Description
When applying the function on grayscale images, it throws the following error:
packages/torchvision/transforms/functional.py", line 729, in rotate
return img.rotate(angle, resample, expand, center, fillcolor=fill)
File "/home/xxx/local/anaconda3/envs/th/lib/python3.7/site-packages/PIL/Image.py", line 2023, in rotate
return self.transform((w, h), AFFINE, matrix, resample, fillcolor=fillcolor)
File "/home/xxx/local/anaconda3/envs/th/lib/python3.7/site-packages/PIL/Image.py", line 2337, in transform
im = new(self.mode, size, fillcolor)
File "/home/xxx/local/anaconda3/envs/th/lib/python3.7/site-packages/PIL/Image.py", line 2544, in new
return im._new(core.fill(mode, size, color))
TypeError: function takes exactly 1 argument (3 given)
It is related to the pull request #1280