Clarify scaling of ToTensor transform for target masks in the documen…

…tation
pytorch · Jul 25, 2020 · c859d7e · c859d7e
1 parent 1aef87d
commit c859d7e
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/torchvision/transforms/transforms.py b/torchvision/transforms/transforms.py
@@ -73,6 +73,10 @@ class ToTensor(object):
     or if the numpy.ndarray has dtype = np.uint8
 
     In the other cases, tensors are returned without scaling.
+    
+    .. note::
+        Because the input image is scaled to [0.0, 1.0], this transformation should not be used when 
+        transforming target image masks. See the references for implementing the transforms for image masks.
     """
 
     def __call__(self, pic):