Yaping Zhu

When training the tvsum dataset, the range of index in the data_loader.py file always exceeds the number of datasets, and there is a problem with the code.

our test code does not get the accuracy rate and the recall rate.

Will you improve the test code? Such as visualization, generating video, and getting accurate f-scores

Do you have WeChat or email? Some questions want to ask you。

Thank you, because my research direction is this, I have been thinking about doing this in the near future. If you can send the test code to me, thank you...