fix NN architecture image vs code mismatch

The network architecture shows images of 5x5 size, while in code, it is written 6x6.
Later in the tutorial, the correct architecture of 5x5 is shown.

Author: boulabiar

beginner_source/blitz/neural_networks_tutorial.py

@@ -51,7 +51,7 @@ def __init__(self):
         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 
+        self.fc1 = nn.Linear(16 * 5 * 5, 120)  # 5*5 from image dimension 
         self.fc2 = nn.Linear(120, 84)
         self.fc3 = nn.Linear(84, 10)