Instructions to use djduecaster/dfreq-tug with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Microduck
How to use djduecaster/dfreq-tug with Microduck:
# Replace SLOT with the slot specified in the model card (walk, stand, sitstand, ground_pick, kick_left, kick_right, roulade). sudo robotctl policy load SLOT djduecaster/dfreq-tug
- Notebooks
- Google Colab
- Kaggle
Download visual-review.json from djduecaster/dfreq-tug: direct link, hf CLI and curl.
- Browser
- Download file 571 Bytes
-
https://huggingface.co/djduecaster/dfreq-tug/resolve/main/visual-review.json
- Command line
-
hf download hf://djduecaster/dfreq-tug/visual-review.json
-
curl -L -o visual-review.json https://huggingface.co/djduecaster/dfreq-tug/resolve/main/visual-review.json
571 Bytes
| { | |
| "model_sha256": "3d67cd3705bf8c8e12ee27723edc05b378fe8c7274350d61c7e53f19b8cfc362", | |
| "image": "validation-visual.png", | |
| "image_sha256": "65a2f3ab42cf1dbf308a4698c003f09d92342be5d5ca1267ae59cd0f1be16c53", | |
| "visually_inspected": true, | |
| "method": "Recorded collision geometry reconstructed with mj_kinematics only; not a new dynamics simulation.", | |
| "own_side": "west on1/3/5; east on2/4", | |
| "all5_pit_wins": true, | |
| "max_recorded_tie_gap_m": 0.005296403544963082, | |
| "limits": "Images show pose/geometry, not measured contact forces. No generalization inference." | |
| } | |