search

vsitzmann / siren

Official implementation of "Implicit Neural Representations with Periodic Activation Functions"
MIT License
1.72k stars 247 forks source link

[Inconsistency with paper] I reproduced audio signal by RELU + MLP. #50

Open sh-lee-prml opened 2 years ago

sh-lee-prml commented 2 years ago

To compare SIREN layer with RELU +MLP, we implement two models.

  1. audio signal (B, T, 1) --> Linear(B, T, 128) +RELU --> Linear(B, T, 128) +RELU --> Linear(B, T, 128) +RELU --> Linear(B, T, 1) --> reproduced signal (B, T, 1)

  2. audio signal (B, T, 1) -->SIREN layer --> SIREN layer -->SIREN layer --> Linear(B, T, 1) --> reproduced signal (B, T, 1)

In your paper, RELU+MLP is not able to reproduce the audio signal, However, First model can reproduce audio signal even better than SIREN...

SIREN is also very instability so i used lower learning rate. But the loss fluctuated.

Could you explain why the siren is better than others in audio reproduction domain?

1999kevin commented 2 years ago

Hi, I also doubt about this. Do you figure why this happen now?