Downloads · 30 days
0
pattgene/trackfish3d
trackfish3d is a machine learning model from pattgene. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
This repository hosts the released checkpoints for TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos.
Downloads · 30 days
0
Access
Public
Updated Oct 1, 2026
Repo size
23.8 MB
Likes
0
Public
Click a slice to open those files.
.pth23.8 MB · 100%
From the Hugging Face model README
This repository hosts the released checkpoints for TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos.
Code repository:
Model repository:
Project page:
SynFish data:
trackfish3d-SAM3trackfish3d-SAM3/best_ckpt.pth--no_dino105a66ab7b34fbb7939de3e2b909021386c6c0d3072488f1b3e6651c022bfad3trackfish3d-YOLO26+SAM2trackfish3d-YOLO26+SAM2/best_ckpt.pth--no_dinod2f566d9c85c0a7dcaa636f77afdec1aa3f82a3216ae88b1f69b6c96d649c6e4trackfish3d-3D-ZeFtrackfish3d-3D-ZeF/best_ckpt.pth--no_dinoe081e148ed481f15a1bfc70901ae86d29b06e0f2b3822980d939fb54c789c536Install the TrackFish3D code from:
Example inference command:
python infer.py \
/path/to/best_ckpt.pth \
/path/to/scene.json \
/path/to/scene-images \
--no_dino \
--output outputs/scene.txt
Example evaluation command:
python evaluate.py \
--pred outputs/test1.txt \
--gt /path/to/synfish/test/gt-traj/test1-gt.csv \
--match_pred_range
For the released benchmark GT filenames, the evaluator selects the matching protocol automatically. For other datasets, configure the evaluation protocol explicitly.
This Hugging Face repository hosts checkpoints only. The released SynFish download is available at:
After extraction, synfish/ should contain train/ and test/.
The official 3D-ZeF dataset source is: