-
Notifications
You must be signed in to change notification settings - Fork 39
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
NAN in training process #7
Comments
You can lower the learning rate of the threshold encoder in
Thanks for your attention! |
adjust the learning rate does works! Thanks for your reply. |
Hi taohan@taohan10200 , after lowing the learning rate, NAN still appeared after 87 iterations. I saved the model and weights every 20 iterations, and felt amazed that based on 80th model, the model can be trained normally without NAN. Do you have any good suggestions? By the way, there is no read_pred_and_gt module in misc.utils.py, causes vis4val.py cannot work properly, would you please commit this part codes?Thanks。 |
In our training, NaN would appear even if we lowered the threshold some times. At this time, we usually lower the threshold again to avoid this problem. We recommend using the experimental configuration we provide under folder We have updated the read_pred_and_gt module in Thanks~ |
where is the path of the save model? |
Hi, when I training the network of NWPU dataset, the results indicates NAN in all following cases. I set the training batch size to 6 for preventing out of memory.
The text was updated successfully, but these errors were encountered: