Skip to content

A home cooked, modular Multi Layer Perceptron with numpy only. Tensors and Jacobian matrices, no shorcuts.

Notifications You must be signed in to change notification settings

JBarmentlo/Multi-Layer-Perceptron-42

Repository files navigation

Multi Layer Perceptron

In this project I will implement a modular libray for feed forward deep learning models. Only numpy will be used.

How-To run it ?

You will need python 3.8 or more. The following code MUST be run from the root of the project tkinker must be installed on the system for the plots to function. Setup environnement:

python3.8 -m venv venv
source .env
pip install --upgrade pip
pip install -r requirements.txt

Train:

python src/train.py

Test:

python src/predict.py data/data.csv mymodel

About

A home cooked, modular Multi Layer Perceptron with numpy only. Tensors and Jacobian matrices, no shorcuts.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published