使用pytorch的resnet50中缺少/意外密钥

我发现以下错误，但不知道原因：

Missing key(s) in state_dict: "layer2.0.layer.0.inplace.0.weight", "layer2.0.layer.0.inplace.0.bias",...

Unexpected key(s) in state_dict: "layer2.0.layer.0.0.weight", "layer2.0.layer.0.0.bias",...

我设置的频道大小似乎正是我想要的。然而，我不知道错误在哪里

import torch.nn as nn

#1x1 convolution
def conv1x1(in_channels: object, out_channels: object, stride: object, padding: object) -> object:

    model = nn.Sequential(
        nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride, padding=padding),
        nn.BatchNorm2d(out_channels),
        nn.ReLU(inplace=True)
    )
    return model


# 3x3 convolution
def conv3x3(in_channels: object, out_channels: object, stride: object, padding: object) -> object:
    model = nn.Sequential(
        nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=padding),
        nn.BatchNorm2d(out_channels),
        nn.ReLU(inplace=True)
    )
    return model


class ResidualBlock(nn.Module):
    def __init__(self, in_channels, middle_channels, out_channels, downsample=False):
        super(ResidualBlock, self).__init__()
        self.downsample = downsample

        if self.downsample:
            self.layer = nn.Sequential(
                nn.ReLU(conv1x1(in_channels, middle_channels,1,0)),
                nn.ReLU(conv3x3(middle_channels, middle_channels,1,0)),
                nn.ReLU(conv1x1(middle_channels,out_channels,1,0))
            )
            self.downsize = conv1x1(in_channels, out_channels, 2, 0)

        else:
            self.layer = nn.Sequential(
                nn.ReLU(conv1x1(in_channels,middle_channels,2,0)),
                nn.ReLU(conv3x3(middle_channels,middle_channels,2,0)),
                nn.ReLU(conv1x1(middle_channels,out_channels,2,0))
            )
            self.make_equal_channel = conv1x1(in_channels, out_channels, 1, 0)

    def forward(self, x):
        if self.downsample:
            out = self.layer(x)
            x = self.downsize(x)
            return out + x
        else:
            out = self.layer(x)
            if x.size() is not out.size():
                x = self.make_equal_channel(x)
            return out + x


class ResNet50_layer4(nn.Module):
    def __init__(self, num_classes= 10 ): # Hint : How many classes in Cifar-10 dataset?
        super(ResNet50_layer4, self).__init__()
        self.layer1 = nn.Sequential(
            #in_channels, out_channels, kernel_size, stride, padding
            nn.Conv2d(in_channels=3, out_channels=64, kernel_size=7, stride=2, padding=3),
                # Hint : Through this conv-layer, the input image size is halved.
                #        Consider stride, kernel size, padding and input & output channel sizes.
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2, padding=0)
        )
        self.layer2 = nn.Sequential(
            #in_channels, middle_channels, out_channels, downsample=False
            ResidualBlock(in_channels=64, middle_channels=64, out_channels=256, downsample=False),
            ResidualBlock(in_channels=256, middle_channels=64, out_channels=256, downsample=False),
            ResidualBlock(in_channels=256, middle_channels=64,out_channels=256, downsample=True)
        )
        self.layer3 = nn.Sequential(
            ResidualBlock(in_channels=256, middle_channels=128, out_channels=512, downsample=False),
            ResidualBlock(in_channels=512, middle_channels=128, out_channels=512, downsample=False),
            ResidualBlock(in_channels=512, middle_channels=128, out_channels=512, downsample=False),
            ResidualBlock(in_channels=512, middle_channels=128, out_channels=512, downsample=True)
        )
        self.layer4 = nn.Sequential(
            ResidualBlock(in_channels=512, middle_channels=256, out_channels=1024, downsample=False),
            ResidualBlock(in_channels=1024, middle_channels=256, out_channels=1024, downsample=False),
            ResidualBlock(in_channels=1024, middle_channels=256, out_channels=1024, downsample=False),
            ResidualBlock(in_channels=1024, middle_channels=256, out_channels=1024, downsample=False),
            ResidualBlock(in_channels=1024, middle_channels=256, out_channels=1024, downsample=False),
            ResidualBlock(in_channels=1024, middle_channels=256, out_channels=1024, downsample=False)

        )

        self.fc = nn.Linear(1024, 10) 
        self.avgpool = nn.AvgPool2d(7, stride=1)

        for m in self.modules():
            if isinstance(m, nn.Linear):
                nn.init.xavier_uniform_(m.weight.data)
            elif isinstance(m, nn.Conv2d):
                nn.init.xavier_uniform_(m.weight.data)

    def forward(self, x):

        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = self.avgpool(out)
        out = out.view(out.size()[0], -1)
        out = self.fc(out)

        return out

---

您已更改了模型，因此，关键点已更改。因此，您将得到一个不匹配错误。我认为您已经在ResidualBlock中的顺序包装中添加了nn.ReLU

在剩余块中，您有：

self.layer = nn.Sequential(
    nn.ReLU(conv1x1(in_channels, middle_channels, 2, 0)),
    nn.ReLU(conv3x3(middle_channels, middle_channels, 2, 0)),
    nn.ReLU(conv1x1(middle_channels, out_channels, 2, 0))
)

但是，在conv1x1和conv3x3中，您已经将nn.ReLUinplace=True作为nn.Sequential中的最后一层。因此，在中有另一个nn.ReLU

似乎没有必要。如果删除nn.ReLU，则键将匹配

我将剩余块修改如下

class ResidualBlock(nn.Module):
    def __init__(self, in_channels, middle_channels, out_channels, downsample=False):
        super(ResidualBlock, self).__init__()
        self.downsample = downsample

        if self.downsample:
            self.layer = nn.Sequential(
                conv1x1(in_channels, middle_channels, 1, 0),
                conv3x3(middle_channels, middle_channels, 1, 0),
                conv1x1(middle_channels, out_channels, 1, 0)
            )
            self.downsize = conv1x1(in_channels, out_channels, 2, 0)

        else:
            self.layer = nn.Sequential(
                conv1x1(in_channels, middle_channels, 2, 0),
                conv3x3(middle_channels, middle_channels, 2, 0),
                conv1x1(middle_channels, out_channels, 2, 0)
            )
            self.make_equal_channel = conv1x1(in_channels, out_channels, 1, 0)

    def forward(self, x):
        '''Your forward method description'''

现在，让我们测试一下

model = ResNet50_layer4()
for k, v in model.named_parameters():
    print(k)

输出：

layer1.0.weight
layer1.0.bias
layer1.1.weight
layer1.1.bias
layer2.0.layer.0.0.weight
layer2.0.layer.0.0.bias
layer2.0.layer.0.1.weight
layer2.0.layer.0.1.bias
...
...

---

如果您仍想使用附加的nn.ReLU，可以训练修改后的模型并保存权重，然后尝试重新加载权重，它会起作用。

@Benedikt如果我的答案对您有帮助，您可以接受：

layer1.0.weight
layer1.0.bias
layer1.1.weight
layer1.1.bias
layer2.0.layer.0.0.weight
layer2.0.layer.0.0.bias
layer2.0.layer.0.1.weight
layer2.0.layer.0.1.bias
...
...