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
#268
by araguapi - opened
Dear SAM3 Team,
My previous access request for SAM3 was rejected. I respectfully ask if you could re-evaluate my request.
I am Huixian Cheng from Southwest University. My current research focuses on self-supervised learning for 2D semantic segmentation in autonomous driving. I intend to use SAM3 for non-commercial academic research on zero-shot text-prompt segmentation and tracking. I will comply with the model license, will not redistribute checkpoints, and will properly cite your work.
If you need any additional information, please let me know. My email: chenghuixian@email.swu.edu.cn
Thank you,
Huixian Cheng