Instructions to use Histochemichael/so101-rack-handle-seg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use Histochemichael/so101-rack-handle-seg with ultralytics:
from huggingface_hub import hf_hub_download from ultralytics import YOLO # pick the weights file from this repo's "Files and versions" tab weights = hf_hub_download("Histochemichael/so101-rack-handle-seg", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
SO101 rack-handle segmentation
Gripper-camera segmentation model trained from 177 manually reviewed positive masks and 72 reviewed negatives.
Held-out test metrics
- Mask mAP50-95: 0.3145
- Mask mAP50: 0.8930
- Mask precision: 0.9274
- Mask recall: 0.8523
The split is grouped by source episode. The 20-image test split was not used for optimization or early stopping.
- Downloads last month
- 19