Sen descrición

Lutz Roeder 56cd7a0d91 Fix icon preview %!s(int64=7) %!d(string=hai) anos
.vscode 9c5d5ff93a Exclude node_modules and build in vscode %!s(int64=7) %!d(string=hai) anos
media c58cf0a220 Update screenshot %!s(int64=8) %!d(string=hai) anos
setup 7c4932220a Icon converter script %!s(int64=7) %!d(string=hai) anos
src 892eeb3a4e Update onnx-metadata.json %!s(int64=7) %!d(string=hai) anos
test b0435f9eac Fix Torch openface (#200) %!s(int64=7) %!d(string=hai) anos
tools 56cd7a0d91 Fix icon preview %!s(int64=7) %!d(string=hai) anos
.gitattributes 7f59d7662f Support variadic and control edges %!s(int64=8) %!d(string=hai) anos
.gitignore 67f817f0bf Add test/data to .gitignore %!s(int64=7) %!d(string=hai) anos
DEVELOPMENT.md 81fedddfd1 Add npm run server -- <args> shortcut %!s(int64=7) %!d(string=hai) anos
LICENSE 0157c86a27 Update license %!s(int64=9) %!d(string=hai) anos
Makefile 3fc1ffaf56 Fix Python package version %!s(int64=7) %!d(string=hai) anos
README.md cb87e2e532 Add .cntk extension support (#153) %!s(int64=7) %!d(string=hai) anos
electron-builder.yml b4f44f4329 Add Torch prototype (#200) %!s(int64=7) %!d(string=hai) anos
package.json daf16036bb Update to 2.7.0 %!s(int64=7) %!d(string=hai) anos
setup.cfg 2018518292 Move to setup.py console_scripts (#146) %!s(int64=7) %!d(string=hai) anos
setup.py b4f44f4329 Add Torch prototype (#200) %!s(int64=7) %!d(string=hai) anos

README.md

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

Netron supports ONNX (.onnx, .pb, .pbtxt), Keras (.h5, .keras), CoreML (.mlmodel), Caffe2 (predict_net.pb, predict_net.pbtxt), MXNet (.model, -symbol.json) and TensorFlow Lite (.tflite). Netron has experimental support for Caffe (.caffemodel, .prototxt), PyTorch (.pth), CNTK (.model, .cntk), scikit-learn (.pkl), TensorFlow.js (model.json, .pb) and TensorFlow (.pb, .meta, .pbtxt).

Install

macOS: Download the .dmg file or 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 -b [MODEL_FILE]. In Python run import netron and netron.start('model.onnx').

Download Models

Sample model files you can download and open:

ONNX Models: Inception v1, Inception v2, ResNet-50, SqueezeNet

Keras Models: resnet, tiny-yolo-voc

CoreML Models: MobileNet, Places205-GoogLeNet, Inception v3

TensorFlow Lite Models: Smart Reply 1.0 , Inception v3 2016

Caffe Models: BVLC AlexNet, BVLC CaffeNet, BVLC GoogleNet

Caffe2 Models: BVLC GoogleNet, Inception v2

MXNet Models: CaffeNet, SqueezeNet v1.1

TensorFlow models: Inception v3, Inception v4, Inception 5h