Instructions to use nielsr/vitpose-base-simple with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nielsr/vitpose-base-simple with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, ViTPoseForPoseEstimation processor = AutoImageProcessor.from_pretrained("nielsr/vitpose-base-simple") model = ViTPoseForPoseEstimation.from_pretrained("nielsr/vitpose-base-simple", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from nielsr/vitpose-base-simple: direct link, hf CLI and curl.
- Browser
- Download file 334 Bytes
-
https://huggingface.co/nielsr/vitpose-base-simple/resolve/refs%2Fpr%2F1/preprocessor_config.json
- Command line
-
hf download hf://nielsr/vitpose-base-simple@refs/pr/1/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/nielsr/vitpose-base-simple/resolve/refs%2Fpr%2F1/preprocessor_config.json
334 Bytes
| { | |
| "do_affine_transform": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "ViTPoseImageProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 256, | |
| "width": 192 | |
| } | |
| } | |