Runtime Error: mat1 and mat2 shapes cannot be multiplied (16x756900 and 3048516x30)

Question

How can I solve this problem?

class Net(nn.Module):
    def __init__(self):
        super().__init__()
        
        self.conv1 = nn.Conv2d(3,8,11, padding=0) # in_channel, out_channel, kernel size
        self.pool = nn.MaxPool2d(2,2) # kernel_size, stride
        self.conv2 = nn.Conv2d(8, 36, 5, padding=0)
        self.fc1 = nn.Linear(36*291*291, 30) # in_features, out_features
        self.fc2 = nn.Linear(30, 20)
        self.fc3 = nn.Linear(20, 10)


    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = torch.flatten(x, 1) # flatten all dimensions except batch
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

I wrote my code like this, but I got "Runtime Error: mat1 and mat2 shapes cannot be multiplied".

The input shape is:'torch.Size([3,600,600])' ,with 3 channels. Please help me!

Answer 1

756900 Just change the model definition, the output shape of your last convolution layer does not have the shape 36x291x291. Just change the model definition to:

class Net(nn.Module):
    def __init__(self):
        super().__init__()
        
        self.conv1 = nn.Conv2d(3,8,11, padding=0) # in_channel, out_channel, kernel size
        self.pool = nn.MaxPool2d(2,2) # kernel_size, stride
        self.conv2 = nn.Conv2d(8, 36, 5, padding=0)
        self.fc1 = nn.Linear(756900, 30) # in_features, out_features
        self.fc2 = nn.Linear(30, 20)
        self.fc3 = nn.Linear(20, 10)


    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = torch.flatten(x, 1) # flatten all dimensions except batch
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

Tried the same with your input size, and it works.