With these enhancements, our model achieves strong multi-modality segmentation performance, and can be trained in approximately 1 day on a single A100 (40GB) GPU.
Training and inference can be done by running train.py and infer.py. Model weights are stored in the pytorch_model.bin file, which can be loaded for inference.
1@article{lyu2024mcp,
2 title={MCP-MedSAM: A Powerful Lightweight Medical Segment Anything Model Trained with a Single GPU in Just One Day},
3 author={Lyu, Donghang and Gao, Ruochen and Staring, Marius},
4 journal={arXiv preprint arXiv:2412.05888},
5 year={2024}
6}
