dg618k

Loss divergency in S2_adv

2

Dear friend! During the training for S2_adv, the gen_loss and disc_loss are divergency by Wasserstein distance. However, it is fine with cross_entropy loss referenced by the adda project. Can you...

make error

3

Hi @wywu I'm really interesting about your method and great result represented in your paper. I'd like to reproduce your code, but I get errors when make it. What I...

Test Problem

1

What's your test method to get the good results? In the code of provided, gallery set isn't used, as I know, the result on probe set only cannot represent Heterogeneous...

Calculate AUC error

2

The pred_hard_encodings size dismatch with preds_scores when faiss indice has -1. so I retrieve preds_scores first len(pred_hard_encoding) to make it correct. Does it introduce any other problems? Thank you.

Is there any policy model trained o crossmoz? Thank you!

[Feature]根据不同条件场景生成不同问答

1

对于同一个问题，不同的条件可能有着不同的答案，此时我希望能够生成条件-问题-答案的数据格式。