SunnyMirror/netron @ 5512c12709352b63c53b263a054d419c0cd0f943

Žiadny popis

3 Vetvy

Lutz Roeder 5512c12709 Update -operator.json files		8 rokov pred
.vscode	1a3875886e first commit	8 rokov pred
media	c58cf0a220 Update screenshot	8 rokov pred
setup	e4e4bc7743 Move electron-builder setup files to /setup	8 rokov pred
src	5512c12709 Update -operator.json files	8 rokov pred
tools	04e5563839 MXNet symbol.json support	8 rokov pred
.gitattributes	7f59d7662f Support variadic and control edges	8 rokov pred
.gitignore	aef727bc5d Add src/coreml.js	8 rokov pred
DEVELOPMENT.md	b2da722b5c Update DEVELOPMENT.md	8 rokov pred
LICENSE	0157c86a27 Update license	9 rokov pred
Makefile	3fc2eef9df Delay load protobuf and library scripts	8 rokov pred
README.md	5512c12709 Update -operator.json files	8 rokov pred
electron-builder.yml	04e5563839 MXNet symbol.json support	8 rokov pred
netron	eaf15f719b Fix Python scripts for 3.x	8 rokov pred
package.json	faa68487f7 Update to 1.6.2	8 rokov pred
setup.cfg	bb17ed372c All Python build outputs to ./build/python	8 rokov pred
setup.py	04e5563839 MXNet symbol.json support	8 rokov pred

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

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

Netron has experimental support for Caffe (.caffemodel), MXNet (-symbol.json) 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').

Sample model files you can download and open:

ONNX Models

Keras Models

CoreML Models

TensorFlow Lite Models

Caffe Models

MXNet Models

TensorFlow models