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
Title: Request for Manual Review of Rejected SAM 3 Access
Hello Meta SAM 3 Team,
I am Wangzc, a2d23s3s3d.
My access request for the SAM 3 model was recently rejected. I would sincerely appreciate it if you could manually review my application or reset its status so that I can submit an updated request.
I am an AI perception engineer working on an intelligent robotic lawn mower project.
My intended use of SAM 3 is to support instance segmentation dataset construction:
- Use manually annotated bounding boxes as visual prompts.
- Generate instance segmentation masks for outdoor scenes, particularly road surfaces and obstacles.
- Manually review and correct the generated masks.
- Convert the reviewed masks into YOLOv8 segmentation training labels.
The model will be used for internal engineering development and dataset preparation. I will comply with the applicable SAM 3 license and usage restrictions, and will not redistribute the model weights.
Could you please let me know whether my application can be reconsidered?
Thank you for your time and consideration.