Hugging Face's logo

tomsanbear
/
docling-layout-heron

Safetensors
rt_detr_v2
Model card Files
xet
 Community
docling-layout-heron / tensor_map.json
tomsanbear's picture
tomsanbear
Add validated Docling Heron bundle
63d9148 verified
Raw History Blame Contribute Delete
232 kB
{
"architecture_id": "layout.heron-rtdetr",
"schema_version": 1,
"source_config_assertions": [
{
"equals": "rt_detr_v2",
"key": "model_type",
"path": "config.json"
},
{
"equals": [
"RTDetrV2ForObjectDetection"
],
"key": "architectures",
"path": "config.json"
},
{
"equals": 300,
"key": "num_queries",
"path": "config.json"
},
{
"equals": 6,
"key": "decoder_layers",
"path": "config.json"
},
{
"equals": true,
"key": "use_focal_loss",
"path": "config.json"
},
{
"equals": "RTDetrImageProcessor",
"key": "image_processor_type",
"path": "preprocessor_config.json"
}
],
"tensors": [
{
"expected_shape": [
32,
3,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.0.convolution.weight",
"target": "model.backbone.model.embedder.embedder.0.convolution.weight"
},
{
"expected_shape": [
32
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.0.normalization.bias",
"target": "model.backbone.model.embedder.embedder.0.normalization.bias"
},
{
"expected_shape": [
32
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.0.normalization.running_mean",
"target": "model.backbone.model.embedder.embedder.0.normalization.running_mean"
},
{
"expected_shape": [
32
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.0.normalization.running_var",
"target": "model.backbone.model.embedder.embedder.0.normalization.running_var"
},
{
"expected_shape": [
32
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.0.normalization.weight",
"target": "model.backbone.model.embedder.embedder.0.normalization.weight"
},
{
"expected_shape": [
32,
32,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.1.convolution.weight",
"target": "model.backbone.model.embedder.embedder.1.convolution.weight"
},
{
"expected_shape": [
32
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.1.normalization.bias",
"target": "model.backbone.model.embedder.embedder.1.normalization.bias"
},
{
"expected_shape": [
32
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.1.normalization.running_mean",
"target": "model.backbone.model.embedder.embedder.1.normalization.running_mean"
},
{
"expected_shape": [
32
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.1.normalization.running_var",
"target": "model.backbone.model.embedder.embedder.1.normalization.running_var"
},
{
"expected_shape": [
32
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.1.normalization.weight",
"target": "model.backbone.model.embedder.embedder.1.normalization.weight"
},
{
"expected_shape": [
64,
32,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.2.convolution.weight",
"target": "model.backbone.model.embedder.embedder.2.convolution.weight"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.2.normalization.bias",
"target": "model.backbone.model.embedder.embedder.2.normalization.bias"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.2.normalization.running_mean",
"target": "model.backbone.model.embedder.embedder.2.normalization.running_mean"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.2.normalization.running_var",
"target": "model.backbone.model.embedder.embedder.2.normalization.running_var"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.embedder.embedder.2.normalization.weight",
"target": "model.backbone.model.embedder.embedder.2.normalization.weight"
},
{
"expected_shape": [
64,
64,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.0.convolution.weight"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.0.normalization.bias"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.0.normalization.running_mean"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.0.normalization.running_var"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.0.normalization.weight"
},
{
"expected_shape": [
64,
64,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.1.convolution.weight"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.1.normalization.bias"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.1.normalization.running_mean"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.1.normalization.running_var"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.1.normalization.weight"
},
{
"expected_shape": [
256,
64,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.2.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.2.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.2.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.2.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.0.layer.2.normalization.weight"
},
{
"expected_shape": [
256,
64,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.shortcut.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.0.shortcut.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.shortcut.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.0.shortcut.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.shortcut.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.0.shortcut.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.shortcut.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.0.shortcut.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.0.shortcut.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.0.shortcut.normalization.weight"
},
{
"expected_shape": [
64,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.0.convolution.weight"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.0.normalization.bias"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.0.normalization.running_mean"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.0.normalization.running_var"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.0.normalization.weight"
},
{
"expected_shape": [
64,
64,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.1.convolution.weight"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.1.normalization.bias"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.1.normalization.running_mean"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.1.normalization.running_var"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.1.normalization.weight"
},
{
"expected_shape": [
256,
64,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.2.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.2.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.2.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.2.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.1.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.1.layer.2.normalization.weight"
},
{
"expected_shape": [
64,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.0.convolution.weight"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.0.normalization.bias"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.0.normalization.running_mean"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.0.normalization.running_var"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.0.normalization.weight"
},
{
"expected_shape": [
64,
64,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.1.convolution.weight"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.1.normalization.bias"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.1.normalization.running_mean"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.1.normalization.running_var"
},
{
"expected_shape": [
64
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.1.normalization.weight"
},
{
"expected_shape": [
256,
64,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.2.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.2.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.2.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.2.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.0.layers.2.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.0.layers.2.layer.2.normalization.weight"
},
{
"expected_shape": [
128,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.0.convolution.weight"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.0.normalization.bias"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.0.normalization.running_mean"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.0.normalization.running_var"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.0.normalization.weight"
},
{
"expected_shape": [
128,
128,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.1.convolution.weight"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.1.normalization.bias"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.1.normalization.running_mean"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.1.normalization.running_var"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.1.normalization.weight"
},
{
"expected_shape": [
512,
128,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.2.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.2.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.2.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.2.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.0.layer.2.normalization.weight"
},
{
"expected_shape": [
512,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.0.shortcut.1.normalization.weight"
},
{
"expected_shape": [
128,
512,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.0.convolution.weight"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.0.normalization.bias"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.0.normalization.running_mean"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.0.normalization.running_var"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.0.normalization.weight"
},
{
"expected_shape": [
128,
