Inference does not work correctly

[darkasevgen]

Hi @LeslieZhoa, thanks for your implementation.
I tried running the inference.py script and I faced some problems.

I fixed the 'netG' key in the line:

DCT-NET.Pytorch/inference.py

Line 25 in ebdc7bd

self.net.load_state_dict(ckpt['netG'],strict=False)

to 'G' because final.pth does not contain 'netG'.

Also in the postprocess method you make the slice [..., ::-1], and you also make it after calling the run method:

DCT-NET.Pytorch/inference.py

Line 55 in ebdc7bd

oup = model.run(img)[...,::-1]

I removed the extra slice.
But I still get an unrealistic image (ran at 1024 and 256 resolutions). I'm attaching an example (first line is 1024, second line is 256) and waiting for a response/comment.

[LeslieZhoa]

Hi @darkasevgen ! Thanks for your question. I fix the slice bug and upload a new model. You can try again!

[darkasevgen]

Can you tell me more about how gif is received ?
Did you apply resize to a certain resolution and run the model? Or can the inference be done at any resolution?

[LeslieZhoa]

Hi @darkasevgen , the gif is generated with the whole image size. just like

img = cv2.imread('')
img_h,img_w,_ = img.shape 
n_h,n_w = img_h // 8 * 8,img_w // 8 * 8
img = cv2.resize(img,(n_w,n_h))

the model can run at any resolution which can be divided with no remainder.
but the result will be slightly worse.

[darkasevgen]

Thank you for your reply.