Nav apraksta

Lutz Roeder 71e9f3b5de Caffe tensor support 8 gadi atpakaļ
.vscode 1a3875886e first commit 8 gadi atpakaļ
media c58cf0a220 Update screenshot 8 gadi atpakaļ
setup e4e4bc7743 Move electron-builder setup files to /setup 8 gadi atpakaļ
src 71e9f3b5de Caffe tensor support 8 gadi atpakaļ
tools b6ae9f8639 Caffe2 clone and protobuf generator script 8 gadi atpakaļ
.gitattributes 7f59d7662f Support variadic and control edges 8 gadi atpakaļ
.gitignore aef727bc5d Add src/coreml.js 8 gadi atpakaļ
DEVELOPMENT.md b2da722b5c Update DEVELOPMENT.md 8 gadi atpakaļ
LICENSE 0157c86a27 Update license 9 gadi atpakaļ
Makefile 3fc2eef9df Delay load protobuf and library scripts 8 gadi atpakaļ
README.md 71e9f3b5de Caffe tensor support 8 gadi atpakaļ
electron-builder.yml 92a56d6146 Add Caffe file extension 8 gadi atpakaļ
netron eaf15f719b Fix Python scripts for 3.x 8 gadi atpakaļ
package.json 9246fc9147 Update to 1.5.9 8 gadi atpakaļ
setup.cfg bb17ed372c All Python build outputs to ./build/python 8 gadi atpakaļ
setup.py c6af1a8833 Add Caffe to browser and Python server 8 gadi atpakaļ

README.md

Netron is a viewer for neural network and machine learning models.

Netron supports ONNX (.onnx, .pb), Keras (.keras, .h5), CoreML (.mlmodel) and TensorFlow Lite (.tflite).

Netron also has has experimental support for Caffe (.caffemodel) and TensorFlow (.pb, .meta).

Install

macOS

Download the .dmg file or with Homebrew 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 [MODEL_FILE].
Serve a model in Python using import netron; netron.serve_file('my_model.onnx').

Download Models

Sample model files you can download and open:

ONNX Models

Keras Models

TensorFlow Lite Models

CoreML Models

TensorFlow models