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

0 vote353 views1 answer
Slug in redirect django
Python Django
1 vote339 views2 answers
How to print values without space in python
Python
106 votes356 views5 answers
Sorting by column in pandas
Python
4 votes398 views4 answers
Convert image to grayscale opencv
Python
0 vote336 views1 answer
Webdriver.chrome() python not working
Python
57 votes350 views4 answers
Get date and time in python
Python
0 vote332 views1 answer
Django 3.2 compatible to python 3.10?
Python
0 vote360 views1 answer
How to check how many cameras are connected to device in python\
Python
0 vote339 views1 answer
Change to first letter capital list python
Python
-1 vote330 views1 answer
Converting jupyter notebook files to python
Python