mismatched code and example image in beginner/blitz/neural_networks_tutorial.html

[csukuangfj]

This image at https://pytorch.org/tutorials/_images/mnist.png

shows that S4 is 16@5x5,

but the code

tutorials/beginner_source/blitz/neural_networks_tutorial.py

Line 54 in 809f27e

self.fc1 = nn.Linear(16 * 6 * 6, 120) # 6*6 from image dimension

says 16@6x6.

Since it is easier to change the code, the following lines

tutorials/beginner_source/blitz/neural_networks_tutorial.py

Lines 51 to 54 in 809f27e

	self.conv1 = nn.Conv2d(1, 6, 3)
	self.conv2 = nn.Conv2d(6, 16, 3)
	# an affine operation: y = Wx + b
	self.fc1 = nn.Linear(16 * 6 * 6, 120) # 6*6 from image dimension

should be changed to

        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 

[csukuangfj]

Furthermore, there is no need to define num_flat_features

tutorials/beginner_source/blitz/neural_networks_tutorial.py

Lines 63 to 74 in 809f27e

	x = x.view(-1, self.num_flat_features(x))
	x = F.relu(self.fc1(x))
	x = F.relu(self.fc2(x))
	x = self.fc3(x)
	return x
	def num_flat_features(self, x):
	size = x.size()[1:] # all dimensions except the batch dimension
	num_features = 1
	for s in size:
	num_features *= s
	return num_features

just use

x = x.view(x.shape[0], -1)

[holly1238]

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