Skip to main content

A Neural Network Visualiser as a Python package utilizing Matplotlib, visualizes plot coordinates from NeuralNetworkCoordinates for single-input, single-output neural networks. Aligned with Explainable AI, it offers concise insights, catering to researchers focused on understanding specific network architectures.

Project description

NNVisualiser

License

Overview

NNVisualiser is a powerful neural network visualization tool that leverages the NeuralNetworkCoordinates package to draw coordinates for various plots. This package offers an extensive collection of plots to facilitate the visualization and understanding of functional transformations at the Neuron, Layer, and Network levels. It serves as an invaluable tool for learning and studying the intricacies of neural networks.

Key Features

  • Multilevel Visualization: NNVisualiser provides plots that allow users to visualize and comprehend functional transformations at the Neuron, Layer, and Network levels.

  • Flow Plots for Data Transformation: The package includes flow plots, offering a comprehensive view of data transformation from input to activations, aiding in understanding the overall flow of information through the network.

  • Compatibility with 1D Networks: The current version is designed to work with lower-dimensional networks, specifically with 1D input and output. Future releases plan on supporting 2D and N-D input/ output neural networks, extending its utility to higher-dimensional network architectures.

  • Matplotlib Integration: Powered by Matplotlib, the package generates detailed and clear visualizations, aiding researchers and practitioners in understanding the internal dynamics of the neural network.

  • Explainable AI Alignment: Aligned with the principles of Explainable AI, NNVisualiser aims to provide concise insights, facilitating a deeper understanding of the intricacies of the neural network.

Installation

To install NNVisualiser, use pip:

pip install NNVisualiser

Usage

Check out the documentation for detailed information on how to use this package effectively.

Documentation

For complete documentation, please refer to the official documentation.

License

This package is provided under The Cat Standard License v1.0. See the LICENSE.txt file for details.

Issues

If you encounter any issues or have suggestions, please open an issue.

Authors

Caxton Emerald S, Vengattaraman T

By using this package, you agree to its terms and conditions.

© 2023 Caxton Emerald S

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

NNVisualiser-1.0.0.tar.gz (6.8 kB view details)

Uploaded Source

Built Distribution

NNVisualiser-1.0.0-py3-none-any.whl (7.1 kB view details)

Uploaded Python 3

File details

Details for the file NNVisualiser-1.0.0.tar.gz.

File metadata

  • Download URL: NNVisualiser-1.0.0.tar.gz
  • Upload date:
  • Size: 6.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/4.0.2 CPython/3.11.7

File hashes

Hashes for NNVisualiser-1.0.0.tar.gz
Algorithm Hash digest
SHA256 0986f9dcb6db986d426432a9cf78e7682b5d510107437290c70ea6a2c4e37c01
MD5 3a3b5d4f86df29ca9d4e9d5d0764ac59
BLAKE2b-256 a40177a5948f87df6c3605798529d2ca014300ba5446e456e45271788e034c31

See more details on using hashes here.

File details

Details for the file NNVisualiser-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for NNVisualiser-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6394b81979ba91dd00a26af02d7ca48b65fd3763c5d62c03b3848f158b036606
MD5 32d6da10ac4b94834d9c4d229e9d45cc
BLAKE2b-256 5436654bad3e4d13882819a7186f3d42f19019719b531e19a784ca46a56e8520

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page