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 AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Request for manual review or reset of rejected SAM3 access
#424
by yilo59 - opened
Hello Meta SAM 3 team,
My access request for facebook/sam3 was rejected. Could you please manually review my request or reset its status so I can resubmit it?
I am reproducing the open-source CaP-X framework for non-commercial robotics research and evaluation. SAM3 will be used locally only for image segmentation and perception in robot-manipulation benchmarks. I will comply with the SAM 3 license and applicable policies, and I will not redistribute the model weights.
Please let me know if any additional information is required. Thank you for your consideration.