QingyangZhang/QMF

复现时发现代码不完整

Closed this issue · 2 comments

wenpeiyu123 commented

作者你好，在使用你们的代码时发现models里没有QMF的代码，以及缺少pytorch_pretrained_bert文件，请问这些缺少部分需要如何获取呢，感谢！

QingyangZhang commented

Sorry for the confusion. The only difference between QMF and late fusion lies in the dynamic fusion weights. Therefore, QMF (as implemented in train_df.py and eval_df.py) simply uses late_fusion.py from the 'models' directory. We will update the code to avoid any confusion and will upload the pretrained model as soon as possible.

  • 👍1
Xinghetayue commented

Sorry for the confusion. The only difference between QMF and late fusion lies in the dynamic fusion weights. Therefore, QMF (as implemented in train_df.py and eval_df.py) simply uses late_fusion.py from the 'models' directory. We will update the code to avoid any confusion and will upload the pretrained model as soon as possible.

waitting for it