Modifying the comments of inceptionV3 dimensions (#748)

* Modifying the comments of inceptionV3 dimensions

Modifying the comments of inceptionV3 dimensions to match the pytorch convention. Relevant (#719 (review))

* Added Batch size in comment

* Update inception.py

Author: ekagra-ranjan

torchvision/models/inception.py

@@ -19,7 +19,7 @@ def inception_v3(pretrained=False, **kwargs):
 
     .. note::
         **Important**: In contrast to the other models the inception_v3 expects tensors with a size of
-        299x299x3, so ensure your images are sized accordingly.
+        N x 3 x 299 x 299, so ensure your images are sized accordingly.
 
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
@@ -78,55 +78,55 @@ def forward(self, x):
             x_ch1 = torch.unsqueeze(x[:, 1], 1) * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
             x_ch2 = torch.unsqueeze(x[:, 2], 1) * (0.225 / 0.5) + (0.406 - 0.5) / 0.5
             x = torch.cat((x_ch0, x_ch1, x_ch2), 1)
-        # 299 x 299 x 3
+        # N x 3 x 299 x 299
         x = self.Conv2d_1a_3x3(x)
-        # 149 x 149 x 32
+        # N x 32 x 149 x 149
         x = self.Conv2d_2a_3x3(x)
-        # 147 x 147 x 32
+        # N x 32 x 147 x 147
         x = self.Conv2d_2b_3x3(x)
-        # 147 x 147 x 64
+        # N x 64 x 147 x 147
         x = F.max_pool2d(x, kernel_size=3, stride=2)
-        # 73 x 73 x 64
+        # N x 64 x 73 x 73
         x = self.Conv2d_3b_1x1(x)
-        # 73 x 73 x 80
+        # N x 80 x 73 x 73
         x = self.Conv2d_4a_3x3(x)
-        # 71 x 71 x 192
+        # N x 192 x 71 x 71
         x = F.max_pool2d(x, kernel_size=3, stride=2)
-        # 35 x 35 x 192
+        # N x 192 x 35 x 35
         x = self.Mixed_5b(x)
-        # 35 x 35 x 256
+        # N x 256 x 35 x 35
         x = self.Mixed_5c(x)
-        # 35 x 35 x 288
+        # N x 288 x 35 x 35 
         x = self.Mixed_5d(x)
-        # 35 x 35 x 288
+        # N x 288 x 35 x 35
         x = self.Mixed_6a(x)
-        # 17 x 17 x 768
+        # N x 768 x 17 x 17
         x = self.Mixed_6b(x)
-        # 17 x 17 x 768
+        # N x 768 x 17 x 17
         x = self.Mixed_6c(x)
-        # 17 x 17 x 768
+        # N x 768 x 17 x 17
         x = self.Mixed_6d(x)
-        # 17 x 17 x 768
+        # N x 768 x 17 x 17
         x = self.Mixed_6e(x)
-        # 17 x 17 x 768
+        # N x 768 x 17 x 17
         if self.training and self.aux_logits:
             aux = self.AuxLogits(x)
-        # 17 x 17 x 768
+        # N x 768 x 17 x 17
         x = self.Mixed_7a(x)
-        # 8 x 8 x 1280
+        # N x 1280 x 8 x 8
         x = self.Mixed_7b(x)
-        # 8 x 8 x 2048
+        # N x 2048 x 8 x 8
         x = self.Mixed_7c(x)
-        # 8 x 8 x 2048
+        # N x 2048 x 8 x 8
         # Adaptive average pooling
         x = F.adaptive_avg_pool2d(x, (1, 1))
-        # 1 x 1 x 2048
+        # N x 2048 x 1 x 1
         x = F.dropout(x, training=self.training)
-        # 1 x 1 x 2048
+        # N x 2048 x 1 x 1
         x = x.view(x.size(0), -1)
-        # 2048
+        # N x 2048
         x = self.fc(x)
-        # 1000 (num_classes)
+        # N x 1000 (num_classes)
         if self.training and self.aux_logits:
             return x, aux
         return x
@@ -305,20 +305,20 @@ def __init__(self, in_channels, num_classes):
         self.fc.stddev = 0.001
 
     def forward(self, x):
-        # 17 x 17 x 768
+        # N x 768 x 17 x 17
         x = F.avg_pool2d(x, kernel_size=5, stride=3)
-        # 5 x 5 x 768
+        # N x 768 x 5 x 5
         x = self.conv0(x)
-        # 5 x 5 x 128
+        # N x 128 x 5 x 5
         x = self.conv1(x)
-        # 1 x 1 x 768
+        # N x 768 x 1 x 1
         # Adaptive average pooling
         x = F.adaptive_avg_pool2d(x, (1, 1))
-        # 1 x 1 x 768
+        # N x 768 x 1 x 1
         x = x.view(x.size(0), -1)
-        # 768
+        # N x 768
         x = self.fc(x)
-        # 1000
+        # N x 1000
         return x