Skip to content
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

a pre-trained youtube model #9

Open
superhg2012 opened this issue Apr 24, 2018 · 3 comments
Open

a pre-trained youtube model #9

superhg2012 opened this issue Apr 24, 2018 · 3 comments

Comments

@superhg2012
Copy link

hi, could you share a well pre_trained youtube8m-model? The existing you provided in your project youtube_model.ckpt.data-00000-of-00001 is not very accurate when run the demo server.

@igor-panteleev
Copy link
Contributor

Hi,
Unfortunately this is the best model checkpoint that i have for now.
It tuned out that models from youtube-8m are not very suitable for audio classification.
I have plans to try some sort of RNN model. It should be much better.
Until then, You can try it yourself.

@superhg2012
Copy link
Author

thanks for reply! One more question, how can I get my own pca matrix instead of the one in your project?

@igor-panteleev
Copy link
Contributor

igor-panteleev commented May 10, 2018

This matrix is a part of vggish and i didn't try another one. Code that read matrix from file. Hope it will help.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants