Instructions to use CIDAS/clipseg-rd64-refined with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CIDAS/clipseg-rd64-refined with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="CIDAS/clipseg-rd64-refined")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, CLIPSegForImageSegmentation processor = AutoProcessor.from_pretrained("CIDAS/clipseg-rd64-refined") model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from CIDAS/clipseg-rd64-refined: direct link, hf CLI and curl.
- Browser
- Download file 380 Bytes
-
https://huggingface.co/CIDAS/clipseg-rd64-refined/resolve/refs%2Fpr%2F7/preprocessor_config.json
- Command line
-
hf download hf://CIDAS/clipseg-rd64-refined@refs/pr/7/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/CIDAS/clipseg-rd64-refined/resolve/refs%2Fpr%2F7/preprocessor_config.json
380 Bytes
| { | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "feature_extractor_type": "ViTImageProcessor", | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "processor_class": "CLIPSegProcessor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 352, | |
| "width": 352 | |
| } | |
| } | |