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 vote223 views1 answer
Pandas select data by column value
Python
5 votes280 views2 answers
Forgot django admin password
Python
96 votes279 views6 answers
Read json file
Python
1 vote283 views5 answers
Delete csr python
Python
28 votes219 views2 answers
Np zeroes
Python
9 votes271 views2 answers
How to create a new virtualenv
Python
0 vote279 views1 answer
Funzione generatore python
Python
5 votes275 views1 answer
Input command in python shell
Python
1 vote312 views2 answers
.save() in django
Python Django
1 vote253 views1 answer
Django wait for database
Python