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")# 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 to reset rejected SAM3 access status β academic benchmarking
Hello Meta SAM3 Team,
My Hugging Face account is currently shown as rejected for the facebook/sam3 repository. However, I did not knowingly submit an access request and did not have an opportunity to provide my affiliation or intended-use information.
Could you please reset my access status so that I can submit the request form correctly?
Hugging Face username: wayflower
Affiliation:
Undergraduate student, School of Electronics Engineering and
Computer Science, Peking University
Intended use:
Non-commercial academic research and benchmarking of SAM 3 for computer vision and robotic perception experiments.
The model will be used locally on a laboratory workstation for segmentation evaluation. I will comply with the model license and acceptable-use requirements, and I will not redistribute the model weights or provide public access to them.
The project does not involve surveillance, biometric identification, military use, or other restricted applications.
Thank you for reviewing or resetting my access status.