training dataset video #2889
Unanswered
XtraspotsSimpson
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
When training for action recognition, does the training video dataset need to match the frame sampling setting? For example, if my training model is VideoMAE and the frame sampling strategy is 1641, does my training video need to have a number of frames that is a multiple of 64?
Whether the frame will be automatically supplemented during training
Beta Was this translation helpful? Give feedback.
All reactions