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 Manual Review / Reset of Rejected SAM 3 Access β Academic Research
Hello Meta SAM Team,
My access request to the SAM 3 gated repository was rejected, and I am unable to submit a new request.
I am Zhiguo Zhou, an Associate Professor at Beijing Institute of Technology. My research focuses on embodied intelligence, multimodal perception, autonomous systems, and signal processing.
I intend to use SAM 3 solely for non-commercial academic research, including visual perception, image segmentation, robotic manipulation, and embodied-system experiments. The model will be used locally for research and evaluation. I will comply fully with the applicable license and acceptable-use requirements and will not redistribute the model weights or access credentials.
Hugging Face username: Zebedee2021
Affiliation: Beijing Institute of Technology
Laboratory: USUN Lab
Website: https://spaitlab.github.io/BIT-USUN-Lab/
Could you please manually reconsider my application or reset it to pending so that I can resubmit the required information?
Thank you.