Open umbertov opened 2 years ago
There is no unique solution, the two settings can give rise to similar results.
Ok, thanks for the reply!
Just for the sake of curiosity though, did you keep a record of the exact settings you trained with to reach the scores/obtain the checkpoints you provided? I assumed they would be the train_bsrgan_x4_{psnr,gan}.json
ones but i wasn't so sure after double checking with the article.
Hi, I was checking training details on the BSRGAN paper, and comparing them to
options/train_bsrgan_x4_gan.json
, I found a few differences which might be important for reproduction and research. I'm working with BSRGAN due to my master thesis project.I refer to the end of section 5, at page 6, second column:
Here i notice two discrepancies:
netD.net_type
isdiscriminator_unet
, rather than the paper'sdiscriminator_patchgan
D_lossfn_weight
is 1 instead of 0.1 as mentioned in the paperThen, the next sentence is:
But looking at the definition of
F
(the feature network used for perceptual loss), I would expect thatF_feature_layer
contains the index of a single layer. Instead I find 5 indices[2,7,16,25,34]
.My question is which one's correct? The info on the paper or the one of the JSON files? It could have gone both ways: reporting correct values on the paper then uploading wrong/old version of the JSON file, or reporting old/wrong data on the paper while having uploaded the correct JSON file to this repo.
@cszn Since you're among the authors of the paper, could you shed some light on this?