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

66 votes407 views6 answers
Python virtual environment
Python
0 vote319 views1 answer
How to convert into grayscale opencv
Python
23 votes374 views2 answers
Python search list
Python
0 vote329 views2 answers
Python get function from string name
Python
7 votes346 views2 answers
Calculate the addition of two lists in python
Python
0 vote335 views1 answer
Numpy prod
Python
0 vote326 views1 answer
Python add columns to dataframe without changing the original
Python
6 votes325 views3 answers
Py -m pip
Python
0 vote358 views1 answer
Open file find and replace commas python
Python
5 votes376 views6 answers
Dict comprehension python
Python