Metadata-Version: 2.4
Name: orange3-imagenets
Version: 0.0.2
Summary: A collection of Orange3 widgets for training and applying neural networks to images
Author-email: Chris Lee <github@chrislee.dhs.org>
License: CC-BY-NC-SA-4.0
Project-URL: Homepage, https://github.com/chrislee35/orange3-imagenets
Keywords: orange3 add-on
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3 :: Only
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: Orange3>=3.39.0
Requires-Dist: orange-canvas-core>=0.1.28
Requires-Dist: orange-widget-base>=4.20.0
Requires-Dist: Orange3-ImageAnalytics>=0.13.0
Requires-Dist: opencv-python>=4.12
Requires-Dist: keras>=3.10.0
Requires-Dist: tf_keras>=2.19.0
Provides-Extra: test
Requires-Dist: coverage; extra == "test"
Provides-Extra: doc
Requires-Dist: sphinx; extra == "doc"
Requires-Dist: recommonmark; extra == "doc"
Requires-Dist: sphinx_rtd_theme; extra == "doc"
Dynamic: license-file

# orange3-imagenets

This provides a collection of widgets for training and applying neural networks to images.

## Installation

Within the Add-ons installer, click on "Add more..." and type in orange3-imagenets

## Widgets

### ImageNet Builder

![Basic training workflow](imgs/training-workflow.png)

You can build a Keras model by adding layers and moving them around.

![Simple CNN with Dense(2) output](imgs/simple-cnn-builder.png)

![Training graph](imgs/training-graph.png)

![Saving the ImageNet model](imgs/save-model.png)

### Using the ImageNet

![Basic classification workflow](imgs/classify-workflow.png)

Load the image net from a saved file.

![Loading the model](imgs/load-model.png)

![Viewing the classification results](imgs/classified-data-table.png)


