SunnyMirror/netron @ ce15c4c096698136d5c8acda8b7acd78dc4f4bbb

Nessuna descrizione

427 Commit

Lutz Roeder ce15c4c096 Update to 1.5.8		8 anni fa
.vscode	1a3875886e first commit	8 anni fa
media	c58cf0a220 Update screenshot	8 anni fa
setup	e4e4bc7743 Move electron-builder setup files to /setup	8 anni fa
src	44011c6337 Caffe experiments	8 anni fa
tools	44011c6337 Caffe experiments	8 anni fa
.gitattributes	7f59d7662f Support variadic and control edges	8 anni fa
.gitignore	aef727bc5d Add src/coreml.js	8 anni fa
DEVELOPMENT.md	b2da722b5c Update DEVELOPMENT.md	8 anni fa
LICENSE	0157c86a27 Update license	9 anni fa
Makefile	3fc2eef9df Delay load protobuf and library scripts	8 anni fa
README.md	bbf5406c67 Update to 1.5.5	8 anni fa
electron-builder.yml	f201be1d6e Fix CoreML file extension	8 anni fa
netron	eaf15f719b Fix Python scripts for 3.x	8 anni fa
package.json	ce15c4c096 Update to 1.5.8	8 anni fa
setup.cfg	bb17ed372c All Python build outputs to ./build/python	8 anni fa
setup.py	7479baccd7 Add favicon to browser version	8 anni fa

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