Brak opisu

Lutz Roeder bb17ed372c All Python build outputs to ./build/python 8 lat temu
.vscode 1a3875886e first commit 8 lat temu
media c58cf0a220 Update screenshot 8 lat temu
setup e4e4bc7743 Move electron-builder setup files to /setup 8 lat temu
src 627ecb01fb Remove --optimize from python server 8 lat temu
tools 627ecb01fb Remove --optimize from python server 8 lat temu
.gitattributes 7f59d7662f Support variadic and control edges 8 lat temu
.gitignore ca42cf9505 Bug fixes and tf/tflite experiments 8 lat temu
LICENSE 0157c86a27 Update license 9 lat temu
Makefile 52224d0d8d Update to 1.3.8 8 lat temu
README.md 1348b85e99 Update README.md 8 lat temu
electron-builder.yml 52224d0d8d Update to 1.3.8 8 lat temu
netron bb17ed372c All Python build outputs to ./build/python 8 lat temu
package.json 52224d0d8d Update to 1.3.8 8 lat temu
setup.cfg bb17ed372c All Python build outputs to ./build/python 8 lat temu
setup.py 627ecb01fb Remove --optimize from python server 8 lat temu

README.md

Netron is a viewer for neural network models.

Netron loads ONNX models (.onnx or .pb), Keras models (.keras, .h5 or .json) and TensorFlow Lite models (.tflite) and has experimental support for TensorFlow models (.pb and .meta).

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')