vsumm-reinforce icon indicating copy to clipboard operation
vsumm-reinforce copied to clipboard

Published 20 hours ago • verified publisher icon KaiyangZhou

How to construct a dataset without label

Open HrsPythonix opened this issue 6 years ago • 3 comments

I got a question, if I want to use my own dataset, but there is no label in the dataset, when I construct the hdf5 file, what should I do with user_summary, gts_score and gtsummary?

Also I see these three labels only used in evaluation process, does this means that I can just delete them both in hdf5 and the evaluation function? (I mean in the pytorch implementation)

Moreover, if I want to use the result.json to generate a summarization video for a raw video, can I delete these three labels?

Originally posted by @HrsPythonix in https://github.com/KaiyangZhou/vsumm-reinforce/issues/1#issuecomment-423401299

HrsPythonix avatar Sep 25 '18 04:09 HrsPythonix

Hey.. Did you work out on user_summary? i am stuck with same

Swati640 avatar Sep 13 '19 15:09 Swati640

Hey... Did you work out on user_summary? I am stuck with the same

Could u please guide me to create a dataset for my own video I don't know how to create a dataset?

anbuharry avatar May 06 '21 09:05 anbuharry

Hey... Did you work out on user_summary? I am stuck with the same

Could u please guide me to create a dataset for my own video I don't know how to create a dataset?

You can check my github profile. I recreated the code on UCF - 101 dataset. The docker image is available

Swati640 avatar May 06 '21 10:05 Swati640