Download libs/model/backbone.py from uav-vts/training_sem: direct link, hf CLI and curl.
- Browser
- Download file 10.7 kB
-
https://huggingface.co/uav-vts/training_sem/resolve/main/libs/model/backbone.py
- Command line
-
hf download hf://uav-vts/training_sem/libs/model/backbone.py
-
curl -L -o backbone.py https://huggingface.co/uav-vts/training_sem/resolve/main/libs/model/backbone.py
10.7 kB
| import torch | |
| from torch import Tensor | |
| import torch.nn as nn | |
| from typing import Type, Any, Callable, Union, List, Optional | |
| model_paths = { | |
| 'resnet18': '/yrfs2/cv6/frwang/PretrainedModelParams/pytorch/ImageNet/ResNet/resnet18-5c106cde.pth', | |
| 'resnet34': '/Pretrain/resnet_34.pth', | |
| 'resnet50': '/yrfs2/cv6/frwang/PretrainedModelParams/pytorch/ImageNet/ResNet/resnet50-19c8e357.pth', | |
| 'resnet101': '/yrfs2/cv6/frwang/PretrainedModelParams/pytorch/ImageNet/ResNet/resnet101-5d3b4d8f.pth', | |
| 'resnet152': '/yrfs2/cv6/frwang/PretrainedModelParams/pytorch/ImageNet/ResNet/resnet152-b121ed2d.pth', | |
| } | |
| def conv3x3(in_planes: int, out_planes: int, stride: int = 1, groups: int = 1, dilation: int = 1) -> nn.Conv2d: | |
| """3x3 convolution with padding""" | |
| return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, | |
| padding=dilation, groups=groups, bias=False, dilation=dilation, padding_mode='reflect') | |
| def conv1x1(in_planes: int, out_planes: int, stride: int = 1) -> nn.Conv2d: | |
| """1x1 convolution""" | |
| return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False) | |
| class BasicBlock(nn.Module): | |
| expansion: int = 1 | |
| def __init__( | |
| self, | |
| inplanes: int, | |
| planes: int, | |
| stride: int = 1, | |
| downsample: Optional[nn.Module] = None, | |
| groups: int = 1, | |
| base_width: int = 64, | |
| dilation: int = 1, | |
| norm_layer: Optional[Callable[..., nn.Module]] = None | |
| ) -> None: | |
| super(BasicBlock, self).__init__() | |
| if norm_layer is None: | |
| norm_layer = nn.BatchNorm2d | |
| if groups != 1 or base_width != 64: | |
| raise ValueError('BasicBlock only supports groups=1 and base_width=64') | |
| if dilation > 1: | |
| raise NotImplementedError("Dilation > 1 not supported in BasicBlock") | |
| # Both self.conv1 and self.downsample layers downsample the input when stride != 1 | |
| self.conv1 = conv3x3(inplanes, planes, stride) | |
| self.bn1 = norm_layer(planes) | |
| self.relu = nn.ReLU(inplace=True) | |
| self.conv2 = conv3x3(planes, planes) | |
| self.bn2 = norm_layer(planes) | |
| self.downsample = downsample | |
| self.stride = stride | |
| def forward(self, x: Tensor) -> Tensor: | |
| identity = x | |
| out = self.conv1(x) | |
| out = self.bn1(out) | |
| out = self.relu(out) | |
| out = self.conv2(out) | |
| out = self.bn2(out) | |
| if self.downsample is not None: | |
| identity = self.downsample(x) | |
| out += identity | |
| out = self.relu(out) | |
| return out | |
| class Bottleneck(nn.Module): | |
| # Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2) | |
| # while original implementation places the stride at the first 1x1 convolution(self.conv1) | |
| # according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385. | |
| # This variant is also known as ResNet V1.5 and improves accuracy according to | |
| # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch. | |
| expansion: int = 4 | |
| def __init__( | |
| self, | |
| inplanes: int, | |
| planes: int, | |
| stride: int = 1, | |
| downsample: Optional[nn.Module] = None, | |
| groups: int = 1, | |
| base_width: int = 64, | |
| dilation: int = 1, | |
| norm_layer: Optional[Callable[..., nn.Module]] = None | |
| ) -> None: | |
| super(Bottleneck, self).__init__() | |
| if norm_layer is None: | |
| norm_layer = nn.BatchNorm2d | |
| width = int(planes * (base_width / 64.)) * groups | |
| # Both self.conv2 and self.downsample layers downsample the input when stride != 1 | |
| self.conv1 = conv1x1(inplanes, width) | |
| self.bn1 = norm_layer(width) | |
| self.conv2 = conv3x3(width, width, stride, groups, dilation) | |
| self.bn2 = norm_layer(width) | |
| self.conv3 = conv1x1(width, planes * self.expansion) | |
| self.bn3 = norm_layer(planes * self.expansion) | |
| self.relu = nn.ReLU(inplace=True) | |
| self.downsample = downsample | |
| self.stride = stride | |
| def forward(self, x: Tensor) -> Tensor: | |
| identity = x | |
| out = self.conv1(x) | |
| out = self.bn1(out) | |
| out = self.relu(out) | |
| out = self.conv2(out) | |
| out = self.bn2(out) | |
| out = self.relu(out) | |
| out = self.conv3(out) | |
| out = self.bn3(out) | |
| if self.downsample is not None: | |
| identity = self.downsample(x) | |
| out += identity | |
| out = self.relu(out) | |
| return out | |
| class ResNet(nn.Module): | |
| def __init__( | |
| self, | |
| block: Type[Union[BasicBlock, Bottleneck]], | |
| layers: List[int], | |
| zero_init_residual: bool = False, | |
| groups: int = 1, | |
| width_per_group: int = 64, | |
| replace_stride_with_dilation: Optional[List[bool]] = None, | |
| norm_layer: Optional[Callable[..., nn.Module]] = None | |
| ) -> None: | |
| super(ResNet, self).__init__() | |
| if norm_layer is None: | |
| norm_layer = nn.BatchNorm2d | |
| self._norm_layer = norm_layer | |
| self.inplanes = 64 | |
| self.dilation = 1 | |
| if replace_stride_with_dilation is None: | |
| # each element in the tuple indicates if we should replace | |
| # the 2x2 stride with a dilated convolution instead | |
| replace_stride_with_dilation = [False, False, False] | |
| if len(replace_stride_with_dilation) != 3: | |
| raise ValueError("replace_stride_with_dilation should be None " | |
| "or a 3-element tuple, got {}".format(replace_stride_with_dilation)) | |
| self.groups = groups | |
| self.base_width = width_per_group | |
| self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=1, padding=3, | |
| bias=False, padding_mode='reflect') | |
| self.bn1 = norm_layer(self.inplanes) | |
| self.relu = nn.ReLU(inplace=True) | |
| self.layer1 = self._make_layer(block, 64, layers[0]) | |
| self.layer2 = self._make_layer(block, 128, layers[1], stride=2, | |
| dilate=replace_stride_with_dilation[0]) | |
| self.layer3 = self._make_layer(block, 256, layers[2], stride=2, | |
| dilate=replace_stride_with_dilation[1]) | |
| self.layer4 = self._make_layer(block, 512, layers[3], stride=2, | |
| dilate=replace_stride_with_dilation[2]) | |
| for m in self.modules(): | |
| if isinstance(m, nn.Conv2d): | |
| nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') | |
| elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)): | |
| nn.init.constant_(m.weight, 1) | |
| nn.init.constant_(m.bias, 0) | |
| # Zero-initialize the last BN in each residual branch, | |
| # so that the residual branch starts with zeros, and each residual block behaves like an identity. | |
| # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677 | |
| if zero_init_residual: | |
| for m in self.modules(): | |
| if isinstance(m, Bottleneck): | |
| nn.init.constant_(m.bn3.weight, 0) # type: ignore[arg-type] | |
| elif isinstance(m, BasicBlock): | |
| nn.init.constant_(m.bn2.weight, 0) # type: ignore[arg-type] | |
| def _make_layer(self, block: Type[Union[BasicBlock, Bottleneck]], planes: int, blocks: int, | |
| stride: int = 1, dilate: bool = False) -> nn.Sequential: | |
| norm_layer = self._norm_layer | |
| downsample = None | |
| previous_dilation = self.dilation | |
| if dilate: | |
| self.dilation *= stride | |
| stride = 1 | |
| if stride != 1 or self.inplanes != planes * block.expansion: | |
| downsample = nn.Sequential( | |
| conv1x1(self.inplanes, planes * block.expansion, stride), | |
| norm_layer(planes * block.expansion), | |
| ) | |
| layers = [] | |
| layers.append(block(self.inplanes, planes, stride, downsample, self.groups, | |
| self.base_width, previous_dilation, norm_layer)) | |
| self.inplanes = planes * block.expansion | |
| for _ in range(1, blocks): | |
| layers.append(block(self.inplanes, planes, groups=self.groups, | |
| base_width=self.base_width, dilation=self.dilation, | |
| norm_layer=norm_layer)) | |
| return nn.Sequential(*layers) | |
| def _forward_impl(self, x: Tensor) -> Tensor: | |
| input = x # (512, 256) | |
| x = self.conv1(x) # (256, 128) # stride=2 | |
| x = self.bn1(x) # (256, 128) | |
| x = self.relu(x) # (256, 128) | |
| c2 = self.layer1(x) # (256, 128) # stride=1, total_stride=2 | |
| c3 = self.layer2(c2) # (128, 64) # stride=2, total_stride=4 | |
| c4 = self.layer3(c3) # (64, 32) # stride=2, total_stride=8 | |
| c5 = self.layer4(c4) # (32, 16) # stride=2, total_stride=16 | |
| return c2, c3, c4, c5 | |
| def forward(self, x: Tensor) -> Tensor: | |
| return self._forward_impl(x) | |
| def _resnet( | |
| arch: str, | |
| block: Type[Union[BasicBlock, Bottleneck]], | |
| layers: List[int], | |
| pretrained: bool, | |
| **kwargs: Any | |
| ) -> ResNet: | |
| model = ResNet(block, layers, **kwargs) | |
| if pretrained: | |
| checkpoint = torch.load(model_paths[arch], map_location='cpu') | |
| state_dict = model.state_dict() | |
| for key, val in state_dict.items(): | |
| if key in checkpoint: | |
| if val.shape == checkpoint[key].shape: | |
| state_dict[key] = checkpoint[key] | |
| model.load_state_dict(state_dict) | |
| return model | |
| def resnet18(pretrained: bool = False, **kwargs: Any) -> ResNet: | |
| return _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, **kwargs) | |
| def resnet34(pretrained: bool = False, **kwargs: Any) -> ResNet: | |
| return _resnet('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, **kwargs) | |
| def resnet50(pretrained: bool = False, **kwargs: Any) -> ResNet: | |
| return _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, **kwargs) | |
| def resnet101(pretrained: bool = False, **kwargs: Any) -> ResNet: | |
| return _resnet('resnet101', Bottleneck, [3, 4, 23, 3], pretrained, **kwargs) | |
| def resnet152(pretrained: bool = False, **kwargs: Any) -> ResNet: | |
| return _resnet('resnet152', Bottleneck, [3, 8, 36, 3], pretrained, **kwargs) | |
| def build_backbone(arch, pretrained=True, norm_layer=nn.BatchNorm2d): | |
| arch_map = { | |
| 'res34': resnet34, | |
| 'res50': resnet50, | |
| 'res101': resnet101, | |
| 'res152': resnet152 | |
| } | |
| if arch not in arch_map: | |
| raise ValueError('Unknown backbone arch: %s' % arch) | |
| return arch_map[arch](pretrained=pretrained, norm_layer=norm_layer) |