metadata

license: apache-2.0
language:
  - en

SAM/SAM2 ONNX Models

The ONNX models in this repository are converted using a slightly modified Colab notebook present in github.com/ibaiGorordo/ONNX-SAM2-Segment-Anything. Use the sam2/sam2.py or annotation_app.py scripts in the ONNX-SAM2-Segment-Anything repository to perform inference with the ONNX models.

Check the modified notebook here: https://github.com/shubham0204/Segment-Anything-Android/blob/main/notebooks/SAM2_ONNX_Export.ipynb

The converted ONNX models are stored in this repository to facilitate their usage in the github.com/shubham0204/Segment-Anything-Android project, which uses the onnxruntime in Android to infer the SAM/SAM2 models.

Citations

@misc{ravi2024sam2segmentimages,
      title={SAM 2: Segment Anything in Images and Videos}, 
      author={Nikhila Ravi and Valentin Gabeur and Yuan-Ting Hu and Ronghang Hu and Chaitanya Ryali and Tengyu Ma and Haitham Khedr and Roman Rädle and Chloe Rolland and Laura Gustafson and Eric Mintun and Junting Pan and Kalyan Vasudev Alwala and Nicolas Carion and Chao-Yuan Wu and Ross Girshick and Piotr Dollár and Christoph Feichtenhofer},
      year={2024},
      eprint={2408.00714},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2408.00714}, 
}

@misc{kirillov2023segment,
      title={Segment Anything}, 
      author={Alexander Kirillov and Eric Mintun and Nikhila Ravi and Hanzi Mao and Chloe Rolland and Laura Gustafson and Tete Xiao and Spencer Whitehead and Alexander C. Berg and Wan-Yen Lo and Piotr Dollár and Ross Girshick},
      year={2023},
      eprint={2304.02643},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2304.02643}, 
}