Mohan Sai Singamsetti

icon indicating a website link https://mohansai23.github.io/

icon company University of Alberta icon location Edmonton icon location MSc in CS, University of Alberta

Results 4 comments of Mohan Sai Singamsetti

Training code for the Adversarial Diffusion Distillation(ADD) not available?

@jon-chuang , thanks for your feedback, I tired to implement a similar training mechanism as what ADD is doing, but it seem to having have a lot of instability in...

Training code for the Adversarial Diffusion Distillation(ADD) not available?

@fingerk28 I was getting a similar image which becomes complete noise, with longer training, which probably could be due to instability in the training, I still face the issue of...

Training code for the Adversarial Diffusion Distillation(ADD) not available?

Hi @jon-chuang, thanks for your answers, I have already tried including the R1 gradient penality, but still couldn't get rid of the "nan" in the gradient norm for the discriminator....

GMACs doesn't match with the paper.

Thank you for your response! Could you please confirm the following setting for SIDD dataset. KBNet_s: width = 32 ffn_scale = 1.5 lightweight= True -> This setting has 57.8 GMACs...