Netron: Open-source Visualizer for Deep Learning, Machine Learning, and Neural Network Models

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



  • Now the framework provides you with the best solution for developing well-structured maintainable and upgradable software it saves a lot of time by reusing generic modules and libraries to focus on other areas of applications developed using a framework that is interoperable with the market standards. in today's world messaging...Read more...

  • CFU Scope is a free iPhone application built to help microbiologists count CFU (Colony-forming units). The application is released for iPhone years ago, but there is an Android edition in the final stage of development (according to the developers). CFU Scope is created by "mediXgraph"; a team which specialized in...Read more...

  • The challenge of matching precipitant (patients) for cancer trials is not easy nor simple. The current methods for patient recruitment for clinical trials result in failure [5]. Our topic of the day MatchMiner is designed to help researchers overcome this challenge. MatchMiner is an open-source computational platform with a specific...Read more...

  • Looking for a segmentation tool developed by radiologists for radiologists? Look no further than MedSeg. MedSeg is an online segmentation tool based on JavaScript that allows radiologists to segment radiological images directly in their web browser without the need to download, install or register. Hence the tool is completely browser...Read more...

  • The arrival of COVID-19 brought complex challenges worldwide. In Latin America, precisely in Brazil, the worst pandemic seen in a century challenges states, cities, and public health care management. Recently, the country surpassed China in the total number of confirmed deaths With cases expected to accelerate in Latin America’s...Read more...