Skip to content

Conversation

@n-poulsen
Copy link
Contributor

This pull request improves the superanimal_analyze_images method:

  • it adds the customized_model_config, customized_pose_checkpoint and customized_detector_checkpoint arguments so models that were refined on a dataset can be evaluated.
  • a new pose_threshold parameter is added to plot predictions either as ‘.’ (for confident predictions with likelihood > pose_threshold) and ’x’ for (likelihood <= pose_threshold).
  • a new plot_skeleton parameter is added to optionally plot a skeleton for the predictions (if one is defined in the config)

- a bit more to docstrings and added demo for pose_threshold for clarity
@MMathisLab MMathisLab merged commit 73f5248 into pytorch_dlc Dec 16, 2024
1 check passed
@MMathisLab MMathisLab deleted the niels/super_animal_image_plotting branch December 16, 2024 14:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants