Instructions to use AhmadYarAI/EdgeTAM-CoreML-Video with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use AhmadYarAI/EdgeTAM-CoreML-Video with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(AhmadYarAI/EdgeTAM-CoreML-Video) with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): predictor.set_image(<your_image>) masks, _, _ = predictor.predict(<input_prompts>)# Use SAM2 with videos import torch from sam2.sam2_video_predictor import SAM2VideoPredictor predictor = SAM2VideoPredictor.from_pretrained(AhmadYarAI/EdgeTAM-CoreML-Video) with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): state = predictor.init_state(<your_video>) # add new prompts and instantly get the output on the same frame frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>): # propagate the prompts to get masklets throughout the video for frame_idx, object_ids, masks in predictor.propagate_in_video(state): ... - Notebooks
- Google Colab
- Kaggle
| EdgeTAM Core ML Video | |
| This repository contains a community Core ML conversion derived from EdgeTAM: | |
| https://github.com/facebookresearch/EdgeTAM | |
| The original EdgeTAM code and checkpoints are Copyright Meta Platforms, Inc. | |
| and affiliates and are distributed under the Apache License, Version 2.0. | |
| Core ML video conversion, explicit-memory runtime design, iOS integration, | |
| and validation were performed by Ahmad Yar (AhmadYarAI). | |
| Modified from the original distribution by conversion from PyTorch checkpoint | |
| components into four Core ML model packages and by exposing an explicit video | |
| memory-bank interface for application-side orchestration. | |
| This community conversion is not affiliated with or endorsed by Meta. | |