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().__init__() if norm_layer isNone: norm_layer = nn.BatchNorm2d if groups != 1or base_width != 64: raise ValueError("BasicBlock only supports groups=1 and base_width=64") if dilation > 1: #空洞卷积 raise NotImplementedError("Dilation > 1 not supported in BasicBlock") # Both self.conv1 and self.downsample layers downsample the input when stride != 1 如果stride=1就不使用下采样 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
defforward(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 isnotNone: identity = self.downsample(x)
out += identity out = self.relu(out)
return out
Bottleneck
classBottleneck(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().__init__() if norm_layer isNone: norm_layer = nn.BatchNorm2d width = int(planes * (base_width / 64.0)) * 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
defforward(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 isnotNone: identity = self.downsample(x)
self.inplanes = 64 self.dilation = 1 if replace_stride_with_dilation isNone: # 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] iflen(replace_stride_with_dilation) != 3: raise ValueError( "replace_stride_with_dilation should be None " f"or a 3-element tuple, got {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(): ifisinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, mode="fan_out", nonlinearity="relu") elifisinstance(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(): ifisinstance(m, Bottleneck): nn.init.constant_(m.bn3.weight, 0) # type: ignore[arg-type] elifisinstance(m, BasicBlock): nn.init.constant_(m.bn2.weight, 0) # type: ignore[arg-type]
defresnet18(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet: r"""ResNet-18 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. 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("resnet18", BasicBlock, [2, 2, 2, 2], pretrained, progress, **kwargs)
defresnet34(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet: r"""ResNet-34 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. 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("resnet34", BasicBlock, [3, 4, 6, 3], pretrained, progress, **kwargs)
defresnet50(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet: r"""ResNet-50 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. 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("resnet50", Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs)
defresnet101(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet: r"""ResNet-101 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. 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("resnet101", Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs)
defresnet152(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> ResNet: r"""ResNet-152 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. 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("resnet152", Bottleneck, [3, 8, 36, 3], pretrained, progress, **kwargs)
打印模型
from torchsummary import summary net = resnet34() summary(net, (3, 224, 224))
