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 of Rejected SAM 3 Access
Hello Meta SAM 3 Team,
My access request to facebook/sam3 was recently rejected. I would appreciate it if you could manually reconsider my request or reset the rejected status so that I can resubmit the application.
I am an undergraduate researcher from Zhejiang University (ZJU), and I'm currently a research intern at ScaleLab, Shanghai Jiaotong Unversity under the guidance of Assistant Professor Yao Mu. I plan to use SAM 3 for non-commercial academic research, primarily for hand/object segmentation and tracking in human-object interaction and robot dexterous manipulation research.
I will comply with the applicable Meta license and usage policies and will not redistribute the model weights.
Hugging Face username: Hydrofoil
Affiliation: College of Control Science and Engineering, Zhejiang University & ScaleLab, Shanghai Jiaotong Unversity
Thank you for your consideration.