Download config.json from lkid08/spacecraft-pose-estimation: direct link, hf CLI and curl.
- Browser
- Download file 656 Bytes
-
https://huggingface.co/lkid08/spacecraft-pose-estimation/resolve/main/config.json
- Command line
-
hf download hf://lkid08/spacecraft-pose-estimation/config.json
-
curl -L -o config.json https://huggingface.co/lkid08/spacecraft-pose-estimation/resolve/main/config.json
656 Bytes
| { | |
| "model_name": "SPEED+ Pose Estimator, sim-to-real study checkpoints", | |
| "description": "Direct 6DoF pose regression (ResNet-50 + MLP head) trained only on synthetic SPEED+ imagery. Seventeen checkpoints, one per experimental arm and seed; see README.md.", | |
| "arxiv": "2611.20321", | |
| "weights_doi": "10.5281/zenodo.24140385", | |
| "code": "https://github.com/lokindoo/spacecraft-pose-estimation", | |
| "license": "cc-by-4.0", | |
| "input": "3x320x512, ImageNet-normalised, from SPEED+ grayscale", | |
| "output": "7 values: translation (3, z-scored; un-normalise with the checkpoint's train_means and train_stds) then quaternion (4, scalar-first; unit-normalise)" | |
| } | |