Lutz Roeder
05761e1a62
Fix lint issues
|
пре 6 година | |
|---|---|---|
| .vscode | пре 7 година | |
| media | пре 6 година | |
| setup | пре 6 година | |
| src | пре 6 година | |
| test | пре 6 година | |
| tools | пре 6 година | |
| .eslintrc.json | пре 6 година | |
| .gitattributes | пре 8 година | |
| .gitignore | пре 7 година | |
| DEVELOPMENT.md | пре 6 година | |
| LICENSE | пре 9 година | |
| Makefile | пре 6 година | |
| README.md | пре 6 година | |
| electron-builder.yml | пре 6 година | |
| package.json | пре 6 година | |
| setup.cfg | пре 6 година | |
| setup.py | пре 6 година |
README.md
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), MXNet (.model, -symbol.json), TorchScript (.pt, .pth), NCNN (.param) and TensorFlow Lite (.tflite).
Netron has experimental support for PyTorch (.pt, .pth), Torch (.t7), CNTK (.model, .cntk), Deeplearning4j (.zip), PaddlePaddle (.zip, __model__), Darknet (.cfg), scikit-learn (.pkl), TensorFlow.js (model.json, .pb) and TensorFlow (.pb, .meta, .pbtxt).
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]').
Download Models
Sample model files to download and open:
- ONNX: resnet-18
- Keras: tiny-yolo-voc
- CoreML: faces_model
- TensorFlow Lite: smartreply
- MXNet: inception_v1
- Caffe: mobilenet_v2
- TensorFlow: inception_v3