
<edge from-layer="434" from-port="2" to-layer="438" to-port="0" />
<edge from-layer="434" from-port="2" to-layer="445" to-port="0" />
<edge from-layer="435" from-port="0" to-layer="444" to-port="0" />
<edge from-layer="435" from-port="0" to-layer="437" to-port="0" />
<edge from-layer="436" from-port="0" to-layer="442" to-port="0" />
<edge from-layer="436" from-port="0" to-layer="443" to-port="0" />
<edge from-layer="437" from-port="1" to-layer="443" to-port="1" />
<edge from-layer="438" from-port="1" to-layer="439" to-port="0" />
<edge from-layer="439" from-port="1" to-layer="441" to-port="0" />
<edge from-layer="440" from-port="0" to-layer="441" to-port="1" />
<edge from-layer="441" from-port="2" to-layer="442" to-port="1" />
<edge from-layer="442" from-port="2" to-layer="443" to-port="2" />
<edge from-layer="443" from-port="3" to-layer="444" to-port="1" />
<edge from-layer="444" from-port="2" to-layer="445" to-port="1" />
<edge from-layer="445" from-port="2" to-layer="446" to-port="1" />
<edge from-layer="446" from-port="2" to-layer="448" to-port="0" />
<edge from-layer="446" from-port="2" to-layer="498" to-port="0" />
<edge from-layer="447" from-port="0" to-layer="448" to-port="1" />
<edge from-layer="448" from-port="2" to-layer="452" to-port="0" />
<edge from-layer="448" from-port="2" to-layer="459" to-port="0" />
<edge from-layer="449" from-port="0" to-layer="451" to-port="0" />
<edge from-layer="449" from-port="0" to-layer="458" to-port="0" />
<edge from-layer="450" from-port="0" to-layer="457" to-port="0" />
<edge from-layer="450" from-port="0" to-layer="456" to-port="0" />
<edge from-layer="451" from-port="1" to-layer="457" to-port="1" />
<edge from-layer="452" from-port="1" to-layer="453" to-port="0" />
<edge from-layer="453" from-port="1" to-layer="455" to-port="0" />
<edge from-layer="454" from-port="0" to-layer="455" to-port="1" />
<edge from-layer="455" from-port="2" to-layer="456" to-port="1" />
<edge from-layer="456" from-port="2" to-layer="457" to-port="2" />
<edge from-layer="457" from-port="3" to-layer="458" to-port="1" />
<edge from-layer="458" from-port="2" to-layer="459" to-port="1" />
<edge from-layer="459" from-port="2" to-layer="460" to-port="1" />
<edge from-layer="460" from-port="2" to-layer="461" to-port="1" />
<edge from-layer="461" from-port="2" to-layer="471" to-port="0" />
<edge from-layer="462" from-port="0" to-layer="464" to-port="0" />
<edge from-layer="462" from-port="0" to-layer="470" to-port="0" />
<edge from-layer="463" from-port="0" to-layer="468" to-port="1" />
<edge from-layer="463" from-port="0" to-layer="469" to-port="0" />
<edge from-layer="464" from-port="1" to-layer="467" to-port="0" />
<edge from-layer="465" from-port="0" to-layer="467" to-port="1" />
<edge from-layer="466" from-port="0" to-layer="467" to-port="2" />
<edge from-layer="467" from-port="4" to-layer="469" to-port="2" />
<edge from-layer="467" from-port="3" to-layer="468" to-port="0" />
<edge from-layer="468" from-port="2" to-layer="469" to-port="1" />
<edge from-layer="469" from-port="3" to-layer="470" to-port="1" />
<edge from-layer="470" from-port="2" to-layer="471" to-port="1" />
<edge from-layer="471" from-port="2" to-layer="482" to-port="0" />
<edge from-layer="471" from-port="2" to-layer="475" to-port="0" />
<edge from-layer="472" from-port="0" to-layer="481" to-port="0" />
<edge from-layer="472" from-port="0" to-layer="474" to-port="0" />
<edge from-layer="473" from-port="0" to-layer="480" to-port="0" />
