Netron

Netron provides an interactive graphical view of neural‑network, deep‑learning and machine‑learning models. It can open model files in formats such as ONNX, TensorFlow Lite, PyTorch, torch.export, ExecuTorch, Core ML, Keras, Caffe, Darknet, TensorFlow.js, Safetensors and NumPy, with experimental support for TorchScript, MLIR, TensorFlow, OpenVINO, RKNN, ncnn, MNN, PaddlePaddle, GGUF and scikit‑learn. The viewer displays layers, connections and parameters, allowing users to explore model architecture without needing the original training code.

The tool is available as a web‑based viewer, a native macOS application, and packages for Linux and Windows, as well as a Python package that can be launched from the command line or embedded in scripts. Installation options include direct downloads, package managers (brew, winget) and pip. Sample models spanning many supported formats can be opened directly from the browser version.

Netron is aimed at developers, researchers and engineers who need to inspect, debug or document model structures across a wide range of machine‑learning frameworks. Its cross‑platform availability and broad format coverage make it a practical utility for visualising model internals.