A simple neural network library with only numpy as dependency
Project description
Handmade NeuralNetwork lib
📝 Description
This is a handmade neural network library, made in python, using numpy as the only dependency.
I made it to challenge myself and to learn more about neural networks, how they work in depth.
The big part of this project was made in 4 hours and a half. The save and load features, and the binary classification support were added later.
I intend to improve the neural networks and add more features in the future.
📦 Features
- Many activation functions (sigmoid, tanh, relu, leaky relu, softmax, linear, elu, selu) 📈
- Many loss functions (mean squared error, mean absolute error, categorical crossentropy, binary crossentropy, huber loss) 📉
- Many optimizers (sgd, momentum, rmsprop, adam) 📊
- Supports binary classification, multiclass classification and regression 📖
- Save and load models 📁
- Simple to use 📚
⚙️ Installation
You can install the library using pip:
pip install neuralnetlib
💡 How to use
See this file for a simple example of how to use the library. More examples in this folder.
You are free to tweak the hyperparameters and the network architecture to see how it affects the results.
I used the MNIST dataset to test the library, but you can use any dataset you want.
📜 Output of the example file
Here is an example with Tkinter:
Here, I decided to print the first 10 predictions and their respective labels to see how the network is performing.
✍️ Authors
- Marc Pinet - Initial work - marcpinet
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
Built Distribution
Hashes for neuralnetlib-1.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 35b87d67d85e9b9bc835d994c6d85591f21d72e5489bb973da46bbd670737c31 |
|
MD5 | 3e9cda64c3b2ff378a64c1e0b6c7c6b3 |
|
BLAKE2b-256 | 6a5b260e4f4dddb8057e7d4e26eb8643bc283f428977a05ea9503aa4015d2335 |