Replies: 1 comment
-
You could try to use additional targets or ReplayCompose for this |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Let's say we solve the problem of classification by sequence of frames (as action recognition). I would like to be able to apply the same augmentation for N frames. I think it's worth adding the "images" parameter, which contains a list of frames (similar to "masks")
Beta Was this translation helpful? Give feedback.
All reactions