Netron is an open-source multi-platform visualizer and editor for artificial intelligence models. It supports many extensions for deep learning, machine learning and neural network models.  Netron is using Electron/ NodeJS and it has a binary application release for Windows, Linux and macOS.

Netron is popular among data scientists, The project's page at Github received 6.8k stars and >800 forks.

Primary support

  • ONNX (.onnx, .pb, .pbtxt)
  • Keras (.h5, .keras)
  • Core ML (.mlmodel)
  • Caffe (.caffemodel, .prototxt)
  • Caffe2 (predict_net.pb, predict_net.pbtxt)
  • MXNet (.model, -symbol.json),
  • NCNN (.param)
  • TensorFlow Lite (.tflite)

Experimental support

Netron's developer has added experimental support for more

  • TorchScript (.pt, .pth)
  • PyTorch (.pt, .pth)
  • Torch (.t7)
  • CNTK (.model, .cntk)
  • Deeplearning4j (.zip)
  • PaddlePaddle (.zip, model)
  • Darknet (.cfg)
  • scikit-learn (.pkl)
  • ML.NET (.zip)
  • MNN (.mnn)
  • OpenVINO (.xml)
  • BigDL (.bigdl, .model)
  • Chainer, (.npz, .h5)
  • TensorFlow.js (model.json, .pb)
  • TensorFlow (.pb, .meta, .pbtxt).

Platforms

  • Windows
  • macOS
  • Linux AppImage and .dep package for (Debian and Ubuntu)

Resources