Pytorch pad to square

import torchvision.transforms.functional as F

class SquarePad:
    def __call__(self, image):
        max_wh = max(image.size)
        p_left, p_top = [(max_wh - s) // 2 for s in image.size]
        p_right, p_bottom = [max_wh - (s+pad) for s, pad in zip(image.size, [p_left, p_top])]
        padding = (p_left, p_top, p_right, p_bottom)
        return F.pad(image, padding, 0, 'constant')

target_image_size = (224, 224)  # as an example
# now use it as the replacement of transforms.Pad class
transform=transforms.Compose([
    SquarePad(),
    transforms.Resize(target_image_size),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
])

Source: discuss.pytorch.org

Similar codes

4 votes140 views3 answers
Python indexing
Python
1 vote178 views1 answer
Managin media django
Python Django
0 vote150 views1 answer
Fforeveer loop python
Python
3 votes193 views6 answers
Get multiple inputs in python
Python
0 vote151 views1 answer
Python import stringIO
Python
0 vote140 views1 answer
Recursive Folder scan
Python
4 votes144 views3 answers
Dice simulator python
Python
12 votes144 views2 answers
Python sorted function descending
Python
1 vote146 views1 answer
Pandas get rows with missing data
Python
0 vote155 views1 answer
Pandas dataframe select last n columns
Python