Wrong designed network for depicted model on PyTorch 60-Minute Blitz

[javadr]

At first, I would like to express my great appreciation to those who created such a nice package with a great manual specially @brianjo for making PyTorch 60-Minute Blitz.

While I was reading this page, I confused with the code that didn't match the illustrated model.
The page started with a model network and then tried to implement it via PyTorch.
But there are subtle typos in it. (I named it typo because I'm sure the one who made it is an expert)
Both conv1 and conv2 in the code must have kernel_size=5 not 3 in compliance with shown model at the beginning of the article -- the correction is here:

self.conv1 = nn.Conv2d(1, 6, 5)
self.conv2 = nn.Conv2d(6, 16, 5)
# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16 * 5 * 5, 120)  # 5*5 from image dimension

https://github.com/pytorch/tutorials/blob/master/beginner_source/blitz/neural_networks_tutorial.py

[bigbigyellow]

I was confused by this number for a long time,thank you!

[holly1238]

Closing this issue. This issue was fixed and merged in #1257.