Medical Open Network for AI for AMD ROCm™
MONAI for AMD ROCm™ is a PyTorch-based, open-source framework for deep learning in healthcare imaging, part of the PyTorch Ecosystem, enabled for AMD Instinct GPUs.
Its ambitions are as follows:
- Developing a community of academic, industrial and clinical researchers collaborating on a common foundation;
- Creating state-of-the-art, end-to-end training workflows for healthcare imaging;
- Providing researchers with the optimized and standardized way to create and evaluate deep learning models.
Please see the technical highlights and What's New of the milestone releases.
- flexible pre-processing for multi-dimensional medical imaging data;
- compositional & portable APIs for ease of integration in existing workflows;
- domain-specific implementations for networks, losses, evaluation metrics and more;
- customizable design for varying user expertise;
- multi-GPU multi-node data parallelism support.
MONAI for AMD ROCm works with Python 3.12, and depends directly on NumPy and PyTorch for AMD ROCm with many optional dependencies.
- AMD MONAI supports ROCm-LS/hipCIM for accelerated image loading and processing on AMD Instinct GPUs.
- See the
requirements*.txtfiles for dependency version information.
Install the current release using pip with the appropriate ROCm index:
| ROCm Version | Install Command |
|---|---|
| 7.0.2 | pip install amd-monai --extra-index-url=https://pypi.amd.com/rocm-7.0.2/simple/ |
| 7.2 | pip install amd-monai --extra-index-url=https://pypi.amd.com/rocm-7.2.0/simple/ |
For additional options, see the installation guide.
MedNIST demo and MONAI for PyTorch Users are available on Colab.
Examples and notebook tutorials are located at Project-MONAI/tutorials.
Technical documentation is available at MONAI for AMD ROCm documentation.
If you have used MONAI in your research, please cite us! The citation can be exported from: https://arxiv.org/abs/2211.02701.
The MONAI Model Zoo is a place for researchers and data scientists to share the latest and great models from the community. Utilizing the MONAI Bundle format makes it easy to get started building workflows with MONAI.
For guidance on making a contribution to MONAI, see the contributing guidelines.
Join the conversation on Twitter/X @ProjectMONAI, LinkedIn, or join our Slack channel.
Ask and answer questions over on MONAI's GitHub Discussions tab.
- Website: https://instinct.docs.amd.com/latest/life-science/MONAI.html
- Code: https://github.com/ROCm-LS/MONAI
- Issue tracker: https://github.com/ROCm-LS/MONAI/issues
- PyPI package: https://pypi.amd.com/simple/amd-monai/