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") - Notebooks
- Google Colab
- Kaggle
Request for SAM3 access
#321
by Jiangeng - opened
Hello Meta AI Team,
My access request to the sam3 repository was rejected today. I am a first-year Ph.D student working on my robotic paper.
I intend to use SAM3 locally for non-commercial academic coursework only. I will fully comply with the SAM3 license, acceptable-use requirements, and the relevant privacy policy. The model and outputs will only be used for learning, experimentation, and writing my course project report.
Could you please let me know whether my request can be manually reviewed or reset so that I can resubmit my information correctly? I would be happy to provide any additional academic affiliation details if needed.
Thank you very much for your time and consideration.