小编Lot*_*you的帖子

我想知道我是否可以在Pytorch中构建一个图像大小调整模块,它将3*H*W的torch.tensor作为输入并返回张量作为调整大小的图像.

我知道可以将张量转换为PIL图像并使用torchvision,但我也希望将调整后的图像中的渐变传播回原始图像,以下示例将返回此类错误(在Windows 10上的PyTorch 0.4.0中) :

import numpy as np
from torchvision import transforms

t2i = transforms.ToPILImage()
i2t = transforms.ToTensor()

trans = transforms.Compose(
    t2i, transforms.Resize(size=200), i2t]
)

test = np.random.normal(size=[3, 300, 300])
test = torch.tensor(test, requires_grad=True)
resized = trans(test)
resized.backward()

print(test.grad)

Traceback (most recent call last):
  File "D:/Projects/Python/PyTorch/test.py", line 41, in <module>
    main()
  File "D:/Projects/Python/PyTorch/test.py", line 33, in main
    resized = trans(test)
  File "D:\Anaconda3\envs\pytorch\lib\site-packages\torchvision\transforms\transforms.py", line 42, in __call__
    img = t(img)
  File "D:\Anaconda3\envs\pytorch\lib\site-packages\torchvision\transforms\transforms.py", line 103, in __call__
    return F.to_pil_image(pic, self.mode)
  File …