Netron
Visualizer for neural network, deep learning and machine learning models.
Categories:
Netron is a viewer for neural network, deep learning, and machine learning models, supporting a wide range of formats across platforms including web, desktop, and Python.
๐ Overview
Netron provides an intuitive way to visualize complex machine learning model architectures, solving the problem of opaque 'black box' models by rendering interactive graphs of layers, nodes, tensors, and attributes.
It is built for machine learning engineers, data scientists, AI researchers, and developers who need to inspect, debug, understand, or present neural network structures without framework-specific tools.
Created by Lutz Roeder, a Principal Software Engineer at Microsoft, Netron was developed to offer universal support for popular model formats, making it easier to explore models from various ecosystems like ONNX, PyTorch, TensorFlow, and more.
โจ Key Features
- Interactive model visualization with support for stable formats including ONNX, TensorFlow Lite, PyTorch, torch.export, ExecuTorch, Core ML, Keras, Caffe, Darknet, TensorFlow.js, Safetensors, and NumPy
- Experimental support for TorchScript, MLIR, TensorFlow, OpenVINO, RKNN, ncnn, MNN, PaddlePaddle, GGUF, scikit-learn, and recent additions like JAX
- Cross-platform: browser-based app at netron.app, native desktop apps for Windows, macOS, Linux, and Python integration via pip
- Sample models available for quick testing
๐ Tech Stack
- Frontend: JavaScript
- Desktop: Electron
- Python: netron package
- No backend, database, or auth required (standalone viewer)
- Hosting: netron.app (web), GitHub releases
๐ฅ Who Is This For?
This project is useful for:
- Developers who want to visualize and debug ML model architectures
- Teams looking for a framework-agnostic model inspector
- Indie makers building AI tools needing quick model insights
๐ธ Screenshots / Demo
- Live demo: https://netron.app
- GitHub: https://github.com/lutzroeder/netron
๐ฅ Project Status
- ๐ข Actively building
Last updated: 2026-03-24
โ FAQ
Is this project free?
Yes โ fully open source under MIT license. (Explain briefly.)
Is the source code available?
Yes โ link to repository https://github.com/lutzroeder/netron
Can I contribute?
Refer to CONTRIBUTING.md, report issues, or submit pull requests on GitHub.
๐ฌ Contact & Links
- Website: https://netron.app
- GitHub: https://github.com/lutzroeder/netron
- Twitter/X: https://x.com/lutzroeder
- Email: (via GitHub issues)
Built with โค๏ธ and kept warm on WarmIndex.
Similar apps
CodeSandbox: Instant Cloud Development Environments
codesandbox.io
CodeSandbox is a cloud development platform that empowers developers to code, collaborate and ship projects of any size from any device in record time.
Beelzebub | AI-Native security platform
beelzebub-honeypot.com
Traditional security fails when attackers are already inside. Beelzebub delivers full-stack AI deception across your entire infrastructure Kubernetes clusters, APIs, AI agent tools, IoT devices. Catching lateral movement with zero false positives, slashing MTTR from hours to seconds, and cutting SOC costs by 60%.
Refero รขยย UI/UX Design Inspiration for Your Next Project
refero.design
The largest collection of UI/UX references and design inspiration for web and iOS. Explore tens of thousands of screenshots with advanced search capabilities
Open-Source LLM Evaluation Platform | Opik by Comet
comet.comsiteproductsopik
Opik is an end-to-end LLM evaluation platform designed to help AI developers test, ship, and continuously improve LLM-powered applications.