<edge from-layer="473" from-port="0" to-layer="479" to-port="0" />
<edge from-layer="474" from-port="1" to-layer="480" to-port="1" />
<edge from-layer="475" from-port="1" to-layer="476" to-port="0" />
<edge from-layer="476" from-port="1" to-layer="478" to-port="0" />
<edge from-layer="477" from-port="0" to-layer="478" to-port="1" />
<edge from-layer="478" from-port="2" to-layer="479" to-port="1" />
<edge from-layer="479" from-port="2" to-layer="480" to-port="2" />
<edge from-layer="480" from-port="3" to-layer="481" to-port="1" />
<edge from-layer="481" from-port="2" to-layer="482" to-port="1" />
<edge from-layer="482" from-port="2" to-layer="483" to-port="1" />
<edge from-layer="483" from-port="2" to-layer="484" to-port="1" />
<edge from-layer="484" from-port="2" to-layer="486" to-port="0" />
<edge from-layer="485" from-port="0" to-layer="486" to-port="1" />
<edge from-layer="486" from-port="2" to-layer="490" to-port="0" />
<edge from-layer="486" from-port="2" to-layer="497" to-port="0" />
<edge from-layer="487" from-port="0" to-layer="489" to-port="0" />
<edge from-layer="487" from-port="0" to-layer="496" to-port="0" />
<edge from-layer="488" from-port="0" to-layer="494" to-port="0" />
<edge from-layer="488" from-port="0" to-layer="495" to-port="0" />
<edge from-layer="489" from-port="1" to-layer="495" to-port="1" />
<edge from-layer="490" from-port="1" to-layer="491" to-port="0" />
<edge from-layer="491" from-port="1" to-layer="493" to-port="0" />
<edge from-layer="492" from-port="0" to-layer="493" to-port="1" />
<edge from-layer="493" from-port="2" to-layer="494" to-port="1" />
<edge from-layer="494" from-port="2" to-layer="495" to-port="2" />
<edge from-layer="495" from-port="3" to-layer="496" to-port="1" />
<edge from-layer="496" from-port="2" to-layer="497" to-port="1" />
<edge from-layer="497" from-port="2" to-layer="498" to-port="1" />
<edge from-layer="498" from-port="2" to-layer="550" to-port="0" />
<edge from-layer="498" from-port="2" to-layer="500" to-port="0" />
<edge from-layer="499" from-port="0" to-layer="500" to-port="1" />
<edge from-layer="500" from-port="2" to-layer="511" to-port="0" />
<edge from-layer="500" from-port="2" to-layer="504" to-port="0" />
<edge from-layer="501" from-port="0" to-layer="510" to-port="0" />
<edge from-layer="501" from-port="0" to-layer="503" to-port="0" />
<edge from-layer="502" from-port="0" to-layer="508" to-port="0" />
<edge from-layer="502" from-port="0" to-layer="509" to-port="0" />
<edge from-layer="503" from-port="1" to-layer="509" to-port="1" />
<edge from-layer="504" from-port="1" to-layer="505" to-port="0" />
<edge from-layer="505" from-port="1" to-layer="507" to-port="0" />
<edge from-layer="506" from-port="0" to-layer="507" to-port="1" />
<edge from-layer="507" from-port="2" to-layer="508" to-port="1" />
<edge from-layer="508" from-port="2" to-layer="509" to-port="2" />
<edge from-layer="509" from-port="3" to-layer="510" to-port="1" />
<edge from-layer="510" from-port="2" to-layer="511" to-port="1" />
<edge from-layer="511" from-port="2" to-layer="512" to-port="1" />
<edge from-layer="512" from-port="2" to-layer="513" to-port="1" />
<edge from-layer="513" from-port="2" to-layer="523" to-port="0" />
<edge from-layer="514" from-port="0" to-layer="516" to-port="0" />
<edge from-layer="514" from-port="0" to-layer="522" to-port="0" />
<edge from-layer="515" from-port="0" to-layer="520" to-port="1" />
<edge from-layer="515" from-port="0" to-layer="521" to-port="0" />
