Why am I wrong in the input of the tensor?

Question

Here is my class for cnn.

class SimpleCnn(nn.Module):

def __init__(self, n_classes):
    super().__init__()
    self.layer1 = nn.Sequential(   # 224*224
        nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, padding=1),
        nn.ReLU(),
        nn.BatchNorm2d(64),
        nn.MaxPool2d(kernel_size=2, stride=2)
    )
    self.layer2 = nn.Sequential(   # 112*112
        nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=128, out_channels=128, kernel_size=3, padding=1),
        nn.ReLU(),
        nn.BatchNorm2d(128),
        nn.MaxPool2d(kernel_size=2, stride=2)
    )
    self.layer3 = nn.Sequential(   # 56*56
        nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, padding=1),
        nn.ReLU(),
        nn.BatchNorm2d(256),
        nn.MaxPool2d(kernel_size=2, stride=2)
    )
    self.layer3 = nn.Sequential(   # 28*28
        nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
        nn.ReLU(),
        nn.BatchNorm2d(512),
        nn.MaxPool2d(kernel_size=2, stride=2)
    )
    self.layer4 = nn.Sequential(   # 14*14
        nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
        nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, padding=1),
        nn.ReLU(),
        nn.BatchNorm2d(512),
        nn.MaxPool2d(kernel_size=2, stride=2)
    )
    self.out1 = nn.Linear(512*7*7, 4096)   # 7*7
    self.out2 = nn.Linear(4096, n_classes)
def forward(self, x):
    x = self.layer1(x)
    x = self.layer2(x)
    x = self.layer3(x)
    x = self.layer4(x)

    x = x.view(1, -1)
    x = self.out1(x)
    logits = self.out2(x)
    return logits  

And it returns such a mistake.

RuntimeError: Given groups=1, weight of size [512, 256, 3, 3], expected input[64, 128, 56, 56] to have 256 channels, but got 128 channels instead.

I've seen other mistakes of such a type but can't find where I'm wrong here. Thank you for your answer.

Answer 1

In your code self.layer3 is first defined but then overwritten (a copy-pasta error I assume?). The error is thrown because in the redefinition of layer3 you assume the input has 256 channels, but the output from self.layer2 only has 128 channels.