Skip to content
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

why the content_loss and adversarial_loss keep increasing with the training? #70

Open
3889187 opened this issue Mar 29, 2020 · 2 comments

Comments

@3889187
Copy link

3889187 commented Mar 29, 2020

No description provided.

@ghost
Copy link

ghost commented Apr 6, 2020

I have the same issue. While training (no matter MSE loss or Perceptual loss) the loss of generator keep increasing. Any idea of that issue? Can it be causing from learning rate?

@3889187
Copy link
Author

3889187 commented Apr 7, 2020

I have the same issue. While training (no matter MSE loss or Perceptual loss) the loss of generator keep increasing. Any idea of that issue? Can it be causing from learning rate?

i found it may cause by the epoch,if u train enough epochs,the loss will descrease.There is my loss with 20099 epoch

progress epoch 20099 step 1 image/sec 47.1 remaining 5549m
global_step 20099
PSNR 10.362125
discrim_loss 1.1745936e-36
adversarial_loss 27.630926
content_loss 0.101071864
learning_rate 9.115951e-05

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant