-
Notifications
You must be signed in to change notification settings - Fork 14
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
training errors #1
Comments
I also has this problem, and the optimization is very slow. Do you have this problem? |
@JACKYLUO1991 Do you solve this problem? |
@lingtengqiu I replaced ID-MRF with L2 loss, which currently works but not very well. |
@JACKYLUO1991 another question. I find the optimization of hybrid stage is very very slow. Do you also confront this problem? In my setting, It spents 20 mins in 200 steps. You said it dose not work very well~ (It means the results or the training time? ). By the way, can I get your email or wechat, which can help us discuss it more conveniently. |
When starting to train the hybrid model, the loss function appears to be anomalous and the images show all black images.
It seems to be caused by the ID-MRF loss function.
The text was updated successfully, but these errors were encountered: