Image of the example convnet is not consistent with the implementation

[hagoston]

In the tutorial of neural networks, the image of the example convnet is not the same as the code below it.

Based on the image conv layers should have 5x5 square kernels:
self.conv1 = nn.Conv2d(1, 6, 5)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)

[itstartstosnow]

Yes, I encountered this problem too while going through the tutorial. It is a minor issue but it did take me a while to search the documentation and try to understand the output shape of conv2d ....

[holly1238]

Kernel size is 5x5. This was fixed in the tutorial in #1257.