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
Please reset my rejected SAM 3 access request
Dear Meta SAM 3 team,
I am writing to ask, respectfully, that you please reconsider a rejected access request. My Hugging Face username is lrn1991. I work at 鍏变韩閾搁挗, on a crane-safety project in a foundry. Overhead cameras watch whether a person is standing near a suspended load, so the crew can be warned before someone is hurt. SAM 3 would be used only on our own machines, inside the factory network, to segment people and the load in these camera views.
I understand that a rejection on Hugging Face stops me from submitting the access form again. I am sorry if my first request was incomplete or unclear. I have checked my account, and I will follow the SAM 3 license, the acceptable-use policy, and the Hugging Face terms. I will not redistribute the weights, publish them, or offer them as a service to anyone else.
Could you please reset my request, or move it back to pending, so that I can agree to the terms and apply once more? I would be very grateful for your time.
Thank you.