# netron

**Repository Path**: xueyoo/netron

## Basic Information

- **Project Name**: netron
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-06-20
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README


<p align='center'><a href='https://github.com/lutzroeder/netron'><img width='400' src='.github/logo.png'/></a></p>

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`), **Darknet** (`.cfg`), **MXNet** (`.model`, `-symbol.json`), **ncnn** (`.param`) and **TensorFlow Lite** (`.tflite`).

Netron has experimental support for **TorchScript** (`.pt`, `.pth`), **PyTorch** (`.pt`, `.pth`), **Torch** (`.t7`), **Arm NN** (`.armnn`), **Barracuda** (`.nn`), **BigDL** (`.bigdl`, `.model`), **Chainer** (`.npz`, `.h5`), **CNTK** (`.model`, `.cntk`), **Deeplearning4j** (`.zip`), **MediaPipe** (`.pbtxt`), **ML.NET** (`.zip`), **MNN** (`.mnn`), **OpenVINO** (`.xml`), **PaddlePaddle** (`.zip`, `__model__`), **scikit-learn** (`.pkl`), **Tengine** (`.tmfile`), **TNN** (`.tnnproto`), **UFF** (`.uff`), **TensorFlow.js** (`model.json`, `.pb`) and **TensorFlow** (`.pb`, `.meta`, `.pbtxt`, `.ckpt`, `.index`).

<p align='center'><a href='https://www.lutzroeder.com/ai'><img src='.github/screenshot.png' width='800'></a></p>

## Install

**macOS**: [**Download**](https://github.com/lutzroeder/netron/releases/latest) the `.dmg` file or run `brew cask install netron`

**Linux**: [**Download**](https://github.com/lutzroeder/netron/releases/latest) the `.AppImage` file or run `snap install netron`

**Windows**: [**Download**](https://github.com/lutzroeder/netron/releases/latest) the `.exe` installer or run `winget install netron`

**Browser**: [**Start**](https://www.lutzroeder.com/ai/netron) the browser version.

**Python Server**: Run `pip install netron` and `netron [FILE]` or `import netron; netron.start('[FILE]')`.

## Models

Sample model files to download or open using the browser version:

 * **ONNX**: [squeezenet](https://raw.githubusercontent.com/onnx/tutorials/master/tutorials/assets/squeezenet.onnx) [[open](https://lutzroeder.github.io/netron?url=https://raw.githubusercontent.com/onnx/tutorials/master/tutorials/assets/squeezenet.onnx)]
 * **CoreML**: [exermote](https://raw.githubusercontent.com/Lausbert/Exermote/master/ExermoteInference/ExermoteCoreML/ExermoteCoreML/Model/Exermote.mlmodel) [[open](https://lutzroeder.github.io/netron?url=https://raw.githubusercontent.com/Lausbert/Exermote/master/ExermoteInference/ExermoteCoreML/ExermoteCoreML/Model/Exermote.mlmodel)]
 * **Darknet**: [yolo](https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolo.cfg) [[open](https://lutzroeder.github.io/netron?url=https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolo.cfg)]
 * **Keras**: [mobilenet](https://raw.githubusercontent.com/aio-libs/aiohttp-demos/master/demos/imagetagger/tests/data/mobilenet.h5) [[open](https://lutzroeder.github.io/netron?url=https://raw.githubusercontent.com/aio-libs/aiohttp-demos/master/demos/imagetagger/tests/data/mobilenet.h5)]
 * **MXNet**: [inception_v3](https://raw.githubusercontent.com/soeaver/mxnet-model/master/cls/inception/inception_v3-symbol.json) [[open](https://lutzroeder.github.io/netron?url=https://raw.githubusercontent.com/soeaver/mxnet-model/master/cls/inception/inception_v3-symbol.json)]
 * **TensorFlow**: [chessbot](https://raw.githubusercontent.com/srom/chessbot/master/model/chessbot.pb) [[open](https://lutzroeder.github.io/netron?url=https://raw.githubusercontent.com/srom/chessbot/master/model/chessbot.pb)]
 * **TensorFlow Lite**: [hair_segmentation](https://raw.githubusercontent.com/google/mediapipe/master/mediapipe/models/hair_segmentation.tflite) [[open](https://lutzroeder.github.io/netron?url=https://raw.githubusercontent.com/google/mediapipe/master/mediapipe/models/hair_segmentation.tflite)]
 * **TorchScript**: [traced_online_pred_layer](https://raw.githubusercontent.com/ApolloAuto/apollo/master/modules/prediction/data/traced_online_pred_layer.pt) [[open](https://lutzroeder.github.io/netron?url=https://raw.githubusercontent.com/ApolloAuto/apollo/master/modules/prediction/data/traced_online_pred_layer.pt)]
 * **Caffe**: [mobilenet_v2](https://raw.githubusercontent.com/shicai/MobileNet-Caffe/master/mobilenet_v2.caffemodel) [[open](https://lutzroeder.github.io/netron?url=https://raw.githubusercontent.com/shicai/MobileNet-Caffe/master/mobilenet_v2.caffemodel)]