128,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.1.convolution.weight"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.1.normalization.bias"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.1.normalization.running_mean"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.1.normalization.running_var"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.1.normalization.weight"
},
{
"expected_shape": [
512,
128,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.2.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.2.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.2.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.2.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.1.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.1.layer.2.normalization.weight"
},
{
"expected_shape": [
128,
512,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.0.convolution.weight"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.0.normalization.bias"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.0.normalization.running_mean"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.0.normalization.running_var"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.0.normalization.weight"
},
{
"expected_shape": [
128,
128,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.1.convolution.weight"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.1.normalization.bias"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.1.normalization.running_mean"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.1.normalization.running_var"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.1.normalization.weight"
},
{
"expected_shape": [
512,
128,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.2.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.2.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.2.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.2.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.2.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.2.layer.2.normalization.weight"
},
{
"expected_shape": [
128,
512,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.0.convolution.weight"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.0.normalization.bias"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.0.normalization.running_mean"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.0.normalization.running_var"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.0.normalization.weight"
},
{
"expected_shape": [
128,
128,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.1.convolution.weight"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.1.normalization.bias"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.1.normalization.running_mean"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.1.normalization.running_var"
},
{
"expected_shape": [
128
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.1.normalization.weight"
},
{
"expected_shape": [
512,
128,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.2.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.2.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.2.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.2.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.1.layers.3.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.1.layers.3.layer.2.normalization.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.0.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.0.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.0.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.0.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.0.normalization.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.1.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.1.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.1.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.1.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.1.normalization.weight"
},
{
"expected_shape": [
1024,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.2.convolution.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.2.normalization.bias"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.2.normalization.running_mean"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.2.normalization.running_var"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.0.layer.2.normalization.weight"
},
{
"expected_shape": [
1024,
512,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.convolution.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.normalization.bias"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.normalization.running_mean"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.normalization.running_var"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.0.shortcut.1.normalization.weight"
},
{
"expected_shape": [
256,
1024,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.0.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.0.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.0.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.0.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.0.normalization.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.1.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.1.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.1.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.1.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.1.normalization.weight"
},
{
"expected_shape": [
1024,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.2.convolution.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.2.normalization.bias"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.2.normalization.running_mean"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.2.normalization.running_var"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.1.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.1.layer.2.normalization.weight"
},
{
"expected_shape": [
256,
1024,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.0.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.0.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.0.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.0.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.0.normalization.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.1.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.1.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.1.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.1.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.1.normalization.weight"
},
{
"expected_shape": [
1024,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.2.convolution.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.2.normalization.bias"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.2.normalization.running_mean"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.2.normalization.running_var"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.2.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.2.layer.2.normalization.weight"
},
{
"expected_shape": [
256,
1024,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.0.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.0.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.0.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.0.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.0.normalization.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.1.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.1.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.1.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.1.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.1.normalization.weight"
},
{
"expected_shape": [
1024,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.2.convolution.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.2.normalization.bias"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.2.normalization.running_mean"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.2.normalization.running_var"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.3.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.3.layer.2.normalization.weight"
},
{
"expected_shape": [
256,
1024,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.0.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.0.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.0.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.0.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.0.normalization.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.1.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.1.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.1.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.1.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.1.normalization.weight"
},
{
"expected_shape": [
1024,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.2.convolution.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.2.normalization.bias"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.2.normalization.running_mean"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.2.normalization.running_var"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.4.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.4.layer.2.normalization.weight"
},
{
"expected_shape": [
256,
1024,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.0.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.0.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.0.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.0.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.0.normalization.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.1.convolution.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.1.normalization.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.1.normalization.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.1.normalization.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.1.normalization.weight"
},
{
"expected_shape": [
1024,
