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 views5 answers
Pattern
Python
76 votes345 views6 answers
Python file open
Python
0 vote298 views1 answer
Create requirements file and load it in new envirnment.
Python
0 vote317 views1 answer
Pathlib check is file
Python
0 vote313 views1 answer
Python test mock class method
Python
2 votes319 views2 answers
How to check if number is negative in python
Python
2 votes300 views2 answers
Forrest Gump
Python
1 vote317 views1 answer
Time it in jupyter notebook
Python
6 votes341 views1 answer
Change dataframe value by index
Python
0 vote313 views1 answer
Django model make the field caseinsensitive
Python