misc/netron 4.1.9_1 DragonFly

Visualizer for neural network, deep learning, machine learning models

System: DragonFly
Repository: DPorts
Maintainer: [email protected] (as in FreeBSD)
License: APACHE20
Categories: misc, python
Package size: 932.9 KiB, 10060.6 KiB installed

Description

Netron is a viewer for neural network, deep learning and machine learning models. Netron supports: * ONNX (.onnx, .pb, .pbtxt), * Keras (.h5, .keras), * Core ML (.mlmodel), * Caffe (.caffemodel, .prototxt), * Caffe2 (predict_net.pb, predict_net.pbtxt), * MXNet (.model, -symbol.json), * TorchScript (.pt, .pth), * NCNN (.param), * TensorFlow Lite (.tflite). Netron has experimental support for: * PyTorch (.pt, .pth), * Torch (.t7), * CNTK (.model, .cntk), * Deeplearning4j (.zip), * PaddlePaddle (.zip, __model__), * Darknet (.cfg), * MNN (.mnn), * scikit-learn (.pkl), * ML.NET (.zip), * TensorFlow.js (model.json, .pb) and TensorFlow (.pb, .meta, .pbtxt).

In the other systems

System

Port

Version

DragonFly

misc/netron

4.1.9_1

FreeBSD

misc/netron

9.3.2

Install

Binary package:

pkg install netron

From DPorts:

cd /usr/dports/misc/netron && make install clean

Dependencies

Run dependencies 1

lang/python311

No port depends on this one.

Configuration

No options to configure.

Service scripts: none

Message after installing

You installed Netron: a neural network visualizer.

Netron displays graphical user interface through a web browser. It is
recommended that it is run through the electron (devel/electron6) browser
to be a standalone app.

In order to do this you can run it with this command line:
$ BROWSER=electron netron -b {model-file}