256,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.2.convolution.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.2.normalization.bias"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.2.normalization.running_mean"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.2.normalization.running_var"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.2.layers.5.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.2.layers.5.layer.2.normalization.weight"
},
{
"expected_shape": [
512,
1024,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.0.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.0.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.0.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.0.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.0.normalization.weight"
},
{
"expected_shape": [
512,
512,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.1.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.1.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.1.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.1.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.1.normalization.weight"
},
{
"expected_shape": [
2048,
512,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.2.convolution.weight"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.2.normalization.bias"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.2.normalization.running_mean"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.2.normalization.running_var"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.0.layer.2.normalization.weight"
},
{
"expected_shape": [
2048,
1024,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.convolution.weight"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.normalization.bias"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.normalization.running_mean"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.normalization.running_var"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.0.shortcut.1.normalization.weight"
},
{
"expected_shape": [
512,
2048,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.0.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.0.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.0.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.0.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.0.normalization.weight"
},
{
"expected_shape": [
512,
512,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.1.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.1.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.1.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.1.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.1.normalization.weight"
},
{
"expected_shape": [
2048,
512,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.2.convolution.weight"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.2.normalization.bias"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.2.normalization.running_mean"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.2.normalization.running_var"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.1.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.1.layer.2.normalization.weight"
},
{
"expected_shape": [
512,
2048,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.0.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.0.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.0.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.0.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.0.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.0.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.0.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.0.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.0.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.0.normalization.weight"
},
{
"expected_shape": [
512,
512,
3,
3
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.1.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.1.convolution.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.1.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.1.normalization.bias"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.1.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.1.normalization.running_mean"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.1.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.1.normalization.running_var"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.1.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.1.normalization.weight"
},
{
"expected_shape": [
2048,
512,
1,
1
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.2.convolution.weight",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.2.convolution.weight"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.2.normalization.bias",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.2.normalization.bias"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.2.normalization.running_mean",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.2.normalization.running_mean"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.2.normalization.running_var",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.2.normalization.running_var"
},
{
"expected_shape": [
2048
],
"notes": "RT-DETR ResNet backbone tensor reused without transpose",
"source": "model.backbone.model.encoder.stages.3.layers.2.layer.2.normalization.weight",
"target": "model.backbone.model.encoder.stages.3.layers.2.layer.2.normalization.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.0.layers.0.bias",
"target": "model.decoder.bbox_embed.0.layers.0.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.0.layers.0.weight",
"target": "model.decoder.bbox_embed.0.layers.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.0.layers.1.bias",
"target": "model.decoder.bbox_embed.0.layers.1.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.0.layers.1.weight",
"target": "model.decoder.bbox_embed.0.layers.1.weight"
},
{
"expected_shape": [
4
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.0.layers.2.bias",
"target": "model.decoder.bbox_embed.0.layers.2.bias"
},
{
"expected_shape": [
4,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.0.layers.2.weight",
"target": "model.decoder.bbox_embed.0.layers.2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.1.layers.0.bias",
"target": "model.decoder.bbox_embed.1.layers.0.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.1.layers.0.weight",
"target": "model.decoder.bbox_embed.1.layers.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.1.layers.1.bias",
"target": "model.decoder.bbox_embed.1.layers.1.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.1.layers.1.weight",
"target": "model.decoder.bbox_embed.1.layers.1.weight"
},
{
"expected_shape": [
4
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.1.layers.2.bias",
"target": "model.decoder.bbox_embed.1.layers.2.bias"
},
{
"expected_shape": [
4,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.1.layers.2.weight",
"target": "model.decoder.bbox_embed.1.layers.2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.2.layers.0.bias",
"target": "model.decoder.bbox_embed.2.layers.0.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.2.layers.0.weight",
"target": "model.decoder.bbox_embed.2.layers.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.2.layers.1.bias",
"target": "model.decoder.bbox_embed.2.layers.1.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.2.layers.1.weight",
"target": "model.decoder.bbox_embed.2.layers.1.weight"
},
{
"expected_shape": [
4
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.2.layers.2.bias",
"target": "model.decoder.bbox_embed.2.layers.2.bias"
},
{
"expected_shape": [
4,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.2.layers.2.weight",
"target": "model.decoder.bbox_embed.2.layers.2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.3.layers.0.bias",
"target": "model.decoder.bbox_embed.3.layers.0.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.3.layers.0.weight",
"target": "model.decoder.bbox_embed.3.layers.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.3.layers.1.bias",
"target": "model.decoder.bbox_embed.3.layers.1.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.3.layers.1.weight",
"target": "model.decoder.bbox_embed.3.layers.1.weight"
},
{
"expected_shape": [
4
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.3.layers.2.bias",
"target": "model.decoder.bbox_embed.3.layers.2.bias"
},
{
"expected_shape": [
4,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.3.layers.2.weight",
"target": "model.decoder.bbox_embed.3.layers.2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.4.layers.0.bias",
"target": "model.decoder.bbox_embed.4.layers.0.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.4.layers.0.weight",
"target": "model.decoder.bbox_embed.4.layers.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.4.layers.1.bias",
"target": "model.decoder.bbox_embed.4.layers.1.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.4.layers.1.weight",
"target": "model.decoder.bbox_embed.4.layers.1.weight"
},
{
"expected_shape": [
4
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.4.layers.2.bias",
"target": "model.decoder.bbox_embed.4.layers.2.bias"
},
{
"expected_shape": [
4,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.4.layers.2.weight",
"target": "model.decoder.bbox_embed.4.layers.2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.5.layers.0.bias",
"target": "model.decoder.bbox_embed.5.layers.0.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.5.layers.0.weight",
"target": "model.decoder.bbox_embed.5.layers.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.5.layers.1.bias",
"target": "model.decoder.bbox_embed.5.layers.1.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.5.layers.1.weight",
"target": "model.decoder.bbox_embed.5.layers.1.weight"
