chaoyuaw / pytorch-coviar

Compressed Video Action Recognition
https://www.cs.utexas.edu/~cywu/projects/coviar/
GNU Lesser General Public License v2.1
500 stars 126 forks source link

Using dataloader in order to extract and save MVs & Residual #54

Closed Esaada closed 5 years ago

Esaada commented 5 years ago

Hi Guys, I want to use your data loader in a bit different way, I want to run on all the videos in my dataset, so that for each video will have saved MVs and Residuals. I thought about just calling the load method multiple times something like: {for Motion Vectors} for my_gop_index in range(): for frame_index in range(): load(video_name, my_gop_index, frame_index, 1, True)

I know that the code is missing, but do you think it will work, or I'm missing something?

Thanks!