import torch import torch.nn as nn def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1): """3x3 convolution with padding""" return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=dilation, groups=groups, bias=False, dilation=dilation) def conv1x1(in_planes, out_planes, stride=1): """1x1 convolution""" return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False) 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 = 4 def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm_layer=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): 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, layers, num_classes=1000, zero_init_residual=False, groups=1, width_per_group=64, replace_stride_with_dilation=None, norm_layer=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=2, padding=3, bias=False) self.bn1 = norm_layer(self.inplanes) self.relu = nn.ReLU(inplace=True) self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) 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]) self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) self.fc = nn.Linear(512 * block.expansion, num_classes) 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.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) def _make_layer(self, block, planes, blocks, stride=1, dilate=False): 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): # See note [TorchScript super()] x = self.conv1(x) x = self.bn1(x) x = self.relu(x) x = self.maxpool(x) #1/4 x4 = self.layer1(x) x8 = self.layer2(x)#8 x16 = self.layer3(x)#16 x32 = self.layer4(x)# 32 # x = self.avgpool(x) # x = torch.flatten(x, 1) # x = self.fc(x) return x4,x8,x16,x32 def forward(self, x): return self._forward_impl(x) def _resnet(block, layers, **kwargs): model = ResNet(block, layers, **kwargs) return model def resnet50(**kwargs): r"""ResNet-50 model from `"Deep Residual Learning for Image Recognition" `_ Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True, displays a progress bar of the download to stderr """ return _resnet(Bottleneck, [3, 4, 6, 3], **kwargs) def resnet101(**kwargs): r"""ResNet-101 model from `"Deep Residual Learning for Image Recognition" `_ Args: pretrained (bool): If True, returns a model pre-trained on ImageNet progress (bool): If True, displays a progress bar of the download to stderr """ return _resnet(Bottleneck, [3, 4, 23, 3], **kwargs) from typing import Dict, List from collections import OrderedDict from torch import nn, Tensor class IntermediateLayerGetter(nn.ModuleDict): """ Module wrapper that returns intermediate layers from a model It has a strong assumption that the modules have been registered into the model in the same order as they are used. This means that one should **not** reuse the same nn.Module twice in the forward if you want this to work. Additionally, it is only able to query submodules that are directly assigned to the model. So if `model` is passed, `model.feature1` can be returned, but not `model.feature1.layer2`. Args: model (nn.Module): model on which we will extract the features return_layers (Dict[name, new_name]): a dict containing the names of the modules for which the activations will be returned as the key of the dict, and the value of the dict is the name of the returned activation (which the user can specify). """ _version = 2 __annotations__ = { "return_layers": Dict[str, str], } def __init__(self, model: nn.Module, return_layers: Dict[str, str]) -> None: if not set(return_layers).issubset([name for name, _ in model.named_children()]): raise ValueError("return_layers are not present in model") orig_return_layers = return_layers return_layers = {str(k): str(v) for k, v in return_layers.items()} # 重新构建backbone，将没有使用到的模块全部删掉 layers = OrderedDict() for name, module in model.named_children(): layers[name] = module if name in return_layers: del return_layers[name] if not return_layers: break super(IntermediateLayerGetter, self).__init__(layers) self.return_layers = orig_return_layers def forward(self, x: Tensor) -> Dict[str, Tensor]: out = OrderedDict() for name, module in self.items(): x = module(x) if name in self.return_layers: out_name = self.return_layers[name] out[out_name] = x return out