-
Notifications
You must be signed in to change notification settings - Fork 22
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
"Train Sketch Autocomplete Models" not working #5
Comments
I have the same problem. I'm training with the Scribble Dataset. The loss of G_L1 is always 0.00. Fake_B (view in visdom) are first just the input with a gray backgroud, then just blank or something meaningless while G_GAN, D_real and D_fake getting toooooo large. I've tried different batch_size and lr_G/D. Could you please check? Thank you and sorry for my English. |
sketchy.log |
|
Hello, I followed the scripts to train the autocomplete model on Sketch Emojis dataset, but the model does not converge, and just provide some meaningless results.
Could you please check whether the settings in the scripts are correct, thank you.
The text was updated successfully, but these errors were encountered: