Deep Learning Library From Scratch

About

This project is a tool for creating various kinds of neural networks. All code is written in Python.

The purpose of this project is not to produce as optimized and computationally effective tool as possible. The main goal of the project is to get some expirience in building libraries and writing deep learning related Python code, understand everything much better and basically Learn.

I repeat, this idea is used exclusively for educational purposes.

Table of Content

1. layers.py

• Dense

2. loss.py

• Mean Squared Error
• Cross Entropy

3. nn.py

• Linear
• Sigmoid
• Tanh
• ReLU
• ELU
• Softmax

4. optimizer.py

• Stochastic Gradient Descent

5. tensor.py

• This one just reshapes everything.

6. train.py

• This one just assembles everything and does forward and backward propagation.

Installation

git clone https://github.com/mishazakharov/DL-library
cd DL-library

Contact

If you want to work on this together or just feeling social, feel free to contact me here. And I am also available at this(misha_zakharov96@mail.ru) and this(vorahkazmisha@gmail.com) email addresses! Feel free to give me any advice. 👍