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

1 vote114 views1 answer
Module not found not module name channels in python
Python
0 vote137 views1 answer
Picture as background of seaborn plot python
Python
-1 vote111 views1 answer
Len
Python
5 votes120 views4 answers
Django get or 404
Python
184 votes204 views6 answers
How to upgrade pip
Python
0 vote114 views3 answers
Selenium python login instagram
Python
2 votes112 views2 answers
Random.randint(0,20) + pyrthon
Python
0 vote123 views1 answer
Ms access python dataframe
Python
12 votes135 views4 answers
Pytesseract.pytesseract.TesseractError: (2, 'Usage: pytesseract [-l lang] input_file')
Python
0 vote108 views1 answer
Reducing noise on Data
Python