syncnet_trainer icon indicating copy to clipboard operation
syncnet_trainer copied to clipboard

Published 20 hours ago • verified publisher icon joonson

Choice of loss function used

Open Mayur28 opened this issue 3 years ago • 0 comments

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

Mayur28 avatar Aug 30 '21 10:08 Mayur28