Why using BCELoss? That is for binary classification while we have 20 classes

pochih / FCN-pytorch

🚘 Easiest Fully Convolutional Networks

404 stars 143 forks source link

Open lucasjinreal opened 5 years ago

lucasjinreal commented 5 years ago

I think multi class can not using BCELoss here, why are u using that?

pochih commented 5 years ago

The output and the target are both construct with 0 and 1 value. So it's trainable with BCELoss.