yusanshi / news-recommendation

Implementations of some methods in news recommendation.
MIT License
241 stars 50 forks source link

True Label Question #43

Closed laowangzi closed 2 years ago

laowangzi commented 2 years ago

Hi, Excellent work. However, I have a question. In the train section of train.py, your code isy = torch.zeros(len(y_pred)).long().to(device). The true label I think is 1 + 0*K, rather than 0 * (K + 1).