Instructions to use AtlasAnalyticsLab/AtlasPatch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use AtlasAnalyticsLab/AtlasPatch with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(AtlasAnalyticsLab/AtlasPatch) 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(AtlasAnalyticsLab/AtlasPatch) 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
Link paper and project page to model card
#1
by nielsr HF Staff - opened
Hi, I'm Niels from the community science team at Hugging Face.
This PR improves the documentation for AtlasPatch by:
- Linking the model card to the research paper on Hugging Face Papers.
- Adding a link to the official project page for better accessibility.
- Updating the citation section with the correct paper URL.
- Ensuring the
library_nameand metadata are correctly set for discoverability.