Instructions to use facebook/flava-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/flava-full with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForPreTraining processor = AutoProcessor.from_pretrained("facebook/flava-full") model = AutoModelForPreTraining.from_pretrained("facebook/flava-full", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from facebook/flava-full: direct link, hf CLI and curl.
- Browser
- Download file 881 Bytes
-
https://huggingface.co/facebook/flava-full/resolve/refs%2Fpr%2F1/preprocessor_config.json
- Command line
-
hf download hf://facebook/flava-full@refs/pr/1/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/facebook/flava-full/resolve/refs%2Fpr%2F1/preprocessor_config.json
881 Bytes
| { | |
| "codebook_crop_size": 112, | |
| "codebook_do_center_crop": true, | |
| "codebook_do_map_pixels": true, | |
| "codebook_do_normalize": true, | |
| "codebook_do_resize": true, | |
| "codebook_image_mean": [ | |
| 0.0, | |
| 0.0, | |
| 0.0 | |
| ], | |
| "codebook_image_std": [ | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "codebook_resample": 1, | |
| "codebook_size": 112, | |
| "crop_size": 224, | |
| "do_center_crop": true, | |
| "do_normalize": true, | |
| "do_resize": true, | |
| "feature_extractor_type": "FlavaFeatureExtractor", | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "input_size_patches": 14, | |
| "mask_group_max_aspect_ratio": null, | |
| "mask_group_max_patches": null, | |
| "mask_group_min_aspect_ratio": 0.3, | |
| "mask_group_min_patches": 16, | |
| "processor_class": "FlavaProcessor", | |
| "resample": 3, | |
| "size": 224, | |
| "total_mask_patches": 75 | |
| } | |