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 or reset of rejected SAM 3 access
#644
by hy2007 - opened
Hello SAM 3 team,
My Hugging Face username is hy200704.
My affiliation is Guangdong Business and Technology University, China.
I intend to use SAM 3 in an educational RoboMaster competition project. The system involves computer-vision image segmentation, target tracking, and automatic aiming for a competition robot. It may also provide aiming data to the robot’s competition-approved firing mechanism.
This is my actual intended use. Could you please confirm whether it is permitted under the SAM 3 license? If it is eligible, would you please manually review or reset my rejected access request?
I will comply with all SAM 3 license and access terms.
Thank you.