Thanks for the great work! Regarding the question, I did try to change the frame r

Did you try to change <a href="https://github.com/antoine77340/video_feature_extractor

Can I extract 3D features per frame? about video_feature_extractor HOT 2 OPEN

antoine77340 commented on July 23, 2024

Can I extract 3D features per frame?

from video_feature_extractor.

Comments (2)

antoine77340 commented on July 23, 2024

Did you try to change https://github.com/antoine77340/video_feature_extractor/blob/master/extract.py#L34
and replace 24 by another frame per second value?

from video_feature_extractor.

Namzakku commented on July 23, 2024

Thanks for the response!
Yes, I tried to change the frame per second value. But the thing is that I found the dimensions of the output seems smaller than what I expected for frame extraction.
After reading again your paper and the instructions, I found that

The 3D model is a ResNexT-101 16 frames (https://github.com/kenshohara/3D-ResNets-PyTorch) pretrained on Kinetics. The 3D features are extracted at 1.5 feature per second at the resolution of 112.

So as far as I understand, it might be because of using the ResNexT-101 16 frames model that you have to adjust the shape in here?
https://github.com/antoine77340/video_feature_extractor/blob/master/preprocessing.py#L35

from video_feature_extractor.

Recommend Projects