These results are different from those with cv2.dft

[lilu1996]

input image "im_gray" of uint8 and size of [256,256], then i made following operations with opencv and torch-dct, respectively:
a = cv2.dct(im_gray.astype("float"))
b = torch_dct.dct_2d(torch.from_numpy(im_gray.astype("float"))).
But a and b are greatly different.

[DYin65535]

Are you sure you used the same norm method as in cv2? Try this:

a = cv2.dct(im_gray.astype("float"))
b = torch_dct.dct_2d(torch.from_numpy(im_gray.astype("float")), norm='ortho')

I suppose both cv2 and MatLab use the orthogonal factor as default.