-
Notifications
You must be signed in to change notification settings - Fork 19
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
Multi instance #1
base: master
Are you sure you want to change the base?
Conversation
Using a TimeDistributed layer Right now augmentations are disabled
Should reduce IO bottleneck by a factor of n_windows (typ 6x) Also got rid of warnings for 0 length windows, by taking into account that augmentation may change length
@@ -18,7 +18,6 @@ https://community.st.com/s/topic/0TO0X0000003iUqWAI/stm32-machine-learning-ai | |||
Experiment | |||
|
|||
- Test 16kHz with 30 mels | |||
- Use multi-instance learning. Get bigger batches and improve GPU utilization |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Did you forget XXX?
Currently this does not perform better than independent instances. It may be that using mean as the pooling operator is not ideal, especially for classes which take a short time (gunshot, bark), or are mostly occluded (children playing in background). |
No description provided.