PyTorch實現的ResNeXt

Aggregated Residual Transformations for Deep Neural Networks
PDF: https://arxiv.org/pdf/1611.05431.pdf
PyTorch代碼: https://github.com/shanglianlm0525/PyTorch-Networks

ResNeXt的三個版本

PyTorch代碼:

class ResNeXtBlock(nn.Module):
    def __init__(self,in_places,places, stride=1,downsampling=False, expansion = 2, cardinality=32):
        super(ResNeXtBlock,self).__init__()
        self.expansion = expansion
        self.downsampling = downsampling

        self.bottleneck = nn.Sequential(
            nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=1, stride=1, bias=False),
            nn.BatchNorm2d(places),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False, groups=cardinality),
            nn.BatchNorm2d(places),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels=places, out_channels=places * self.expansion, kernel_size=1, stride=1, bias=False),
            nn.BatchNorm2d(places * self.expansion),
        )

        if self.downsampling:
            self.downsample = nn.Sequential(
                nn.Conv2d(in_channels=in_places, out_channels=places * self.expansion, kernel_size=1, stride=stride,bias=False),
                nn.BatchNorm2d(places * self.expansion)
            )
        self.relu = nn.ReLU(inplace=True)

    def forward(self, x):
        residual = x
        out = self.bottleneck(x)

        if self.downsampling:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)
        return out

可以直接將VGG 和 ResNet中的Block換做 ResNeXt block