-
Notifications
You must be signed in to change notification settings - Fork 8
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
FPN logit #3
Comments
I fixed the above problem |
Hi @Zzang-yeah, thank you for your interest in our repo. |
When learning with multi-GPU, the online learning didn't seem to work well because the order between processes was messed up. I have one question: I understand that in online learning, the teacher model is augmented and saved logit for every iteration to KD train the student model, and in offline learning, the student model is KD trained by running Teacher_Inference.py with the teacher model and running augmentation and save logit only once. |
Thank you for raising this concern; I thought it would have been obvious, but maybe not. |
When comparing nano models trained with KD to nano models trained without, we found that the performance was not significantly better. Does the fact that the model with KD performed better mean that the FP was improved? In my experiments, the AP was higher for the nano model without KD than for the model with KD. |
I encountered the same issue when using a single GPU. I tried the method you provided, but I still get an error saying the npy file was not found. May I take a look at your modified code? |
我已经解决了 |
大佬,怎么解决的? |
When and where is the FPN logit stored?
Whether online or offline, tools/demo.py just runs and generates an image, but no npy file is created, so I can't proceed with student learning.
The text was updated successfully, but these errors were encountered: