Skip to content

Conversation

@n-poulsen
Copy link
Contributor

This pull request implements methods to visualize maps output by PyTorch models (scoremaps, location refinement fields and part-affinity fields) as they are for TensorFlow models.

API Methods Implemented for the PyTorch Engine

  • extract_maps
  • visualize_scoremaps
  • visualize_locrefs
  • visualize_paf
  • extract_save_all_maps

UX Improvements

  • only start training pose models when epochs > 0
  • get_model_snapshots: when no snapshots were found, the snapshot manager's snapshot prefix was obtained incorrectly
  • fine-tuning SuperAnimal detectors: added key_metric so the best detector si saved

@MMathisLab
Copy link
Member

@maximpavliv please test; I won't have time in the next days.

Copy link
Contributor

@maximpavliv maximpavliv left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Some minor corrections :)

@n-poulsen
Copy link
Contributor Author

@maximpavliv good catches, thanks! I implemented the fixes from your suggestions

@n-poulsen n-poulsen requested a review from maximpavliv December 2, 2024 12:24
@n-poulsen n-poulsen requested a review from maximpavliv December 2, 2024 12:55
@n-poulsen n-poulsen merged commit 5e24956 into pytorch_dlc Dec 2, 2024
@n-poulsen n-poulsen deleted the niels/extract_maps branch December 2, 2024 12:56
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.

4 participants