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

24 votes334 views10 answers
Python timer
Python
1 vote192 views1 answer
How to generate random normal number in python
Python
0 vote179 views1 answer
Try open file
Python
0 vote174 views3 answers
Mechanize python fill
Python
1 vote170 views1 answer
Make python look good
Python
1 vote199 views1 answer
Python file.write is not writing whole line
Python
0 vote197 views1 answer
Pandas fill missing index values
Python
0 vote233 views1 answer
Django request.data example
Python Django
8 votes194 views2 answers
Python float print 2 digits
Python
0 vote202 views1 answer
With torch.no_grad() if condition
Python