Evaluation on official trained model

[wb-finalking]

Hello, thanks a lot for opening your source code. Now I am reimplementing your work. But the metrics from the trained model are not the same as the papers. Could you support the detailed document about how to do evaluation.

[SenHe]

Hello, thanks a lot for opening your source code. Now I am reimplementing your work. But the metrics from the trained model are not the same as the papers. Could you support the detailed document about how to do evaluation.

Please refer to this issue

[wb-finalking]

Thanks a lot! I want to know when you can supplement the instruction for evaluation. And did you check whether the pretrained models are the same as your paper's?