-
Notifications
You must be signed in to change notification settings - Fork 479
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
valPSNR increase very slowly #21
Comments
|
Thanks for your reply And I used adobe240dataset using create_dataset script |
Can you attach the interpolated results from tensorboard? Also specify your setup- CPU/GPU, PyTorch version, OS, etc. 15.5 valPSNR is really low. Maybe there is a problem with dataset or setup. |
#22 |
Right. The two reference (left and right corner) look very different. Frames in a clip look very similar since they are slow motion videos. Will fix the code. |
@avinashpaliwal line 69 in create_dataset.py. |
@avinashpaliwal I have the same problem. I had trained the model to 270 epoch, but the valPSNR keep bellow 15, can you help me ? |
Fixed issues as per suggestions.
Try the new create_dataset script to generate the dataset and try training again. The model starts converging right from the beginning. |
Nice work thanks!
I have a question about convergence speed
I've run your training code and almost passed 50 epoch. The valPSNR is still under 15.5.
Is that normal?
also created clips seems to be not sequencial is that ok?
The text was updated successfully, but these errors were encountered: