Published November 27, 2024 | Version v1
Model Open

DIPLOMAT verification set: pretrained DLC and SLEAP models and a video clip from MABe22

Authors/Creators

  • 1. ROR icon University of Arizona

Description

File N5PZS.avi is licensed under CC-BY-NC-SA 2.0.

N5PZS.avi was created using FFmpeg to clip 30 frames between seconds 9 and 10 from video N5PZSB5ZMMNNUJ4APNYG.avi in the MABe 2022 dataset mouse_submission_videos_resized_224.zip.

Files SLEAP_5bp.zip and DLC_5bp.zip are licensed under CC-BY-4.0.

SLEAP_5bp.zip contains a pretrained SLEAP animal tracking model. 

DLC_5bp.zip contains a pretrained DeepLabCut animal tracking model.

Both models were trained using the University of Arizona's high-performance computing (HPC) resources.

Files

DLC_5bp.zip

Files (590.7 MB)

Name Size Download all
md5:14ce90f52c8a58d76e42c7b9628ea2ae
462.4 MB Preview Download
md5:2b0b1357c7c9de33385262469d7349e3
127.7 kB Download
md5:c6ebb7f60683ae05de40839b79062ed8
128.2 MB Preview Download

Additional details

Dates

Created
2024-11-27

References

  • Sun, J., Marks, M., Guether, B., Kumar, V., Robie, A., Schretter, C., Sheppard, K., Chakraborty, D., Wagner, J., Parker, J., Branson, K., & Kennedy, A. (2023). Dataset for MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior [Data set]. CaltechDATA. https://doi.org/10.22002/rdsa8-rde65
  • T. D. Pereira, N. Tabris, A. Matsliah, D. M. Turner, J. Li, S. Ravindranath, E. S. Papadoyannis, E. Nor- mand, D. S. Deutsch, Z. Y. Wang et al., "Sleap: A deep learning system for multi-animal pose tracking," Nature methods, vol. 19, no. 4, pp. 486–495, 2022.
  • J. Lauer, M. Zhou, S. Ye, W. Menegas, S. Schneider, T. Nath, M. M. Rahman, V. Di Santo, D. Soberanes, G. Feng et al., "Multi-animal pose estimation, identi- fication and tracking with deeplabcut," Nature Methods, vol. 19, no. 4, pp. 496–504, 2022.