Keine Beschreibung

Lutz Roeder c58cf0a220 Update screenshot vor 8 Jahren
.vscode 1a3875886e first commit vor 8 Jahren
media c58cf0a220 Update screenshot vor 8 Jahren
setup e4e4bc7743 Move electron-builder setup files to /setup vor 8 Jahren
src 6fd706e65d Documentation button in px vor 8 Jahren
tools d50889a040 More colors vor 8 Jahren
.gitattributes 7f59d7662f Support variadic and control edges vor 8 Jahren
.gitignore ca42cf9505 Bug fixes and tf/tflite experiments vor 8 Jahren
LICENSE 0157c86a27 Update license vor 9 Jahren
README.md 82bb17c2ec Add Inception v3 to README.md vor 8 Jahren
package.json a8c596313e Update to 1.2.9 vor 8 Jahren
setup.cfg 7d9e677e20 Write .egg-info to /tmp vor 8 Jahren
setup.py 32febd7acb Experimental Keras H5 loader vor 8 Jahren

README.md

Netron is a viewer for neural network models. Netron loads ONNX models and TensorFlow Lite models and has experimental support for TensorFlow Graph and Saved Model files.

Install

macOS

Download the .dmg file or with Homebrew run brew cask install netron

Linux

Download the .AppImage or .deb file. The .AppImage needs to be made executable after download.

Windows

Download the .exe file.

Download Models

Below are a few model files you can download and open:

ONNX Models

TensorFlow Lite Models

TensorFlow models

Install Python Model Server

To run Netron in a web browser, install the Python web server using pip:

pip install netron

Launch the model server:

netron my_model.onnx

To serve a model from Python code:

import netron

netron.serve_file('my_model.onnx')