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 AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3") - Notebooks
- Google Colab
- Kaggle
Request for SAM3 access
#236
by Xielinbo - opened
I am a graduate student at Northeastern Univerisity, focusing on robotic grasping and embodied intelligence research. I request access to SAM 3 to develop a zero-shot visual perception module for our collaborative robot grasping system, to solve the segmentation bottleneck of unseen, occluded objects in unstructured cluttered scenes.
I will use the model exclusively for non-commercial academic research, will not share or distribute the model weights to any third party, and will properly cite the SAM 3 paper in all related academic outputs. I will strictly comply with the Meta SAM License and all relevant usage terms.