SunnyMirror/netron @ bbf5406c67cb23d461934f4a4e390cf5cf59d96c

説明なし

Lutz Roeder bbf5406c67 Update to 1.5.5		8 年前
.vscode	1a3875886e first commit	8 年前
media	c58cf0a220 Update screenshot	8 年前
setup	e4e4bc7743 Move electron-builder setup files to /setup	8 年前
src	d7b6c86003 Keras documentation rendering	8 年前
tools	d7b6c86003 Keras documentation rendering	8 年前
.gitattributes	7f59d7662f Support variadic and control edges	8 年前
.gitignore	aef727bc5d Add src/coreml.js	8 年前
DEVELOPMENT.md	b2da722b5c Update DEVELOPMENT.md	8 年前
LICENSE	0157c86a27 Update license	9 年前
Makefile	3fc2eef9df Delay load protobuf and library scripts	8 年前
README.md	bbf5406c67 Update to 1.5.5	8 年前
electron-builder.yml	f201be1d6e Fix CoreML file extension	8 年前
netron	3fc2eef9df Delay load protobuf and library scripts	8 年前
package.json	bbf5406c67 Update to 1.5.5	8 年前
setup.cfg	bb17ed372c All Python build outputs to ./build/python	8 年前
setup.py	7479baccd7 Add favicon to browser version	8 年前

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

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

Netron has experimental support for CoreML models (.mlmodel) and TensorFlow models (.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

TensorFlow Lite Models

CoreML Models

TensorFlow models