Closed nguyenquyem99dt closed 1 year ago
Hi @nguyenquyem99dt, Thanks for your appreciation. The model is only trained with data <=150s, there is no performance guarantee for videos longer than that. However, the model might be general enough to be extended to longer videos.
Thank you for your explanation!
First of all, I thank you for your contribution to the community. Can you explain why the MomentDETR only supports the video up to 150s? When I comment
run_on_video/run.py, L:41
, it still works.