netron
SHA-256A viewer for neural network, deep learning and machine learning models.
Smart Download
Download Download Version
v9.0.7 · 91.8 MB
Drag and drop any model file to visualize its neural network architecture instantly.
Core Features
- Supports ONNX, TensorFlow Lite, PyTorch, Core ML, OpenVINO, Keras, Caffe, Darknet and more
- Browser version runs instantly at netron.app
- Desktop app for macOS, Linux, and Windows
- Drag & drop interface reveals layer details, tensor shapes, and parameters
- Export to image or share via URL
What It Can't Do
- •Experimental formats may lack full compatibility; large models (>1GB) load slowly; avoid uploading sensitive data in the browser version.
Use Cases
- Debug model structure when training with PyTorch or TensorFlow
- Learn deep learning by exploring pre-trained model architectures
- Collaborate with teams by sharing visualized model layouts
Detailed Introduction
Netron is a visualizer that lets you inspect neural network, deep learning and machine learning models in a user-friendly interface. It supports ONNX, TensorFlow Lite, PyTorch, Core ML, OpenVINO, Keras, Caffe, Darknet, and many more formats. You can explore layer-by-layer architecture, view tensor shapes, parameters, and connections without writing code. Netron runs in your browser as a web app, or as a native desktop application on macOS, Linux, and Windows. It also offers a Python package for programmatic use. The tool is ideal for debugging, understanding model structure, and sharing insights with team members. With experimental support for MLIR, GGUF, and other emerging formats, Netron stays up-to-date with the latest AI frameworks.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Install the appropriate package for your distro (dpkg / rpm / AppImage)
Browser: open netron.app, upload file or paste URL
Desktop: download installer for your OS and run it
Python: pip install netron, then netron model.onnx
- Browser: open netron.app, upload file or paste URL
- Desktop: download installer for your OS and run it
- Python: pip install netron, then netron model.onnx
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
1a3b484ec41cafd404463105bc14ac7b0232fc0c1336ac1a85b316495e708aeaThis checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
macOS: move Netron to Trash; Windows: uninstall via Settings/Apps; Linux: use package manager (e.g. apt remove netron)
No Extra Dependencies
Ready to use after download. No additional runtime required.
Similar Projects
Visual Studio Code (Code - OSS)
A free, open-source code editor by Microsoft with rich extensions, debugging, and Git integration. The most popular developer tool worldwide.
scrcpy
Display and control your Android device from your computer via USB or TCP/IP. No root required, high performance, low latency, supports audio and video mirroring.
godot
Godot Engine is a free, open-source, cross-platform 2D and 3D game engine with a unified editor. Unlike Unity or Unreal, it's entirely MIT-licensed and community-driven, offering a lightweight yet powerful node-based workflow that runs on a single executable.