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 to reconsider SAM3 access β academic research
I am a researcher working on the application of AI to hydraulic and civil engineering. My current research focuses on video-based construction quality inspection for rockfill and earth-rock dam construction, including object segmentation, tracking, and process understanding of abnormal large aggregate particles during material dumping and spreading operations.
I would like to use SAM 3.1 for non-commercial academic research, mainly to evaluate its video segmentation and multi-object tracking capabilities in complex engineering construction scenarios with occlusion, appearance changes, and similar-background interference.
The model will be used only for scientific research, method evaluation, and academic publication. I will comply with the SAM license, usage policies, and all applicable terms and conditions.