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 vote105 views1 answer
Using Lists as Queues
Python
4 votes101 views1 answer
How to add condition if null value in django orm
Python
1 vote95 views1 answer
Python close all plot figures
Python
0 vote106 views1 answer
How to convert into grayscale opencv
Python
9 votes116 views2 answers
Python check if number is in range
Python
0 vote99 views2 answers
Find index of null values pandas
Python
7 votes102 views2 answers
What is numpy
Python
0 vote96 views1 answer
Convert utm to decimal degrees python
Python
1 vote89 views1 answer
Django.db.models avg
Python
0 vote147 views1 answer
Sum of values with none
Python