Replace num_flat_features with torch.flatten (pytorch#1505)

Apply the best practices from alexnet
https://github.com/pytorch/vision/blob/master/torchvision/models/alexnet.py#L48

Author: apivovarov

beginner_source/blitz/cifar10_tutorial.py

@@ -136,7 +136,7 @@ def __init__(self):
     def forward(self, x):
         x = self.pool(F.relu(self.conv1(x)))
         x = self.pool(F.relu(self.conv2(x)))
-        x = x.view(-1, 16 * 5 * 5)
+        x = torch.flatten(x, 1) # flatten all dimensions except batch
         x = F.relu(self.fc1(x))
         x = F.relu(self.fc2(x))
         x = self.fc3(x)

beginner_source/blitz/neural_networks_tutorial.py

@@ -60,19 +60,12 @@ def forward(self, x):
         x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
         # If the size is a square, you can specify with a single number
         x = F.max_pool2d(F.relu(self.conv2(x)), 2)
-        x = x.view(-1, self.num_flat_features(x))
+        x = torch.flatten(x, 1) # flatten all dimensions except the batch dimension
         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
-
 
 net = Net()
 print(net)
@@ -171,7 +164,7 @@ def num_flat_features(self, x):
 # ::
 #
 #     input -> conv2d -> relu -> maxpool2d -> conv2d -> relu -> maxpool2d
-#           -> view -> linear -> relu -> linear -> relu -> linear
+#           -> flatten -> linear -> relu -> linear -> relu -> linear
 #           -> MSELoss
 #           -> loss
 #