Changing to AdaptiveAvgPool2d on Alexnet (#746)

The update allows Alexnet to process images larger or smaller than prescribed imagenet size using adaptive average pooling. Will be useful while finetuning or testing on different resolution images. Similar to https://github.com/pytorch/vision/pull/643 and https://github.com/pytorch/vision/pull/672. I did not include adaptive avg pool in features or classifier block so that these predefined blocks can be used as it is.

torchvision/models/alexnet.py

@@ -29,6 +29,7 @@ class AlexNet(nn.Module):
             nn.ReLU(inplace=True),
             nn.MaxPool2d(kernel_size=3, stride=2),
         )
+        self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
         self.classifier = nn.Sequential(
             nn.Dropout(),
             nn.Linear(256 * 6 * 6, 4096),
@@ -41,6 +42,7 @@ class AlexNet(nn.Module):
 
     def forward(self, x):
         x = self.features(x)
+        x = self.avgpool(x)
         x = x.view(x.size(0), 256 * 6 * 6)
         x = self.classifier(x)
         return x