May 9, 2019

209 words 1 min read

lutzroeder/netron

lutzroeder/netron

Visualizer for neural network, deep learning and machine learning models

repo name lutzroeder/netron
repo link https://github.com/lutzroeder/netron
homepage https://www.lutzroeder.com/ai
language JavaScript
size (curr.) 21620 kB
stars (curr.) 8301
created 2010-12-26
license MIT License

Netron is a viewer for neural network, deep learning and machine learning models.

Netron supports ONNX (.onnx, .pb, .pbtxt), Keras (.h5, .keras), Core ML (.mlmodel), Caffe (.caffemodel, .prototxt), Caffe2 (predict_net.pb, predict_net.pbtxt), Darknet (.cfg), MXNet (.model, -symbol.json), ncnn (.param) and TensorFlow Lite (.tflite).

Netron has experimental support for TorchScript (.pt, .pth), PyTorch (.pt, .pth), Torch (.t7), Arm NN (.armnn), BigDL (.bigdl, .model), Chainer (.npz, .h5), CNTK (.model, .cntk), Deeplearning4j (.zip), MediaPipe (.pbtxt), ML.NET (.zip), MNN (.mnn), OpenVINO (.xml), PaddlePaddle (.zip, __model__), scikit-learn (.pkl), TensorFlow.js (model.json, .pb) and TensorFlow (.pb, .meta, .pbtxt, .ckpt, .index).

Install

macOS: Download the .dmg file or run brew cask install netron

Linux: Download the .AppImage file or run snap install netron

Windows: Download the .exe installer.

Browser: Start the browser version.

Python Server: Run pip install netron and netron [FILE] or import netron; netron.start('[FILE]').

Models

Sample model files to download or open using the browser version:

comments powered by Disqus