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

12 votes240 views3 answers
Matplotlib legend
Python
0 vote218 views1 answer
How to define a functio in python
Python
3 votes243 views1 answer
Matplotlib text too small
Python
0 vote215 views1 answer
Subset data frame by date
Python
1 vote235 views3 answers
Django reverse
Python
7 votes216 views5 answers
Install discord python
Python
38 votes238 views2 answers
Delay time python
Python
5 votes219 views2 answers
Who created python
Python
0 vote218 views4 answers
Pandas filter
Python
1 vote232 views2 answers
Python delete key if exists
Python