Instructions to use rapadilla/videomae-base-short with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rapadilla/videomae-base-short with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("video-classification", model="rapadilla/videomae-base-short")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForPreTraining processor = AutoImageProcessor.from_pretrained("rapadilla/videomae-base-short") model = AutoModelForPreTraining.from_pretrained("rapadilla/videomae-base-short", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from rapadilla/videomae-base-short: direct link, hf CLI and curl.
- Browser
- Download file 271 Bytes
-
https://huggingface.co/rapadilla/videomae-base-short/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://rapadilla/videomae-base-short/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/rapadilla/videomae-base-short/resolve/main/preprocessor_config.json
271 Bytes
| { | |
| "do_center_crop": true, | |
| "do_normalize": true, | |
| "do_resize": true, | |
| "feature_extractor_type": "VideoMAEFeatureExtractor", | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "resample": 2, | |
| "size": 224 | |
| } | |