<edge from-layer="516" from-port="1" to-layer="519" to-port="0" />
<edge from-layer="517" from-port="0" to-layer="519" to-port="1" />
<edge from-layer="518" from-port="0" to-layer="519" to-port="2" />
<edge from-layer="519" from-port="3" to-layer="520" to-port="0" />
<edge from-layer="519" from-port="4" to-layer="521" to-port="2" />
<edge from-layer="520" from-port="2" to-layer="521" to-port="1" />
<edge from-layer="521" from-port="3" to-layer="522" to-port="1" />
<edge from-layer="522" from-port="2" to-layer="523" to-port="1" />
<edge from-layer="523" from-port="2" to-layer="534" to-port="0" />
<edge from-layer="523" from-port="2" to-layer="527" to-port="0" />
<edge from-layer="524" from-port="0" to-layer="533" to-port="0" />
<edge from-layer="524" from-port="0" to-layer="526" to-port="0" />
<edge from-layer="525" from-port="0" to-layer="532" to-port="0" />
<edge from-layer="525" from-port="0" to-layer="531" to-port="0" />
<edge from-layer="526" from-port="1" to-layer="532" to-port="1" />
<edge from-layer="527" from-port="1" to-layer="528" to-port="0" />
<edge from-layer="528" from-port="1" to-layer="530" to-port="0" />
<edge from-layer="529" from-port="0" to-layer="530" to-port="1" />
<edge from-layer="530" from-port="2" to-layer="531" to-port="1" />
<edge from-layer="531" from-port="2" to-layer="532" to-port="2" />
<edge from-layer="532" from-port="3" to-layer="533" to-port="1" />
<edge from-layer="533" from-port="2" to-layer="534" to-port="1" />
<edge from-layer="534" from-port="2" to-layer="535" to-port="1" />
<edge from-layer="535" from-port="2" to-layer="536" to-port="1" />
<edge from-layer="536" from-port="2" to-layer="538" to-port="0" />
<edge from-layer="537" from-port="0" to-layer="538" to-port="1" />
<edge from-layer="538" from-port="2" to-layer="542" to-port="0" />
<edge from-layer="538" from-port="2" to-layer="549" to-port="0" />
<edge from-layer="539" from-port="0" to-layer="541" to-port="0" />
<edge from-layer="539" from-port="0" to-layer="548" to-port="0" />
<edge from-layer="540" from-port="0" to-layer="546" to-port="0" />
<edge from-layer="540" from-port="0" to-layer="547" to-port="0" />
<edge from-layer="541" from-port="1" to-layer="547" to-port="1" />
<edge from-layer="542" from-port="1" to-layer="543" to-port="0" />
<edge from-layer="543" from-port="1" to-layer="545" to-port="0" />
<edge from-layer="544" from-port="0" to-layer="545" to-port="1" />
<edge from-layer="545" from-port="2" to-layer="546" to-port="1" />
<edge from-layer="546" from-port="2" to-layer="547" to-port="2" />
<edge from-layer="547" from-port="3" to-layer="548" to-port="1" />
<edge from-layer="548" from-port="2" to-layer="549" to-port="1" />
<edge from-layer="549" from-port="2" to-layer="550" to-port="1" />
<edge from-layer="550" from-port="2" to-layer="552" to-port="0" />
<edge from-layer="551" from-port="0" to-layer="552" to-port="1" />
<edge from-layer="552" from-port="2" to-layer="556" to-port="0" />
<edge from-layer="552" from-port="2" to-layer="563" to-port="0" />
<edge from-layer="553" from-port="0" to-layer="555" to-port="0" />
<edge from-layer="553" from-port="0" to-layer="562" to-port="0" />
<edge from-layer="554" from-port="0" to-layer="560" to-port="0" />
<edge from-layer="554" from-port="0" to-layer="561" to-port="0" />
<edge from-layer="555" from-port="1" to-layer="561" to-port="1" />
<edge from-layer="556" from-port="1" to-layer="557" to-port="0" />
<edge from-layer="557" from-port="1" to-layer="559" to-port="0" />
