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

55 votes254 views4 answers
List len python
Python
6 votes258 views5 answers
How to count unique values in a column dataframe in python
Python
1 vote224 views1 answer
Order by listview django
Python Django
0 vote253 views1 answer
Sklean tfidf
Python
68 votes226 views6 answers
Python dict sort by value
Python
0 vote245 views1 answer
Module not found after sucessful install
Python
0 vote225 views1 answer
Pip ne marche pas
Python
2 votes220 views1 answer
Os.getlogin() python
Python
1 vote240 views1 answer
Flask render error template
Python Flask
0 vote230 views2 answers
Removing rows dataframe not in another dataframe using two columns
Python