SEGAN icon indicating copy to clipboard operation
SEGAN copied to clipboard

verified publisher icon leftthomas
→

Metadata

A PyTorch implementation of SEGAN based on INTERSPEECH 2017 paper "SEGAN: Speech Enhancement Generative Adversarial Network"

Results 2 SEGAN issues
Sort by recently updated
recently updated
newest added

fix/pytorch

- fixing for Pytorch 1.3.0 >=

dendisuhubdy avatar dendisuhubdy

Shouldn't ref_batch be inside the loop?

Currently, the `ref_batch` is sampled only once before the training loop starts [as here in line 32](https://github.com/leftthomas/SEGAN/blob/master/main.py#L32). Shouldn't it be randomly sampled for each batch? I am guessing it based...

keunwoochoi avatar keunwoochoi

← Metadata

129
Stars
42
Forks
Watchers

Owner

verified publisher icon leftthomas

Metadata

A PyTorch implementation of SEGAN based on INTERSPEECH 2017 paper "SEGAN: Speech Enhancement Generative Adversarial Network"

Back