},
{
"expected_shape": [
4
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.5.layers.2.bias",
"target": "model.decoder.bbox_embed.5.layers.2.bias"
},
{
"expected_shape": [
4,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.bbox_embed.5.layers.2.weight",
"target": "model.decoder.bbox_embed.5.layers.2.weight"
},
{
"expected_shape": [
17
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.0.bias",
"target": "model.decoder.class_embed.0.bias"
},
{
"expected_shape": [
17,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.0.weight",
"target": "model.decoder.class_embed.0.weight"
},
{
"expected_shape": [
17
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.1.bias",
"target": "model.decoder.class_embed.1.bias"
},
{
"expected_shape": [
17,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.1.weight",
"target": "model.decoder.class_embed.1.weight"
},
{
"expected_shape": [
17
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.2.bias",
"target": "model.decoder.class_embed.2.bias"
},
{
"expected_shape": [
17,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.2.weight",
"target": "model.decoder.class_embed.2.weight"
},
{
"expected_shape": [
17
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.3.bias",
"target": "model.decoder.class_embed.3.bias"
},
{
"expected_shape": [
17,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.3.weight",
"target": "model.decoder.class_embed.3.weight"
},
{
"expected_shape": [
17
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.4.bias",
"target": "model.decoder.class_embed.4.bias"
},
{
"expected_shape": [
17,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.4.weight",
"target": "model.decoder.class_embed.4.weight"
},
{
"expected_shape": [
17
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.5.bias",
"target": "model.decoder.class_embed.5.bias"
},
{
"expected_shape": [
17,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.class_embed.5.weight",
"target": "model.decoder.class_embed.5.weight"
},
{
"expected_shape": [
96
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn.attention_weights.bias",
"target": "model.decoder.layers.0.encoder_attn.attention_weights.bias"
},
{
"expected_shape": [
96,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn.attention_weights.weight",
"target": "model.decoder.layers.0.encoder_attn.attention_weights.weight"
},
{
"expected_shape": [
12
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn.n_points_scale",
"target": "model.decoder.layers.0.encoder_attn.n_points_scale"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn.output_proj.bias",
"target": "model.decoder.layers.0.encoder_attn.output_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn.output_proj.weight",
"target": "model.decoder.layers.0.encoder_attn.output_proj.weight"
},
{
"expected_shape": [
192
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn.sampling_offsets.bias",
"target": "model.decoder.layers.0.encoder_attn.sampling_offsets.bias"
},
{
"expected_shape": [
192,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn.sampling_offsets.weight",
"target": "model.decoder.layers.0.encoder_attn.sampling_offsets.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn.value_proj.bias",
"target": "model.decoder.layers.0.encoder_attn.value_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn.value_proj.weight",
"target": "model.decoder.layers.0.encoder_attn.value_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn_layer_norm.bias",
"target": "model.decoder.layers.0.encoder_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.encoder_attn_layer_norm.weight",
"target": "model.decoder.layers.0.encoder_attn_layer_norm.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.fc1.bias",
"target": "model.decoder.layers.0.fc1.bias"
},
{
"expected_shape": [
1024,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.fc1.weight",
"target": "model.decoder.layers.0.fc1.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.fc2.bias",
"target": "model.decoder.layers.0.fc2.bias"
},
{
"expected_shape": [
256,
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.fc2.weight",
"target": "model.decoder.layers.0.fc2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.final_layer_norm.bias",
"target": "model.decoder.layers.0.final_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.final_layer_norm.weight",
"target": "model.decoder.layers.0.final_layer_norm.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn.k_proj.bias",
"target": "model.decoder.layers.0.self_attn.k_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn.k_proj.weight",
"target": "model.decoder.layers.0.self_attn.k_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn.out_proj.bias",
"target": "model.decoder.layers.0.self_attn.out_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn.out_proj.weight",
"target": "model.decoder.layers.0.self_attn.out_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn.q_proj.bias",
"target": "model.decoder.layers.0.self_attn.q_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn.q_proj.weight",
"target": "model.decoder.layers.0.self_attn.q_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn.v_proj.bias",
"target": "model.decoder.layers.0.self_attn.v_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn.v_proj.weight",
"target": "model.decoder.layers.0.self_attn.v_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn_layer_norm.bias",
"target": "model.decoder.layers.0.self_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.0.self_attn_layer_norm.weight",
"target": "model.decoder.layers.0.self_attn_layer_norm.weight"
},
{
"expected_shape": [
96
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn.attention_weights.bias",
"target": "model.decoder.layers.1.encoder_attn.attention_weights.bias"
},
{
"expected_shape": [
96,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn.attention_weights.weight",
"target": "model.decoder.layers.1.encoder_attn.attention_weights.weight"
},
{
"expected_shape": [
12
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn.n_points_scale",
"target": "model.decoder.layers.1.encoder_attn.n_points_scale"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn.output_proj.bias",
"target": "model.decoder.layers.1.encoder_attn.output_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn.output_proj.weight",
"target": "model.decoder.layers.1.encoder_attn.output_proj.weight"
},
{
"expected_shape": [
192
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn.sampling_offsets.bias",
"target": "model.decoder.layers.1.encoder_attn.sampling_offsets.bias"
},
{
"expected_shape": [
192,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn.sampling_offsets.weight",
"target": "model.decoder.layers.1.encoder_attn.sampling_offsets.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn.value_proj.bias",
"target": "model.decoder.layers.1.encoder_attn.value_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn.value_proj.weight",
"target": "model.decoder.layers.1.encoder_attn.value_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn_layer_norm.bias",
"target": "model.decoder.layers.1.encoder_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.encoder_attn_layer_norm.weight",
"target": "model.decoder.layers.1.encoder_attn_layer_norm.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.fc1.bias",
"target": "model.decoder.layers.1.fc1.bias"
},
{
"expected_shape": [
1024,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.fc1.weight",
"target": "model.decoder.layers.1.fc1.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.fc2.bias",
"target": "model.decoder.layers.1.fc2.bias"
},
{
"expected_shape": [
256,
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.fc2.weight",
"target": "model.decoder.layers.1.fc2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.final_layer_norm.bias",
"target": "model.decoder.layers.1.final_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.final_layer_norm.weight",
"target": "model.decoder.layers.1.final_layer_norm.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn.k_proj.bias",
"target": "model.decoder.layers.1.self_attn.k_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn.k_proj.weight",
"target": "model.decoder.layers.1.self_attn.k_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn.out_proj.bias",
"target": "model.decoder.layers.1.self_attn.out_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn.out_proj.weight",
"target": "model.decoder.layers.1.self_attn.out_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn.q_proj.bias",
"target": "model.decoder.layers.1.self_attn.q_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn.q_proj.weight",
"target": "model.decoder.layers.1.self_attn.q_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn.v_proj.bias",
"target": "model.decoder.layers.1.self_attn.v_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn.v_proj.weight",
"target": "model.decoder.layers.1.self_attn.v_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn_layer_norm.bias",
"target": "model.decoder.layers.1.self_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.1.self_attn_layer_norm.weight",
"target": "model.decoder.layers.1.self_attn_layer_norm.weight"
},
{
"expected_shape": [
96
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn.attention_weights.bias",
"target": "model.decoder.layers.2.encoder_attn.attention_weights.bias"
},
{
"expected_shape": [
96,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn.attention_weights.weight",
"target": "model.decoder.layers.2.encoder_attn.attention_weights.weight"
},
{
"expected_shape": [
12
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn.n_points_scale",
"target": "model.decoder.layers.2.encoder_attn.n_points_scale"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn.output_proj.bias",
"target": "model.decoder.layers.2.encoder_attn.output_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn.output_proj.weight",
"target": "model.decoder.layers.2.encoder_attn.output_proj.weight"
},
{
"expected_shape": [
192
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn.sampling_offsets.bias",
"target": "model.decoder.layers.2.encoder_attn.sampling_offsets.bias"
},
{
"expected_shape": [
192,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn.sampling_offsets.weight",
"target": "model.decoder.layers.2.encoder_attn.sampling_offsets.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn.value_proj.bias",
"target": "model.decoder.layers.2.encoder_attn.value_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn.value_proj.weight",
"target": "model.decoder.layers.2.encoder_attn.value_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn_layer_norm.bias",
"target": "model.decoder.layers.2.encoder_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.encoder_attn_layer_norm.weight",
"target": "model.decoder.layers.2.encoder_attn_layer_norm.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.fc1.bias",
"target": "model.decoder.layers.2.fc1.bias"
},
{
"expected_shape": [
1024,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.fc1.weight",
"target": "model.decoder.layers.2.fc1.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.fc2.bias",
"target": "model.decoder.layers.2.fc2.bias"
},
{
"expected_shape": [
256,
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.fc2.weight",
"target": "model.decoder.layers.2.fc2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.final_layer_norm.bias",
"target": "model.decoder.layers.2.final_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.final_layer_norm.weight",
"target": "model.decoder.layers.2.final_layer_norm.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn.k_proj.bias",
"target": "model.decoder.layers.2.self_attn.k_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn.k_proj.weight",
"target": "model.decoder.layers.2.self_attn.k_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn.out_proj.bias",
"target": "model.decoder.layers.2.self_attn.out_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn.out_proj.weight",
"target": "model.decoder.layers.2.self_attn.out_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn.q_proj.bias",
"target": "model.decoder.layers.2.self_attn.q_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn.q_proj.weight",
"target": "model.decoder.layers.2.self_attn.q_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn.v_proj.bias",
"target": "model.decoder.layers.2.self_attn.v_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn.v_proj.weight",
"target": "model.decoder.layers.2.self_attn.v_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn_layer_norm.bias",
"target": "model.decoder.layers.2.self_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.2.self_attn_layer_norm.weight",
"target": "model.decoder.layers.2.self_attn_layer_norm.weight"
},
{
"expected_shape": [
96
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn.attention_weights.bias",
"target": "model.decoder.layers.3.encoder_attn.attention_weights.bias"
},
{
"expected_shape": [
96,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn.attention_weights.weight",
"target": "model.decoder.layers.3.encoder_attn.attention_weights.weight"
},
{
"expected_shape": [
12
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn.n_points_scale",
"target": "model.decoder.layers.3.encoder_attn.n_points_scale"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn.output_proj.bias",
"target": "model.decoder.layers.3.encoder_attn.output_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn.output_proj.weight",
"target": "model.decoder.layers.3.encoder_attn.output_proj.weight"
},
{
"expected_shape": [
192
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn.sampling_offsets.bias",
"target": "model.decoder.layers.3.encoder_attn.sampling_offsets.bias"
},
{
"expected_shape": [
192,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn.sampling_offsets.weight",
"target": "model.decoder.layers.3.encoder_attn.sampling_offsets.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn.value_proj.bias",
"target": "model.decoder.layers.3.encoder_attn.value_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn.value_proj.weight",
"target": "model.decoder.layers.3.encoder_attn.value_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn_layer_norm.bias",
"target": "model.decoder.layers.3.encoder_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.encoder_attn_layer_norm.weight",
"target": "model.decoder.layers.3.encoder_attn_layer_norm.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.fc1.bias",
"target": "model.decoder.layers.3.fc1.bias"
},
{
"expected_shape": [
1024,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.fc1.weight",
"target": "model.decoder.layers.3.fc1.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.fc2.bias",
"target": "model.decoder.layers.3.fc2.bias"
},
{
"expected_shape": [
256,
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.fc2.weight",
"target": "model.decoder.layers.3.fc2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.final_layer_norm.bias",
"target": "model.decoder.layers.3.final_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.final_layer_norm.weight",
"target": "model.decoder.layers.3.final_layer_norm.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn.k_proj.bias",
"target": "model.decoder.layers.3.self_attn.k_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn.k_proj.weight",
"target": "model.decoder.layers.3.self_attn.k_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn.out_proj.bias",
"target": "model.decoder.layers.3.self_attn.out_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn.out_proj.weight",
"target": "model.decoder.layers.3.self_attn.out_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn.q_proj.bias",
"target": "model.decoder.layers.3.self_attn.q_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn.q_proj.weight",
"target": "model.decoder.layers.3.self_attn.q_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn.v_proj.bias",
"target": "model.decoder.layers.3.self_attn.v_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn.v_proj.weight",
"target": "model.decoder.layers.3.self_attn.v_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn_layer_norm.bias",
"target": "model.decoder.layers.3.self_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.3.self_attn_layer_norm.weight",
"target": "model.decoder.layers.3.self_attn_layer_norm.weight"
},
{
"expected_shape": [
96
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn.attention_weights.bias",
"target": "model.decoder.layers.4.encoder_attn.attention_weights.bias"
},
{
"expected_shape": [
96,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn.attention_weights.weight",
"target": "model.decoder.layers.4.encoder_attn.attention_weights.weight"
},
{
"expected_shape": [
12
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn.n_points_scale",
"target": "model.decoder.layers.4.encoder_attn.n_points_scale"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn.output_proj.bias",
"target": "model.decoder.layers.4.encoder_attn.output_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn.output_proj.weight",
"target": "model.decoder.layers.4.encoder_attn.output_proj.weight"
},
{
"expected_shape": [
192
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn.sampling_offsets.bias",
"target": "model.decoder.layers.4.encoder_attn.sampling_offsets.bias"
},
{
"expected_shape": [
192,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn.sampling_offsets.weight",
"target": "model.decoder.layers.4.encoder_attn.sampling_offsets.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn.value_proj.bias",
"target": "model.decoder.layers.4.encoder_attn.value_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn.value_proj.weight",
"target": "model.decoder.layers.4.encoder_attn.value_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn_layer_norm.bias",
"target": "model.decoder.layers.4.encoder_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.encoder_attn_layer_norm.weight",
"target": "model.decoder.layers.4.encoder_attn_layer_norm.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.fc1.bias",
"target": "model.decoder.layers.4.fc1.bias"
},
{
"expected_shape": [
1024,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.fc1.weight",
"target": "model.decoder.layers.4.fc1.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.fc2.bias",
"target": "model.decoder.layers.4.fc2.bias"
},
{
"expected_shape": [
256,
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.fc2.weight",
"target": "model.decoder.layers.4.fc2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.final_layer_norm.bias",
"target": "model.decoder.layers.4.final_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.final_layer_norm.weight",
"target": "model.decoder.layers.4.final_layer_norm.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn.k_proj.bias",
"target": "model.decoder.layers.4.self_attn.k_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn.k_proj.weight",
"target": "model.decoder.layers.4.self_attn.k_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn.out_proj.bias",
"target": "model.decoder.layers.4.self_attn.out_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn.out_proj.weight",
"target": "model.decoder.layers.4.self_attn.out_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn.q_proj.bias",
"target": "model.decoder.layers.4.self_attn.q_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn.q_proj.weight",
"target": "model.decoder.layers.4.self_attn.q_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn.v_proj.bias",
"target": "model.decoder.layers.4.self_attn.v_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn.v_proj.weight",
"target": "model.decoder.layers.4.self_attn.v_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn_layer_norm.bias",
"target": "model.decoder.layers.4.self_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.4.self_attn_layer_norm.weight",
"target": "model.decoder.layers.4.self_attn_layer_norm.weight"
},
{
"expected_shape": [
96
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn.attention_weights.bias",
"target": "model.decoder.layers.5.encoder_attn.attention_weights.bias"
},
{
"expected_shape": [
96,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn.attention_weights.weight",
"target": "model.decoder.layers.5.encoder_attn.attention_weights.weight"
},
{
"expected_shape": [
12
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn.n_points_scale",
"target": "model.decoder.layers.5.encoder_attn.n_points_scale"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn.output_proj.bias",
"target": "model.decoder.layers.5.encoder_attn.output_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn.output_proj.weight",
"target": "model.decoder.layers.5.encoder_attn.output_proj.weight"
},
{
"expected_shape": [
192
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn.sampling_offsets.bias",
"target": "model.decoder.layers.5.encoder_attn.sampling_offsets.bias"
},
{
"expected_shape": [
192,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn.sampling_offsets.weight",
"target": "model.decoder.layers.5.encoder_attn.sampling_offsets.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn.value_proj.bias",
"target": "model.decoder.layers.5.encoder_attn.value_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn.value_proj.weight",
"target": "model.decoder.layers.5.encoder_attn.value_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn_layer_norm.bias",
"target": "model.decoder.layers.5.encoder_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.encoder_attn_layer_norm.weight",
"target": "model.decoder.layers.5.encoder_attn_layer_norm.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.fc1.bias",
"target": "model.decoder.layers.5.fc1.bias"
},
{
"expected_shape": [
1024,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.fc1.weight",
"target": "model.decoder.layers.5.fc1.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.fc2.bias",
"target": "model.decoder.layers.5.fc2.bias"
},
{
"expected_shape": [
256,
1024
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.fc2.weight",
"target": "model.decoder.layers.5.fc2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.final_layer_norm.bias",
"target": "model.decoder.layers.5.final_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.final_layer_norm.weight",
"target": "model.decoder.layers.5.final_layer_norm.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn.k_proj.bias",
"target": "model.decoder.layers.5.self_attn.k_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn.k_proj.weight",
"target": "model.decoder.layers.5.self_attn.k_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn.out_proj.bias",
"target": "model.decoder.layers.5.self_attn.out_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn.out_proj.weight",
"target": "model.decoder.layers.5.self_attn.out_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn.q_proj.bias",
"target": "model.decoder.layers.5.self_attn.q_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn.q_proj.weight",
"target": "model.decoder.layers.5.self_attn.q_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn.v_proj.bias",
"target": "model.decoder.layers.5.self_attn.v_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn.v_proj.weight",
"target": "model.decoder.layers.5.self_attn.v_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn_layer_norm.bias",
"target": "model.decoder.layers.5.self_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.layers.5.self_attn_layer_norm.weight",
"target": "model.decoder.layers.5.self_attn_layer_norm.weight"
},
{
"expected_shape": [
512
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.query_pos_head.layers.0.bias",
"target": "model.decoder.query_pos_head.layers.0.bias"
},
{
"expected_shape": [
512,
4
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.query_pos_head.layers.0.weight",
"target": "model.decoder.query_pos_head.layers.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.query_pos_head.layers.1.bias",
"target": "model.decoder.query_pos_head.layers.1.bias"
},
{
"expected_shape": [
256,
512
],
"notes": "RT-DETR decoder tensor reused without transpose",
"source": "model.decoder.query_pos_head.layers.1.weight",
"target": "model.decoder.query_pos_head.layers.1.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.0.0.weight",
"target": "model.decoder_input_proj.0.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.0.1.bias",
"target": "model.decoder_input_proj.0.1.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.decoder_input_proj.0.1.num_batches_tracked",
"target": "model.decoder_input_proj.0.1.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.0.1.running_mean",
"target": "model.decoder_input_proj.0.1.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.0.1.running_var",
"target": "model.decoder_input_proj.0.1.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.0.1.weight",
"target": "model.decoder_input_proj.0.1.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.1.0.weight",
"target": "model.decoder_input_proj.1.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.1.1.bias",
"target": "model.decoder_input_proj.1.1.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.decoder_input_proj.1.1.num_batches_tracked",
"target": "model.decoder_input_proj.1.1.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.1.1.running_mean",
"target": "model.decoder_input_proj.1.1.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.1.1.running_var",
"target": "model.decoder_input_proj.1.1.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.1.1.weight",
"target": "model.decoder_input_proj.1.1.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.2.0.weight",
"target": "model.decoder_input_proj.2.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.2.1.bias",
"target": "model.decoder_input_proj.2.1.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.decoder_input_proj.2.1.num_batches_tracked",
"target": "model.decoder_input_proj.2.1.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.2.1.running_mean",
"target": "model.decoder_input_proj.2.1.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.2.1.running_var",
"target": "model.decoder_input_proj.2.1.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR decoder input projection tensor reused without transpose",
"source": "model.decoder_input_proj.2.1.weight",
"target": "model.decoder_input_proj.2.1.weight"
},
{
"expected_shape": [
18,
256
],
"notes": "RT-DETR denoising class embedding reused without transpose",
"source": "model.denoising_class_embed.weight",
"target": "model.denoising_class_embed.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder bbox head tensor reused without transpose",
"source": "model.enc_bbox_head.layers.0.bias",
"target": "model.enc_bbox_head.layers.0.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR encoder bbox head tensor reused without transpose",
"source": "model.enc_bbox_head.layers.0.weight",
"target": "model.enc_bbox_head.layers.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder bbox head tensor reused without transpose",
"source": "model.enc_bbox_head.layers.1.bias",
"target": "model.enc_bbox_head.layers.1.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR encoder bbox head tensor reused without transpose",
"source": "model.enc_bbox_head.layers.1.weight",
"target": "model.enc_bbox_head.layers.1.weight"
},
{
"expected_shape": [
4
],
"notes": "RT-DETR encoder bbox head tensor reused without transpose",
"source": "model.enc_bbox_head.layers.2.bias",
"target": "model.enc_bbox_head.layers.2.bias"
},
{
"expected_shape": [
4,
256
],
"notes": "RT-DETR encoder bbox head tensor reused without transpose",
"source": "model.enc_bbox_head.layers.2.weight",
"target": "model.enc_bbox_head.layers.2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder output projection tensor reused without transpose",
"source": "model.enc_output.0.bias",
"target": "model.enc_output.0.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR encoder output projection tensor reused without transpose",
"source": "model.enc_output.0.weight",
"target": "model.enc_output.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder output projection tensor reused without transpose",
"source": "model.enc_output.1.bias",
"target": "model.enc_output.1.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder output projection tensor reused without transpose",
"source": "model.enc_output.1.weight",
"target": "model.enc_output.1.weight"
},
{
"expected_shape": [
17
],
"notes": "RT-DETR encoder score head tensor reused without transpose",
"source": "model.enc_score_head.bias",
"target": "model.enc_score_head.bias"
},
{
"expected_shape": [
17,
256
],
"notes": "RT-DETR encoder score head tensor reused without transpose",
"source": "model.enc_score_head.weight",
"target": "model.enc_score_head.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.0.conv.weight",
"target": "model.encoder.downsample_convs.0.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.0.norm.bias",
"target": "model.encoder.downsample_convs.0.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.downsample_convs.0.norm.num_batches_tracked",
"target": "model.encoder.downsample_convs.0.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.0.norm.running_mean",
"target": "model.encoder.downsample_convs.0.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.0.norm.running_var",
"target": "model.encoder.downsample_convs.0.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.0.norm.weight",
