Fix potential overflow in convert_image_dtype (pytorch#3107)

We could have errors such as aten/src/ATen/native/cpu/PowKernel.cpp:41:5:  runtime error: 5.7896e+76 is outside the range of representable values of type 'float'

torchvision/transforms/functional_tensor.py

@@ -105,14 +105,15 @@ def convert_image_dtype(image: torch.Tensor, dtype: torch.dtype = torch.float) -
         return result.to(dtype)
     else:
         input_max = _max_value(image.dtype)
-        output_max = _max_value(dtype)
 
         # int to float
         # TODO: replace with dtype.is_floating_point when torchscript supports it
         if torch.tensor(0, dtype=dtype).is_floating_point():
             image = image.to(dtype)
             return image / input_max
 
+        output_max = _max_value(dtype)
+
         # int to int
         if input_max > output_max:
             # factor should be forced to int for torch jit script