Instructions to use t3ta/EdgeTAM-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use t3ta/EdgeTAM-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="t3ta/EdgeTAM-hf")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("t3ta/EdgeTAM-hf") model = AutoModel.from_pretrained("t3ta/EdgeTAM-hf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download video_preprocessor_config.json from t3ta/EdgeTAM-hf: direct link, hf CLI and curl.
- Browser
- Download file 711 Bytes
-
https://huggingface.co/t3ta/EdgeTAM-hf/resolve/main/video_preprocessor_config.json
- Command line
-
hf download hf://t3ta/EdgeTAM-hf/video_preprocessor_config.json
-
curl -L -o video_preprocessor_config.json https://huggingface.co/t3ta/EdgeTAM-hf/resolve/main/video_preprocessor_config.json
711 Bytes
| { | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "device": null, | |
| "do_center_crop": null, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "do_sample_frames": null, | |
| "fps": null, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "input_data_format": null, | |
| "num_frames": null, | |
| "pad_size": null, | |
| "processor_class": "Sam2VideoProcessor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_metadata": false, | |
| "size": { | |
| "height": 1024, | |
| "width": 1024 | |
| }, | |
| "video_metadata": null, | |
| "video_processor_type": "Sam2VideoVideoProcessor" | |
| } | |