Closed zamling closed 2 years ago
Well, I think training without grid alignment may not converge well because frequencies are mixed. But I haven't tried it, so it may work. I think the difference between cv2.dct(Y) and jpegio is because jpegio reads raw DCT coefficients from the JPEG header while cv2.dct(Y) computes it from a decoded image. JPEG decoding, as well as encoding, causes information loss, so the results are different.
I get it !!! Thanks <3
Hi~ I saw there is a param
self._grid_crop
in dataset class, determining a random number wheter it is a integer multiple of 8. Does it have a large influence when I set this param asFalse
.I worry about that when I set this param as
False
, the crop results cannot align with the original DCT blocks (since it seems like the DCT in jpegio is calculated by a 8x8 block. And cropping may break this block and generate a new 8x8 block, which is not the same as the original DCT information from jpegio). btw, I am also stuck in the implementation about DCT calculation in jpegio. It is quite different with the results bycv2.dct(Y)
in Y channel. Can you give me some breif explanations? :) thanks a lot <3