search

joonson / syncnet_trainer

Disentangled Speech Embeddings using Cross-Modal Self-Supervision
MIT License
155 stars 26 forks source link

Choice of loss function used #17

Open Mayur28 opened 3 years ago

Mayur28 commented 3 years ago

Hi,

I am looking through this repo and I am confused about the choice of loss function used. I am using SyncNet to measure lip-sync error and considering that this may be considered a binary classification problem, I am confused as to why the CrossEntropyLoss is used as opposed to the Binary Cross Entropy Loss.

Any clarification would be highly appreciated. Thanks