Netron – 网络可视化
Netron – 网络可视化
Netron supports 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) and TensorFlow Lite (.tflite).
Netron has experimental support for 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), Chainer, (.npz, .h5), TensorFlow.js (model.json, .pb) and TensorFlow (.pb, .meta, .pbtxt).
1. Install
macOS: Download the .dmg file or run brew cask install netron
Linux: Download the .AppImage or .deb file.
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]').
2. Download Models
Sample model files to download and open:
- ONNX: resnet-18 https://s3.amazonaws.com/onnx-model-zoo/resnet/resnet18v1/resnet18v1.onnx
- Keras: tiny-yolo-voc https://github.com/hollance/YOLO-CoreML-MPSNNGraph/raw/master/Convert/yad2k/model_data/tiny-yolo-voc.h5
- CoreML: faces_model https://github.com/NovaTecConsulting/FaceRecognition-in-ARKit/files//faces_model.mlmodel.zip
- TensorFlow Lite: smartreply https://storage.proxy.ustclug.org/download.tensorflow.org/models/tflite/smartreply_1.0_2017_11_01.zip
- MXNet: inception_v1 https://s3.amazonaws.com/model-server/models/onnx-inception_v1/inception_v1.model
- Caffe: mobilenet_v2 https://raw.githubusercontent.com/shicai/MobileNet-Caffe/master/mobilenet_v2.caffemodel
- TensorFlow: inception_v3 https://storage.proxy.ustclug.org/download.tensorflow.org/models/inception_v3_2016_08_28_frozen.pb.tar.gz
3. Browser
https://lutzroeder.github.io/netron/
发布者：全栈程序员-站长，转载请注明出处：https://javaforall.net/176806.html原文链接：https://javaforall.net
