After Training and Inference, some nodes are not predicted #1164
Unanswered
Jaspermoray
asked this question in
Help!
Replies: 1 comment 7 replies
-
Hi @Jaspermoray, It sounds like the crop size is for your top-down model is too small. Can you ensure that the crop size is set to Auto for both model configurations (in the Training Pipeline GUI)? Let us know if that helps. Thanks, |
Beta Was this translation helpful? Give feedback.
7 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi all,
I'm trying to use SLEAP to track crayfish, but I've run into a problem: After I choose initial instances, I run a top down training on 20 random frames, and only SOME of the nodes in those frames are predicted. When I return to the video scrolling part of the program, the predicted frames have less than half of the nodes, with the others just greyed out.
If it helps, I noticed that when I turned on visualization of the training, the frame appears to be cut off at the edges, and those nodes that are cut off are not predicted. Does anybody know why this would be?
Best,
Jasper Coles Hood
Beta Was this translation helpful? Give feedback.
All reactions