Beginner PyTorch - RuntimeError: shape '[16, 400]' is invalid for input of size 9600

Question

I'm trying to build a CNN but I get this error:

---> 52         x = x.view(x.size(0), 5 * 5 * 16)
RuntimeError: shape '[16, 400]' is invalid for input of size 9600

It's not clear for me what the inputs of the 'x.view' line should be. Also, I don't really understand how many times I should have this 'x.view' function in my code. Is it only once, after the 3 convolutional layers and 2 linear layers? Or is it 5 times, one after every layer?

Here's my code:

CNN

import torch.nn.functional as F

# Convolutional neural network
class ConvNet(nn.Module):

    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()

        self.conv1 = nn.Conv2d(
            in_channels=3, 
            out_channels=16, 
            kernel_size=3)

        self.conv2 = nn.Conv2d(
            in_channels=16, 
            out_channels=24, 
            kernel_size=4)

        self.conv3 = nn.Conv2d(
            in_channels=24, 
            out_channels=32, 
            kernel_size=4)

        self.dropout = nn.Dropout2d(p=0.3)

        self.pool = nn.MaxPool2d(2)

        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(512, 10)

        self.final = nn.Softmax(dim=1)

    def forward(self, x):

        print('shape 0 ' + str(x.shape))

        x = F.max_pool2d(F.relu(self.conv1(x)), 2)  
        x = self.dropout(x)

        print('shape 1 ' + str(x.shape))

        x = F.max_pool2d(F.relu(self.conv2(x)), 2)  
        x = self.dropout(x)

        print('shape 2 ' + str(x.shape))

        # x = F.max_pool2d(F.relu(self.conv3(x)), 2)  
        # x = self.dropout(x)

        x = F.interpolate(x, size=(5, 5))  
        x = x.view(x.size(0), 5 * 5 * 16)

        x = self.fc1(x) 

        return x

net = ConvNet()

Can someone help me understand the problem?

The output of 'x.shape' is:

shape 0 torch.Size([16, 3, 256, 256])

shape 1 torch.Size([16, 16, 127, 127])

shape 2 torch.Size([16, 24, 62, 62])

Thanks

Solution

This means that instead the product of the channel and spatial dimensions is not 5*5*16. To flatten the tensor, replace x = x.view(x.size(0), 5 * 5 * 16) with:

x = x.view(x.size(0), -1)

And self.fc1 = nn.Linear(600, 120) with:

self.fc1 = nn.Linear(600, 120)

Comments

[mokiliii Lo]

Thanks for your answer. Should I flatten the tensor at each convolution, or just once after my 3 convolutions, or 5 times (bc I have 5 layers in total), or.. ?

[ccl]

Tensor flattening is done right before your fully-connected (linear) layer(s), so you only have to do it once i.e. after F.interpolate().

[ccl]

Did my answer help? If so feel free to accept/vote on this answer.

[mokiliii Lo]

Not really, I'm getting another error now: RuntimeError: size mismatch, m1: [16 x 800], m2: [600 x 120] any idea?

[ccl]

Did you modify your code/input size? Did you add an FC layer?

[Sameen]

The size mismatch issue is mainly caused by the input size, make sure your input is not smaller than what the net is expecting.