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 vote240 views1 answer
What modules are used for NLG in python
Python
0 vote264 views1 answer
Python diferente de
Python
0 vote239 views1 answer
Mat.at(row,col) Opencv
Python
0 vote235 views1 answer
Flask stream with data/context
Python
0 vote278 views1 answer
Get all methods of an instance
Python
0 vote254 views1 answer
Remove empty string from list python single line
Python
0 vote251 views1 answer
Full body tracking module
Python
0 vote262 views1 answer
How to use drf pagination directly
Python
0 vote241 views1 answer
Find position of key in dictionary python
Python
1 vote270 views1 answer
Creating folder in s3 bucket python
Python