<edge from-layer="558" from-port="0" to-layer="559" to-port="1" />
<edge from-layer="559" from-port="2" to-layer="560" to-port="1" />
<edge from-layer="560" from-port="2" to-layer="561" to-port="2" />
<edge from-layer="561" from-port="3" to-layer="562" to-port="1" />
<edge from-layer="562" from-port="2" to-layer="563" to-port="1" />
<edge from-layer="563" from-port="2" to-layer="564" to-port="0" />
<edge from-layer="564" from-port="1" to-layer="566" to-port="0" />
<edge from-layer="565" from-port="0" to-layer="566" to-port="1" />
<edge from-layer="565" from-port="0" to-layer="694" to-port="1" />
<edge from-layer="565" from-port="0" to-layer="611" to-port="1" />
<edge from-layer="566" from-port="2" to-layer="567" to-port="1" />
<edge from-layer="567" from-port="2" to-layer="582" to-port="1" />
<edge from-layer="567" from-port="2" to-layer="569" to-port="0" />
<edge from-layer="568" from-port="0" to-layer="569" to-port="1" />
<edge from-layer="569" from-port="2" to-layer="573" to-port="0" />
<edge from-layer="569" from-port="2" to-layer="580" to-port="0" />
<edge from-layer="570" from-port="0" to-layer="579" to-port="0" />
<edge from-layer="570" from-port="0" to-layer="572" to-port="0" />
<edge from-layer="571" from-port="0" to-layer="577" to-port="0" />
<edge from-layer="571" from-port="0" to-layer="578" to-port="0" />
<edge from-layer="572" from-port="1" to-layer="578" to-port="1" />
<edge from-layer="573" from-port="1" to-layer="574" to-port="0" />
<edge from-layer="574" from-port="1" to-layer="576" to-port="0" />
<edge from-layer="575" from-port="0" to-layer="576" to-port="1" />
<edge from-layer="576" from-port="2" to-layer="577" to-port="1" />
<edge from-layer="577" from-port="2" to-layer="578" to-port="2" />
<edge from-layer="578" from-port="3" to-layer="579" to-port="1" />
<edge from-layer="579" from-port="2" to-layer="580" to-port="1" />
<edge from-layer="580" from-port="2" to-layer="581" to-port="0" />
<edge from-layer="581" from-port="1" to-layer="582" to-port="0" />
<edge from-layer="582" from-port="2" to-layer="584" to-port="0" />
<edge from-layer="583" from-port="0" to-layer="584" to-port="1" />
<edge from-layer="584" from-port="2" to-layer="588" to-port="0" />
<edge from-layer="584" from-port="2" to-layer="595" to-port="0" />
<edge from-layer="585" from-port="0" to-layer="587" to-port="0" />
<edge from-layer="585" from-port="0" to-layer="594" to-port="0" />
<edge from-layer="586" from-port="0" to-layer="593" to-port="0" />
<edge from-layer="586" from-port="0" to-layer="592" to-port="0" />
<edge from-layer="587" from-port="1" to-layer="593" to-port="1" />
<edge from-layer="588" from-port="1" to-layer="589" to-port="0" />
<edge from-layer="589" from-port="1" to-layer="591" to-port="0" />
<edge from-layer="590" from-port="0" to-layer="591" to-port="1" />
<edge from-layer="591" from-port="2" to-layer="592" to-port="1" />
<edge from-layer="592" from-port="2" to-layer="593" to-port="2" />
<edge from-layer="593" from-port="3" to-layer="594" to-port="1" />
<edge from-layer="594" from-port="2" to-layer="595" to-port="1" />
<edge from-layer="595" from-port="2" to-layer="596" to-port="0" />
<edge from-layer="596" from-port="1" to-layer="598" to-port="0" />
<edge from-layer="597" from-port="0" to-layer="598" to-port="1" />
<edge from-layer="598" from-port="2" to-layer="602" to-port="0" />
<edge from-layer="598" from-port="2" to-layer="609" to-port="0" />
