This code is a shameless hack from the might work at OpenAI and their Video PreTraining (VPT) project.
To generate .jsonl files from video, place the IDM model and weights in the same folder as this readme.
then run: python IDM_Video.py --video-path=video.mp4
This is standing on the shoulders of a large effort by a dedicated team at OpenAI: Bowen Baker, Ilge Akkaya, Peter Zhokhov, Joost Huizinga, Jie Tang, Adrien Ecoffet, Brandon Houghton, Raul Sampedro, Jeff Clune The code here is a dirty dirty hack of the superb work of Anssi Kanervisto