facebookresearch / AudioMAE

This repo hosts the code and models of "Masked Autoencoders that Listen".
Other
547 stars 45 forks source link

Cannot reproduce finetuning result on Audioset-20k #23

Open kxgong opened 1 year ago

kxgong commented 1 year ago

Thanks for the great work.

When I reproduce the finetuning result on Audioset-20k, the best I can get is 35.4 while the reported result is 37.0.

I use the example script in this repo.

In addition, I vary the value of the learning rate from [-1e-4, -1e-2] and the value of batch size from [4, 64], the best result remains 35.4.

Could you provide some ideas to have better results?