<edge from-layer="599" from-port="0" to-layer="601" to-port="0" />
<edge from-layer="599" from-port="0" to-layer="608" to-port="0" />
<edge from-layer="600" from-port="0" to-layer="606" to-port="0" />
<edge from-layer="600" from-port="0" to-layer="607" to-port="0" />
<edge from-layer="601" from-port="1" to-layer="607" to-port="1" />
<edge from-layer="602" from-port="1" to-layer="603" to-port="0" />
<edge from-layer="603" from-port="1" to-layer="605" to-port="0" />
<edge from-layer="604" from-port="0" to-layer="605" to-port="1" />
<edge from-layer="605" from-port="2" to-layer="606" to-port="1" />
<edge from-layer="606" from-port="2" to-layer="607" to-port="2" />
<edge from-layer="607" from-port="3" to-layer="608" to-port="1" />
<edge from-layer="608" from-port="2" to-layer="609" to-port="1" />
<edge from-layer="609" from-port="2" to-layer="610" to-port="0" />
<edge from-layer="610" from-port="1" to-layer="611" to-port="0" />
<edge from-layer="611" from-port="2" to-layer="612" to-port="1" />
<edge from-layer="612" from-port="2" to-layer="614" to-port="0" />
<edge from-layer="612" from-port="2" to-layer="627" to-port="1" />
<edge from-layer="613" from-port="0" to-layer="614" to-port="1" />
<edge from-layer="614" from-port="2" to-layer="618" to-port="0" />
<edge from-layer="614" from-port="2" to-layer="625" to-port="0" />
<edge from-layer="615" from-port="0" to-layer="617" to-port="0" />
<edge from-layer="615" from-port="0" to-layer="624" to-port="0" />
<edge from-layer="616" from-port="0" to-layer="622" to-port="0" />
<edge from-layer="616" from-port="0" to-layer="623" to-port="0" />
<edge from-layer="617" from-port="1" to-layer="623" to-port="1" />
<edge from-layer="618" from-port="1" to-layer="619" to-port="0" />
<edge from-layer="619" from-port="1" to-layer="621" to-port="0" />
<edge from-layer="620" from-port="0" to-layer="621" to-port="1" />
<edge from-layer="621" from-port="2" to-layer="622" to-port="1" />
<edge from-layer="622" from-port="2" to-layer="623" to-port="2" />
<edge from-layer="623" from-port="3" to-layer="624" to-port="1" />
<edge from-layer="624" from-port="2" to-layer="625" to-port="1" />
<edge from-layer="625" from-port="2" to-layer="626" to-port="0" />
<edge from-layer="626" from-port="1" to-layer="627" to-port="0" />
<edge from-layer="627" from-port="2" to-layer="629" to-port="0" />
<edge from-layer="628" from-port="0" to-layer="629" to-port="1" />
<edge from-layer="629" from-port="2" to-layer="640" to-port="0" />
<edge from-layer="629" from-port="2" to-layer="633" to-port="0" />
<edge from-layer="630" from-port="0" to-layer="632" to-port="0" />
<edge from-layer="630" from-port="0" to-layer="639" to-port="0" />
<edge from-layer="631" from-port="0" to-layer="637" to-port="0" />
<edge from-layer="631" from-port="0" to-layer="638" to-port="0" />
<edge from-layer="632" from-port="1" to-layer="638" to-port="1" />
<edge from-layer="633" from-port="1" to-layer="634" to-port="0" />
<edge from-layer="634" from-port="1" to-layer="636" to-port="0" />
<edge from-layer="635" from-port="0" to-layer="636" to-port="1" />
<edge from-layer="636" from-port="2" to-layer="637" to-port="1" />
<edge from-layer="637" from-port="2" to-layer="638" to-port="2" />
<edge from-layer="638" from-port="3" to-layer="639" to-port="1" />
<edge from-layer="639" from-port="2" to-layer="640" to-port="1" />
<edge from-layer="640" from-port="2" to-layer="641" to-port="0" />
<edge from-layer="641" from-port="1" to-layer="643" to-port="0" />
<edge from-layer="642" from-port="0" to-layer="643" to-port="1" />
<edge from-layer="643" from-port="2" to-layer="654" to-port="0" />
<edge from-layer="643" from-port="2" to-layer="647" to-port="0" />
<edge from-layer="644" from-port="0" to-layer="653" to-port="0" />
<edge from-layer="644" from-port="0" to-layer="646" to-port="0" />
<edge from-layer="645" from-port="0" to-layer="651" to-port="0" />
<edge from-layer="645" from-port="0" to-layer="652" to-port="0" />
<edge from-layer="646" from-port="1" to-layer="652" to-port="1" />
<edge from-layer="647" from-port="1" to-layer="648" to-port="0" />
<edge from-layer="648" from-port="1" to-layer="650" to-port="0" />
<edge from-layer="649" from-port="0" to-layer="650" to-port="1" />
<edge from-layer="650" from-port="2" to-layer="651" to-port="1" />
<edge from-layer="651" from-port="2" to-layer="652" to-port="2" />
<edge from-layer="652" from-port="3" to-layer="653" to-port="1" />
<edge from-layer="653" from-port="2" to-layer="654" to-port="1" />
<edge from-layer="654" from-port="2" to-layer="655" to-port="0" />
<edge from-layer="655" from-port="1" to-layer="657" to-port="0" />
<edge from-layer="656" from-port="0" to-layer="657" to-port="1" />
<edge from-layer="657" from-port="2" to-layer="661" to-port="0" />
<edge from-layer="657" from-port="2" to-layer="668" to-port="0" />
<edge from-layer="658" from-port="0" to-layer="660" to-port="0" />
<edge from-layer="658" from-port="0" to-layer="667" to-port="0" />
<edge from-layer="659" from-port="0" to-layer="665" to-port="0" />
<edge from-layer="659" from-port="0" to-layer="666" to-port="0" />
<edge from-layer="660" from-port="1" to-layer="666" to-port="1" />
<edge from-layer="661" from-port="1" to-layer="662" to-port="0" />
<edge from-layer="662" from-port="1" to-layer="664" to-port="0" />
<edge from-layer="663" from-port="0" to-layer="664" to-port="1" />
<edge from-layer="664" from-port="2" to-layer="665" to-port="1" />
<edge from-layer="665" from-port="2" to-layer="666" to-port="2" />
<edge from-layer="666" from-port="3" to-layer="667" to-port="1" />
<edge from-layer="667" from-port="2" to-layer="668" to-port="1" />
<edge from-layer="668" from-port="2" to-layer="669" to-port="0" />
<edge from-layer="669" from-port="1" to-layer="671" to-port="0" />
<edge from-layer="670" from-port="0" to-layer="671" to-port="1" />
<edge from-layer="671" from-port="2" to-layer="675" to-port="0" />
<edge from-layer="671" from-port="2" to-layer="682" to-port="0" />
<edge from-layer="672" from-port="0" to-layer="674" to-port="0" />
<edge from-layer="672" from-port="0" to-layer="681" to-port="0" />
<edge from-layer="673" from-port="0" to-layer="679" to-port="0" />
<edge from-layer="673" from-port="0" to-layer="680" to-port="0" />
<edge from-layer="674" from-port="1" to-layer="680" to-port="1" />
<edge from-layer="675" from-port="1" to-layer="676" to-port="0" />
<edge from-layer="676" from-port="1" to-layer="678" to-port="0" />
<edge from-layer="677" from-port="0" to-layer="678" to-port="1" />
<edge from-layer="678" from-port="2" to-layer="679" to-port="1" />
<edge from-layer="679" from-port="2" to-layer="680" to-port="2" />
<edge from-layer="680" from-port="3" to-layer="681" to-port="1" />
<edge from-layer="681" from-port="2" to-layer="682" to-port="1" />
<edge from-layer="682" from-port="2" to-layer="684" to-port="0" />
<edge from-layer="683" from-port="0" to-layer="684" to-port="1" />
<edge from-layer="684" from-port="2" to-layer="691" to-port="0" />
<edge from-layer="685" from-port="0" to-layer="688" to-port="0" />
<edge from-layer="685" from-port="0" to-layer="691" to-port="1" />
<edge from-layer="686" from-port="0" to-layer="691" to-port="2" />
<edge from-layer="687" from-port="0" to-layer="689" to-port="0" />
<edge from-layer="688" from-port="1" to-layer="689" to-port="1" />
<edge from-layer="689" from-port="2" to-layer="691" to-port="3" />
<edge from-layer="690" from-port="0" to-layer="691" to-port="4" />
<edge from-layer="691" from-port="5" to-layer="693" to-port="0" />
<edge from-layer="692" from-port="0" to-layer="693" to-port="1" />
<edge from-layer="693" from-port="2" to-layer="694" to-port="0" />
<edge from-layer="694" from-port="2" to-layer="695" to-port="0" />
</edges>
<rt_info>
<info name="OpenVINO Runtime" value="2026.4.1-22982-e213a147257-releases/2026/4" />
</rt_info>
</net>
<net name="onnx_Frontend_IR" version="11">
<layers>
<layer id="0" name="serving_default_args_0" type="Parameter" version="opset1">
<data shape="1,4,512,512" element_type="f32" />
<output>
<port id="0" precision="FP32" names="serving_default_args_0">
<dim>1</dim>
<dim>4</dim>
<dim>512</dim>
<dim>512</dim>
</port>
</output>
</layer>
<layer id="1" name="Relu6__52_max__223" type="Const" version="opset1">
<data element_type="f32" shape="" offset="0" size="4" />
<output>
<port id="0" precision="FP32" names="Relu6__52_max__223" />
</output>
</layer>
<layer id="2" name="Relu6__22_min__132" type="Const" version="opset1">
<data element_type="f32" shape="" offset="4" size="4" />
<output>
<port id="0" precision="FP32" names="Relu6__22_min__132" />
</output>
</layer>
<layer id="3" name="Constant_4" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="8" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="4" name="Constant_5" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="40" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="5" name="Constant_3" type="Const" version="opset1">
<data element_type="f32" shape="" offset="4" size="4" />
<output>
<port id="0" precision="FP32" />
</output>
</layer>
<layer id="6" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0;1" type="Pad" version="opset12">
<data pad_mode="constant" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>4</dim>
<dim>512</dim>
<dim>512</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
<port id="2" precision="I64">
<dim>4</dim>
</port>
<port id="3" precision="FP32" />
</input>
<output>
<port id="4" precision="FP32" names="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0;1">
<dim>1</dim>
<dim>4</dim>
<dim>513</dim>
<dim>513</dim>
</port>
</output>
</layer>
<layer id="7" name="const_fold_opt__375" type="Const" version="opset1">
<data element_type="f32" shape="32, 4, 3, 3" offset="72" size="4608" />
<output>
<port id="0" precision="FP32" names="const_fold_opt__375">
<dim>32</dim>
<dim>4</dim>
<dim>3</dim>
<dim>3</dim>
</port>
</output>
</layer>
<layer id="8" name="models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.activation.ReLU6_2;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.batchnorm.BatchNorm2d_1;;models.mbv2_mlsd_tiny.MobileV2_MLSD_Tiny/models.mbv2_mlsd_tiny.MobileNetV2_backbone/models.mbv2_mlsd_tiny.ConvBNReLU_0/torch.nn.modules.conv.Conv2d_0;2/WithoutBiases" type="Convolution" version="opset1">
<data strides="2, 2" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>4</dim>
<dim>513</dim>
<dim>513</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>4</dim>
<dim>3</dim>
<dim>3</dim>
</port>