DRJYYDS

> hi, [pretrain_coglm.py](https://github.com/THUDM/CogView2/blob/main/pretrain_coglm.py) is the pretraining code (first-stage). The code for the second stage is a bit messy and not very useful for finetuning, so I didn't push them. The...

> Thanks for your reply! > But the perceptual loss can be extremely huge(i.e >1e5) and ms-ssim seems in range [0,1], did you observe MS-SSIM really work when directly sum...

> There are multiple issues with the figures here - thank you for the report! Your're welcome. The ar5iv project is such a impressive work, very appreciate it!

> FYI, I got a fid of 20 using @junhsss 's code; > > I also calculated with https://github.com/mseitzer/pytorch-fid using the same 10k generated images (calculated with the whole cifar10...

> Hi @DRJYYDS , > > sorry for the confusion. > > In @junhsss 's implementation, the ground truth folder has 10k images, but the 56 fid was calculated using...

> > Thanks for your reply! > > I believe that you now have the correct FID. By the way, FID is calculated between 50k generated images and 50k real...

> Hi, guys, I would like to ask the number of iterations you adopt when you calculate FID. Is the high FID possibly due to the insufficient training? Sure. According...