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 Reconsideration of SAM 3 Access for Remote Sensing Research
Hello SAM 3 team,
My access request was recently rejected, and I would appreciate it if you could reconsider it or reset my application.
I am an undergraduate student at Yunnan Normal University, China, conducting research on remote sensing image segmentation for my graduation project. My work focuses on farmland boundary extraction and area estimation.
I have previously used SAM 2 to segment remote sensing imagery. I would now like to evaluate SAM 3 on the same task and compare its segmentation quality with SAM 2, particularly its ability to delineate farmland boundaries in complex agricultural landscapes.
The intended use is academic research. I will follow the model’s license and applicable usage requirements and properly cite the work.
Hugging Face username: yaoyu-rs-2026
Affiliation: Yunnan Normal University
Role: Undergraduate student
If any information in my original application was incomplete or unclear, I would be happy to clarify it.
Thank you for your time and consideration.