lisbet.io.ext_sources.mabe22#

MABe22 dataset.

References

  1. Sun, J. J. et al. MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior. Preprint at https://doi.org/10.48550/arXiv.2207.10553 (2023).

  2. Sun, J. et al. Dataset for MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior. CaltechDATA https://doi.org/10.22002/rdsa8-rde65 (2023).

  3. AIcrowd | MABe 2022: Mouse-Triplets - Video Data | Challenges. AIcrowd | MABe 2022: Mouse-Triplets - Video Data | Challenges https://www.aicrowd.com/challenges/multi-agent-behavior-challenge-2022/problems/mabe-2022-mouse-triplets-video-data.

  4. AIcrowd | MABe 2022: Mouse Triplets | Challenges. AIcrowd | MABe 2022: Mouse Triplets | Challenges https://www.aicrowd.com/challenges/multi-agent-behavior-challenge-2022/problems/mabe-2022-mouse-triplets.

Functions

load_mouse_triplets(train_path, ...)

Load the MABe22 Mouse Triplets dataset.
lisbet.io.ext_sources.mabe22.load_mouse_triplets(train_path, test_seq_path, test_labels_path)[source]#

Load the MABe22 Mouse Triplets dataset.

Parameters:

  • train_path (str) – Path to the training data file (numpy .npz format).

  • test_seq_path (str) – Path to the test sequences file (numpy .npz format).

  • test_labels_path (str) – Path to the test labels file (numpy .npz format).

Returns:

List of tuples (record_id, record_data) for training data.

Return type:

list