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 vote361 views1 answer
How to save inputs python
Python
0 vote286 views2 answers
Tkinter disable resize
Python
2 votes333 views2 answers
Combination without repetition python
Python
0 vote342 views1 answer
Python input for competitive programming
Python
0 vote401 views1 answer
Join a list of items with different types as string in Python
Python
1 vote364 views1 answer
R2 score sklearn
Python
0 vote325 views1 answer
Python message from teams
Python
0 vote324 views1 answer
Create new column with mask pandas
Python
7 votes327 views3 answers
Concat dataframes
Python
1 vote316 views1 answer
Return json with flask
Python