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 vote143 views1 answer
Seaborn plot to see outliers
Python
148 votes257 views10 answers
Grepper
Python
0 vote145 views1 answer
Replit python keep discord bot online
Python
0 vote138 views1 answer
Gtk entry focus python
Python
0 vote143 views1 answer
How to instal django cities
Python
-1 vote143 views1 answer
Starry spheres
Python
0 vote119 views2 answers
Remove columns that contain string pandas
Python
0 vote137 views1 answer
Task orchestration framework
Python
0 vote138 views1 answer
Discord bot response to private message python
Python
-1 vote133 views1 answer
Matplotlib limit number of ticks
Python