Introducing the visualization tool Netron

Netron is a visualization tool for neural networks, deep learning, and machine learning models.You can generate descriptive visualizations of the model's architecture.The source code is at: https://github.com/lutzroeder/netron , mainly implemented by the JavaScript language, the license is MIT, and the latest release version is 5.9.6.

   Netron is a cross-platform tool that works on Linux, Windows andRuns on Macand supports multiple frameworks and formats.Netron supports ONNX, TensorFlow Lite, Caffe, Keras, Darknet, PaddlePaddle, ncnn, MNN, Core ML, RKNN, MXNet, MindSpore Lite, TNN, Barracuda, Tengine, CNTK, TensorFlow.js, Caffe2 and UFF.It also experimentally supports PyTorch, TensorFlow, TorchScript, OpenVINO, Torch, Vitis AI, kmodel, Arm NN, BigDL, Chainer, Deeplearning4j, MediaPipe, ML.NET, and scikit-learn.

   Installing Netron:

    (1).windows: from https://github.com/lutzroeder/netron/releases/tag/v5.9.6 Download Netron-Setup-5.9.6.exe, double-click to install, after installation, a Netron icon will be generated on the desktop, double-click the icon to open, the interface is as shown below:

(2) Linux: from https://github.com/lutzroeder/netron/releases/tag/v5.9.6 Download Netron-5.9.6.AppImage and add execute permission to this file: chmod u+x Netron-5.9.6.AppImage , then double-click the file to open it.

   Example: Open an onnx model, such as Lenet-5.onnx (from: https://blog.csdn.net/fengbingchun/article/details/126072998 ), click the Open Model... button, the result is as shown in the following figure: Click each box on the left (similar to the layer type name), and the box properties will be displayed on the rightother information