search

ashawkey / RAD-NeRF

Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
MIT License
878 stars 153 forks source link

请问什么是emb mode呢？ #31

Open kendo6666 opened 1 year ago

kendo6666 commented 1 year ago

在main.py中，有一个emb模式的参数，请问它的具体功能是什么呢？在什么样的场景下使用呢？谢谢指点

ashawkey commented 1 year ago

@kendo6666 Hi, it's not meant to be used. Basically it means we provide audio features as class labels and learn an embedding per class instead of directly passing in per class logits. As far as I have tested, it generates worse results.