"target": "model.encoder.downsample_convs.0.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.1.conv.weight",
"target": "model.encoder.downsample_convs.1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.1.norm.bias",
"target": "model.encoder.downsample_convs.1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.downsample_convs.1.norm.num_batches_tracked",
"target": "model.encoder.downsample_convs.1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.1.norm.running_mean",
"target": "model.encoder.downsample_convs.1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.1.norm.running_var",
"target": "model.encoder.downsample_convs.1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.downsample_convs.1.norm.weight",
"target": "model.encoder.downsample_convs.1.norm.weight"
},
{
"expected_shape": [
1024
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.fc1.bias",
"target": "model.encoder.encoder.0.layers.0.fc1.bias"
},
{
"expected_shape": [
1024,
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.fc1.weight",
"target": "model.encoder.encoder.0.layers.0.fc1.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.fc2.bias",
"target": "model.encoder.encoder.0.layers.0.fc2.bias"
},
{
"expected_shape": [
256,
1024
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.fc2.weight",
"target": "model.encoder.encoder.0.layers.0.fc2.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.final_layer_norm.bias",
"target": "model.encoder.encoder.0.layers.0.final_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.final_layer_norm.weight",
"target": "model.encoder.encoder.0.layers.0.final_layer_norm.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn.k_proj.bias",
"target": "model.encoder.encoder.0.layers.0.self_attn.k_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn.k_proj.weight",
"target": "model.encoder.encoder.0.layers.0.self_attn.k_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn.out_proj.bias",
"target": "model.encoder.encoder.0.layers.0.self_attn.out_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn.out_proj.weight",
"target": "model.encoder.encoder.0.layers.0.self_attn.out_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn.q_proj.bias",
"target": "model.encoder.encoder.0.layers.0.self_attn.q_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn.q_proj.weight",
"target": "model.encoder.encoder.0.layers.0.self_attn.q_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn.v_proj.bias",
"target": "model.encoder.encoder.0.layers.0.self_attn.v_proj.bias"
},
{
"expected_shape": [
256,
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn.v_proj.weight",
"target": "model.encoder.encoder.0.layers.0.self_attn.v_proj.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn_layer_norm.bias",
"target": "model.encoder.encoder.0.layers.0.self_attn_layer_norm.bias"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.encoder.0.layers.0.self_attn_layer_norm.weight",
"target": "model.encoder.encoder.0.layers.0.self_attn_layer_norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.conv.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.bias",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.running_mean",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.running_var",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.conv.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.bias",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.running_mean",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.running_var",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.0.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.conv.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.bias",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.running_mean",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.running_var",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.conv.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.bias",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.running_mean",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.running_var",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.1.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.conv.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.bias",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.running_mean",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.running_var",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.conv.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.bias",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.running_mean",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.running_var",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.weight",
"target": "model.encoder.fpn_blocks.0.bottlenecks.2.conv2.norm.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv1.conv.weight",
"target": "model.encoder.fpn_blocks.0.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv1.norm.bias",
"target": "model.encoder.fpn_blocks.0.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.0.conv1.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.0.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv1.norm.running_mean",
"target": "model.encoder.fpn_blocks.0.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv1.norm.running_var",
"target": "model.encoder.fpn_blocks.0.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv1.norm.weight",
"target": "model.encoder.fpn_blocks.0.conv1.norm.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv2.conv.weight",
"target": "model.encoder.fpn_blocks.0.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv2.norm.bias",
"target": "model.encoder.fpn_blocks.0.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.0.conv2.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.0.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv2.norm.running_mean",
"target": "model.encoder.fpn_blocks.0.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv2.norm.running_var",
"target": "model.encoder.fpn_blocks.0.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.0.conv2.norm.weight",
"target": "model.encoder.fpn_blocks.0.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.conv.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.bias",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.running_mean",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.running_var",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.conv.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.bias",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.running_mean",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.running_var",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.0.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.conv.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.bias",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.running_mean",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.running_var",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.conv.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.bias",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.running_mean",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.running_var",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.1.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.conv.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.bias",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.running_mean",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.running_var",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.conv.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.bias",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.running_mean",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.running_var",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.weight",
"target": "model.encoder.fpn_blocks.1.bottlenecks.2.conv2.norm.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv1.conv.weight",
"target": "model.encoder.fpn_blocks.1.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv1.norm.bias",
"target": "model.encoder.fpn_blocks.1.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.1.conv1.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.1.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv1.norm.running_mean",
"target": "model.encoder.fpn_blocks.1.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv1.norm.running_var",
"target": "model.encoder.fpn_blocks.1.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv1.norm.weight",
"target": "model.encoder.fpn_blocks.1.conv1.norm.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv2.conv.weight",
"target": "model.encoder.fpn_blocks.1.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv2.norm.bias",
"target": "model.encoder.fpn_blocks.1.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.fpn_blocks.1.conv2.norm.num_batches_tracked",
"target": "model.encoder.fpn_blocks.1.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv2.norm.running_mean",
"target": "model.encoder.fpn_blocks.1.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv2.norm.running_var",
"target": "model.encoder.fpn_blocks.1.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.fpn_blocks.1.conv2.norm.weight",
"target": "model.encoder.fpn_blocks.1.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.0.conv.weight",
"target": "model.encoder.lateral_convs.0.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.0.norm.bias",
"target": "model.encoder.lateral_convs.0.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.lateral_convs.0.norm.num_batches_tracked",
"target": "model.encoder.lateral_convs.0.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.0.norm.running_mean",
"target": "model.encoder.lateral_convs.0.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.0.norm.running_var",
"target": "model.encoder.lateral_convs.0.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.0.norm.weight",
"target": "model.encoder.lateral_convs.0.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.1.conv.weight",
"target": "model.encoder.lateral_convs.1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.1.norm.bias",
"target": "model.encoder.lateral_convs.1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.lateral_convs.1.norm.num_batches_tracked",
"target": "model.encoder.lateral_convs.1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.1.norm.running_mean",
"target": "model.encoder.lateral_convs.1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.1.norm.running_var",
"target": "model.encoder.lateral_convs.1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.lateral_convs.1.norm.weight",
"target": "model.encoder.lateral_convs.1.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.conv.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.bias",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.running_mean",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.running_var",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.conv.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.bias",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.running_mean",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.running_var",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.0.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.conv.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.bias",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.running_mean",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.running_var",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.conv.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.bias",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.running_mean",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.running_var",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.1.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.conv.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.bias",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.running_mean",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.running_var",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.conv.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.bias",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.running_mean",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.running_var",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.weight",
"target": "model.encoder.pan_blocks.0.bottlenecks.2.conv2.norm.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv1.conv.weight",
"target": "model.encoder.pan_blocks.0.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv1.norm.bias",
"target": "model.encoder.pan_blocks.0.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.0.conv1.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.0.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv1.norm.running_mean",
"target": "model.encoder.pan_blocks.0.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv1.norm.running_var",
"target": "model.encoder.pan_blocks.0.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv1.norm.weight",
"target": "model.encoder.pan_blocks.0.conv1.norm.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv2.conv.weight",
"target": "model.encoder.pan_blocks.0.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv2.norm.bias",
"target": "model.encoder.pan_blocks.0.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.0.conv2.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.0.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv2.norm.running_mean",
"target": "model.encoder.pan_blocks.0.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv2.norm.running_var",
"target": "model.encoder.pan_blocks.0.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.0.conv2.norm.weight",
"target": "model.encoder.pan_blocks.0.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.conv.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.bias",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.running_mean",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.running_var",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.conv.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.bias",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.running_mean",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.running_var",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.0.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.conv.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.bias",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.running_mean",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.running_var",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.conv.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.bias",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.running_mean",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.running_var",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.1.conv2.norm.weight"
},
{
"expected_shape": [
256,
256,
3,
3
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.conv.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.bias",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.running_mean",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.running_var",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv1.norm.weight"
},
{
"expected_shape": [
256,
256,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.conv.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.bias",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.running_mean",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.running_var",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.weight",
"target": "model.encoder.pan_blocks.1.bottlenecks.2.conv2.norm.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv1.conv.weight",
"target": "model.encoder.pan_blocks.1.conv1.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv1.norm.bias",
"target": "model.encoder.pan_blocks.1.conv1.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.1.conv1.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.1.conv1.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv1.norm.running_mean",
"target": "model.encoder.pan_blocks.1.conv1.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv1.norm.running_var",
"target": "model.encoder.pan_blocks.1.conv1.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv1.norm.weight",
"target": "model.encoder.pan_blocks.1.conv1.norm.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv2.conv.weight",
"target": "model.encoder.pan_blocks.1.conv2.conv.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv2.norm.bias",
"target": "model.encoder.pan_blocks.1.conv2.norm.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder.pan_blocks.1.conv2.norm.num_batches_tracked",
"target": "model.encoder.pan_blocks.1.conv2.norm.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv2.norm.running_mean",
"target": "model.encoder.pan_blocks.1.conv2.norm.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv2.norm.running_var",
"target": "model.encoder.pan_blocks.1.conv2.norm.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR hybrid encoder, FPN, or PAN tensor reused without transpose",
"source": "model.encoder.pan_blocks.1.conv2.norm.weight",
"target": "model.encoder.pan_blocks.1.conv2.norm.weight"
},
{
"expected_shape": [
256,
512,
1,
1
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.0.0.weight",
"target": "model.encoder_input_proj.0.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.0.1.bias",
"target": "model.encoder_input_proj.0.1.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder_input_proj.0.1.num_batches_tracked",
"target": "model.encoder_input_proj.0.1.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.0.1.running_mean",
"target": "model.encoder_input_proj.0.1.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.0.1.running_var",
"target": "model.encoder_input_proj.0.1.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.0.1.weight",
"target": "model.encoder_input_proj.0.1.weight"
},
{
"expected_shape": [
256,
1024,
1,
1
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.1.0.weight",
"target": "model.encoder_input_proj.1.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.1.1.bias",
"target": "model.encoder_input_proj.1.1.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder_input_proj.1.1.num_batches_tracked",
"target": "model.encoder_input_proj.1.1.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.1.1.running_mean",
"target": "model.encoder_input_proj.1.1.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.1.1.running_var",
"target": "model.encoder_input_proj.1.1.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.1.1.weight",
"target": "model.encoder_input_proj.1.1.weight"
},
{
"expected_shape": [
256,
2048,
1,
1
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.2.0.weight",
"target": "model.encoder_input_proj.2.0.weight"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.2.1.bias",
"target": "model.encoder_input_proj.2.1.bias"
},
{
"expected_shape": [
"scalar"
],
"notes": "batch norm training counter copied from source; native inference may ignore it",
"source": "model.encoder_input_proj.2.1.num_batches_tracked",
"target": "model.encoder_input_proj.2.1.num_batches_tracked"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.2.1.running_mean",
"target": "model.encoder_input_proj.2.1.running_mean"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.2.1.running_var",
"target": "model.encoder_input_proj.2.1.running_var"
},
{
"expected_shape": [
256
],
"notes": "RT-DETR encoder input projection tensor reused without transpose",
"source": "model.encoder_input_proj.2.1.weight",
"target": "model.encoder_input_proj.2.1.weight"
}
]
}