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
Rejected
Hello Meta SAM 3 Team,
My Hugging Face access request for the facebook/sam3 repository was rejected, and I would like to respectfully request a manual review or reset of my access request so that I can reapply.
I intend to use SAM 3 for GIS and remote sensing image segmentation, particularly for building footprint extraction from aerial and satellite imagery. The model will be used locally for technical evaluation, geospatial analysis, and development of a building segmentation workflow.
I will comply with the SAM 3 license, Meta policies, and Hugging Face terms. I will not redistribute the model weights or provide unauthorized access to the model.
If my previous access request was incomplete or inconsistent, I would appreciate the opportunity to correct the information and submit the request again.
Hugging Face username: @dewanankcp
Could you please manually review my request or reset the rejected access status so I can reapply?
Thank you for your consideration.