Gwanghyun (Bradley) Kim
Gwanghyun (Bradley) Kim
Hi @sabuj7177, Oh, it's almost the same situation as mine. Unfortunately, I didn't found any solution.. I controlled the hyperparams such as LR, but it didn't work. If you solve...
@SmallFan7 Not yet, I think it's just the limitation of this work.
@Sumching, @qshzh, @IceClear @ariel415el, @Smith42 Guys, how low are your training losses? In my case, the noise prediction losses are several hundred ~ thousands. Is this right?
Does it means that the cases are CXR positive but PCR negative?
Thanks for your reply. I'll be happy if you share the model when training is finished!
@rosinality Thanks a lot!
As I told you by e-mail, I appreciate your findings! I'll fix them and update the arxiv submission and I will ask the chair of CVPR 2022 whether I can...
Good idea! I reopened the issue to let other people know the erratra in our paper. I also update the arXiv paper with the correction and request the chairs of...
Thanks for the great suggestion. Sooner or later, I will try uploading the model.
Great! Those could be great! I will add them to the README. My Hugging Face accout is _gwang-kim_. Thank you for your effort.