google-deepmind/kinetics-i3d

extract features

Serendipity-LC opened this issue · 5 comments

Serendipity-LC commented

Hi！How to use I3D to extract features from other datasets? If n represents the frames of a video, How can I extract features of size n*1024 with rgb_videos as the input?

Nandini2801 commented

Hi @chenjiakun I also had similar ques. Have you got any progress for the above problem?

  • 👍1
Tortoise17 commented

@Nandini2801 This is pytorch version Kinetics-PyTorch which is working. But still I need to know how to extract features from second last layer.

Nandini2801 commented

@Tortoise17 how to make this code to extract features from other datasets rather than kinetic?

Tortoise17 commented

Sorry, now in above repl is the code.

Nandini2801 commented

Thanks for the reply