Instructions to use facebook/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="facebook/sam3")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Request for Reconsideration of Rejected SAM 3 Access
#695
by ber1231 - opened
Hello SAM 3 Team,
My access request to the facebook/sam3 repository on Hugging Face was rejected.
I am working on a robotics vision research project involving egocentric-to-robot-view rendering and human demonstration data processing.
I would like to use SAM 3 for:
- Human body and arm segmentation.
- Video object segmentation and tracking.
- Generating segmentation masks for background inpainting and robot scene reconstruction.
The model will be used locally for academic and research purposes. I will comply with the SAM 3 license and usage requirements, and I will not redistribute the model weights.
Could you please review my access request and, if possible, reset my rejected access status so that I can submit a new request?
My Hugging Face username: ber1231
Thank you for your time and consideration.