Instructions to use ronka/postureDetection-Mediapipe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ronka/postureDetection-Mediapipe with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ronka/postureDetection-Mediapipe", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from ronka/postureDetection-Mediapipe: direct link, hf CLI and curl.
- Browser
- Download file 490 Bytes
-
https://huggingface.co/ronka/postureDetection-Mediapipe/resolve/main/config.json
- Command line
-
hf download hf://ronka/postureDetection-Mediapipe/config.json
-
curl -L -o config.json https://huggingface.co/ronka/postureDetection-Mediapipe/resolve/main/config.json
490 Bytes
| { | |
| "model_type": "posture_detection", | |
| "architecture": "PostureDetectionModel", | |
| "trained_weights": null, | |
| "init_args": { | |
| "image_size": 256, | |
| "num_channels": 3, | |
| "output_features": ["offset", "neck_inclination", "torso_inclination"] | |
| }, | |
| "mediapipe": { | |
| "mp_pose": { | |
| "module_path": "mediapipe.solutions.pose", | |
| "class_name": "Pose" | |
| }, | |
| "mp_pose_landmark": { | |
| "module_path": "mediapipe.solutions.pose", | |
| "class_name": "PoseLandmark" | |
| } | |
| } | |
| } |