search

li-plus / DSNet

DSNet: A Flexible Detect-to-Summarize Network for Video Summarization
https://ieeexplore.ieee.org/document/9275314
MIT License
209 stars 50 forks source link

OVP dataset and YouTube dataset not in the same format as TVSum dataset #28

Open Jiangllu opened 1 year ago

Jiangllu commented 1 year ago

When I was reproducing your code, I found that the OVP dataset and YouTube dataset are not in the same format as the TVSum dataset and Summe, missing 'change_points', 'n_frames', 'picks', etc., which prevents the model from completing the transfer. and Augmented settings, how should it be solved?

Mirli1234 commented 1 year ago

When I was reproducing your code, I found that the OVP dataset and YouTube dataset are not in the same format as the TVSum dataset and Summe, missing 'change_points', 'n_frames', 'picks', etc., which prevents the model from completing the transfer. and Augmented settings, how should it be solved?

There may be two possible reasons for this problem. Firstly, you did not download the associated datasets from the author README.md for training. Secondly, you did not run make_ shots. py program performs shot segmentation.

Mirli1234 commented 1 year ago

When I was reproducing your code, I found that the OVP dataset and YouTube dataset are not in the same format as the TVSum dataset and Summe, missing 'change_points', 'n_frames', 'picks', etc., which prevents the model from completing the transfer. and Augmented settings, how should it be solved?

There may be two possible reasons for this problem. Firstly, you did not download the associated datasets from the author README.md for training. Secondly, you did not run make_ shots. py program performs shot segmentation.