fix transform for rcnns so original images list is unchanged (#1084)

* fix transform for rcnns so original images are unchanged

* transform does not change input list anymore

transform does not change input list anymore. Improve code according to reviewer comment

* transform for maskrcnn no longer modify input list

transform for maskrcnn no longer modify input list. improve code according to comment

* transform for maskrcnn no longer modifies input list

torchvision/models/detection/transform.py

@@ -30,6 +30,7 @@ class GeneralizedRCNNTransform(nn.Module):
         self.image_std = image_std
 
     def forward(self, images, targets=None):
+        images = images[:]
         for i in range(len(images)):
             image = images[i]
             target = targets[i] if targets is not None else targets
@@ -41,6 +42,7 @@ class GeneralizedRCNNTransform(nn.Module):
             images[i] = image
             if targets is not None:
                 targets[i] = target
+
         image_sizes = [img.shape[-2:] for img in images]
         images = self.batch_images(images)
         image_list = ImageList(images, image_sizes)