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 review or reset of rejected SAM3 access
Hello SAM3 team,
My name is Jiangyu Liu (刘江宇), and I am a student in the Department of Automation at Tsinghua University.
My access request to facebook/sam3 was rejected, but no reason was shown. Could you please review my request or reset its status so I can provide any missing information?
Hugging Face username: hezhou0331
Affiliation: Department of Automation, Tsinghua University
Intended use: Object segmentation in robotic simulation
We plan to run SAM3 on our research server to identify and segment target objects in simulated robot scenes, supporting perception and manipulation experiments. We will use the model in accordance with its license and applicable usage requirements.
I would be happy to provide further details about our research if needed.
Thank you for your time and consideration.
Best regards,
Jiangyu Liu