Video Classification
Transformers
Safetensors
egosieve
robotics
egocentric-video
video-quality
dataset-curation
physical-ai
custom_code
Eval Results (legacy)
Instructions to use itspublu/EgoSieve-S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use itspublu/EgoSieve-S with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("video-classification", model="itspublu/EgoSieve-S", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForVideoClassification model = AutoModelForVideoClassification.from_pretrained("itspublu/EgoSieve-S", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from itspublu/EgoSieve-S: direct link, hf CLI and curl.
- Browser
- Download file 362 Bytes
-
https://huggingface.co/itspublu/EgoSieve-S/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://itspublu/EgoSieve-S/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/itspublu/EgoSieve-S/resolve/main/preprocessor_config.json
362 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_egosieve.EgoSieveProcessor" | |
| }, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "EgoSieveProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "num_frames": 12, | |
| "resample": 3, | |
| "resize_shortest_edge": 256, | |
| "size": { | |
| "height": 518, | |
| "width": 518 | |
| } | |
| } | |