RuntimeError: Given groups=1, weight of size [8, 16, 3, 3], expected input[64, 32, 13, 13] to have 16 channels, but got 32 channels instead

Im getting the error

RuntimeError: Given groups=1, weight of size [8, 16, 3, 3], expected input[64, 32, 13, 13] to have 16 channels, but got 32 channels instead

Here is the network:

class Net(nn.Module):
    """A representation of a convolutional neural network comprised of VGG blocks."""
    def __init__(self, n_channels):
        super(Net, self).__init__()
        # VGG block 1
        self.conv1 = nn.Conv2d(n_channels, 64, (3,3))
        self.act1 = nn.ReLU()
        self.pool1 = nn.MaxPool2d((2,2), stride=(2,2))
        # VGG block 2
        self.conv2 = nn.Conv2d(64, 64, (3,3))
        self.act2 = nn.ReLU()
        self.pool2 = nn.MaxPool2d((2,2), stride=(2,2))
        # VGG block 3
        self.conv3 = nn.Conv2d(64, 128, (3,3))
        self.act3 = nn.ReLU()
        self.pool3 = nn.MaxPool2d((2,2), stride=(2,2))
        # Fully connected layer
        self.f1 = nn.Linear(8192, 1000)
        self.act4 = nn.ReLU()
        # Output layer
        self.f2 = nn.Linear(1000, 10)
        self.act5 = nn.Softmax(dim=1)

    def forward(self, X):
        """This function forward propagates the input."""
        # VGG block 1
        X = self.conv1(X)
        X = self.act1(X)
        X = self.pool1(X)
        # VGG block 2
        X = self.conv2(X)
        X = self.act2(X)
        X = self.pool2(X)
        # VGG block 3
        X = self.conv3(X)
        X = self.act3(X)
        X = self.pool3(X)
        print(X.shape)
        # Flatten
        X = X.view(-1, 8192)
        # Fully connected layer
        X = self.f1(X)
        X = self.act4(X)
        # Output layer
        X = self.f2(X)
        X = self.act5(X)

        return X
        

Why am I getting the above error?

Could you please provide an explanation with your answer? thanks.

Before

# VGG block 3
self.conv2 = nn.Conv2d(16, 8, (3,3))
self.act3 = nn.ReLU()
self.pool3 = nn.MaxPool2d((2,2), stride=(2,2))

After

# VGG block 3
self.conv3 = nn.Conv2d(16, 8, (3,3))
self.act3 = nn.ReLU()
self.pool3 = nn.MaxPool2d((2,2), stride=(2,2))
2 Likes

You are replacing self.conv2:

        self.conv2 = nn.Conv2d(32, 16, (3,3))
        self.act2 = nn.ReLU()
        self.pool2 = nn.MaxPool2d((2,2), stride=(2,2))
        # VGG block 3
        self.conv2 = nn.Conv2d(16, 8, (3,3))

The second self.conv2 definition should most likely be self.conv3.

EDIT: a few seconds too late! @Eta_C :stuck_out_tongue:

1 Like

yeah i noticed that typo too and i fixed it. But im having trouble determining the linear’s channels? I have written 8192 but its wrong. Im working on the mnist dataset whose images have the following shape: 1,28,28. I edited the network i posted.

Choose one:

  1. resize the input from (28, 28) to about (80, 80)
  2. use 256 instead of 8192

i chose to change it to 256 but i got this error ValueError: Expected input batch_size (32) to match target batch_size (64)