Train GCN issue - Githubissues

TianBian95 / BiGCN

Source Codes: Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks--AAAI 2020

250 stars 73 forks source link

Train GCN issue #25

Open Xzk233233 opened 3 months ago

Xzk233233 commented 3 months ago

In the Train_GCN function, model.eval() is called inside the loop to set the model to evaluation mode. Should model.train() also be called inside the loop to ensure the model is set back to training mode?