Instructions to use chill112/UNI-fixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use chill112/UNI-fixed with timm:
import timm model = timm.create_model("hf_hub:chill112/UNI-fixed", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from chill112/UNI-fixed: direct link, hf CLI and curl.
- Browser
- Download file 552 Bytes
-
https://huggingface.co/chill112/UNI-fixed/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://chill112/UNI-fixed/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/chill112/UNI-fixed/resolve/main/preprocessor_config.json
552 Bytes
| { | |
| "_comment": "Preprocessor configuration for mahmoodlab/UNI (image encoder). Optimized for image understanding tasks.", | |
| "feature_extractor_type": "ImageFeatureExtractor", | |
| "model_input_name": "pixel_values", | |
| "do_resize": true, | |
| "do_center_crop": true, | |
| "do_normalize": true, | |
| "do_convert_rgb": true, | |
| "size": { | |
| "shortest_edge": 224 | |
| }, | |
| "crop_size": { | |
| "height": 224, | |
| "width": 224 | |
| }, | |
| "image_mean": [0.485, 0.456, 0.406], | |
| "image_std": [0.229, 0.224, 0.225], | |
| "resample": 2, | |
| "format": "RGB", | |
| "reduce_labels": false | |
| } | |