#6262nd of 105 in ML frameworks and librariesFor science, health and research
monai
PyTorch framework for deep learning on medical imaging data
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 8.8k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
7,957 on 1 Apr 20268,790 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
MONAI is a PyTorch-based Python library for training and evaluating deep learning models on healthcare imaging data. It provides pre-processing for multi-dimensional medical images, plus networks, losses and metrics specific to the domain, with multi-GPU and multi-node data parallelism. Pretrained models are shared in a separate Model Zoo using the MONAI Bundle format.
Who it is for: Researchers and engineers training deep learning models on medical images
Strengths
- Domain-specific networks, losses and metrics for medical imaging, not generic vision only
- Supports multi-GPU and multi-node data parallel training
- Installs with pip, conda-forge or a Docker image; Apache-2.0 licensed
- Separate Model Zoo and tutorials repo with Colab notebooks, plus Read the Docs API docs
Weaknesses
- Tied to PyTorch; supports the current release plus three previous minor versions
- Scope is healthcare imaging; not a general-purpose ML or LLM library
- README gives no hardware requirements such as RAM or VRAM
- Many features depend on optional dependencies that need separate installation
What it needs
- GPU optional
- Docker
- Needs PyTorch, NumPy
- Models: PyTorch, MONAI Bundle
Also in ML frameworks and libraries
See all 105| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 92 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |