Closed
Description
❓ Questions and Help
Windows 10:
CUDA version :10.1
torchvision.version is 0.7.0
python: 3.7
The docs on the website: torchvision.transforms.functional.resize() and torchvision.transforms.functional.crop() are written that the two functions support both PIL and tensor as inputs.
But when I use the two functions on Windows, I found that it still only support PIL as inputs. I'd like to use tensor as inputs. Some of the source code in functional.py is:
def resize(img, size, interpolation=Image.BILINEAR):
r"""Resize the input PIL Image to the given size.
Args:
img (PIL Image): Image to be resized.
size (sequence or int): Desired output size. If size is a sequence like
(h, w), the output size will be matched to this. If size is an int,
the smaller edge of the image will be matched to this number maintaining
the aspect ratio. i.e, if height > width, then image will be rescaled to
:math:`\left(\text{size} \times \frac{\text{height}}{\text{width}}, \text{size}\right)`
interpolation (int, optional): Desired interpolation. Default is
``PIL.Image.BILINEAR``
Returns:
PIL Image: Resized image.
"""
if not _is_pil_image(img):
raise TypeError('img should be PIL Image. Got {}'.format(type(img)))
if not (isinstance(size, int) or (isinstance(size, Iterable) and len(size) == 2)):
raise TypeError('Got inappropriate size arg: {}'.format(size))
if isinstance(size, int):
w, h = img.size
if (w <= h and w == size) or (h <= w and h == size):
return img
if w < h:
ow = size
oh = int(size * h / w)
return img.resize((ow, oh), interpolation)
else:
oh = size
ow = int(size * w / h)
return img.resize((ow, oh), interpolation)
else:
return img.resize(size[::-1], interpolation)