Cynwell / Text-Level-GNN

Text Level Graph Neural Network for Text Classification
Apache License 2.0
46 stars 13 forks source link

why choose BCELoss? #6

Open HZD0014 opened 2 years ago

HZD0014 commented 2 years ago

As far as I know, BCE is customarily used for binary classification problems. Wouldn't it be better to use CrossEntropyLoss