Compact implementation of keras made for educational purposes. Written in python using numpy
Reason this release was yanked:
New version is available
Project description
nano-keras
Overview
nano-keras is a compact implementation of Keras using only Python and NumPy. It's designed with the primary aim of deepening understanding about neural network fundamentals and their implementation at a lower level. While it might not match the speed or feature-rich capabilities of Keras, it serves as an educational project to explore the inner workings of neural networks
Key Features
- Simplicity: Built using fundamental Python and NumPy functionalities, emphasizing simplicity and readability
- Educational: Intended as a learning tool to understand neural network components at a lower level
- Customization: Allows for tinkering and understanding the core mechanics of neural network operations
Instalation
You will be able to download it from PyPI after around 12th of Noveber and I will explain how to do it then
Documentation
Currently, the documentation is in progress and is expected to be released along with the first version on November 12th. It will cover:
- Installation instructions
- Usage examples
- Explanation of classes and methods
License
This project is licensed under the MIT License - see the LICENSE file for details
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nano-keras-0.9.0.tar.gz
(18.8 kB
view hashes)
Built Distribution
nano_keras-0.9.0-py3-none-any.whl
(20.3 kB
view hashes)
Close
Hashes for nano_keras-0.9.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | cb9a98ddd608fd5e11d1cef3e8169e08d35c86e1e4355710314d0e55e22cc84e |
|
MD5 | 66015e439ab9371c530a7977b4bc8cb6 |
|
BLAKE2b-256 | 8c78262a830c21629082154e60137db3973f7b7d7c395b22e61b795d63e3cf6b |