Skip to content

Latest commit

 

History

History
19 lines (14 loc) · 1.07 KB

File metadata and controls

19 lines (14 loc) · 1.07 KB

nets

This project aims to serve as a basic implementation of PyTorch for educational purposes. It includes functionality for creating and training deep learning models, written entirely in Python.

Installation & Configuration

You don't have to do anything special. Just clone the repository, add it to your project, and try it out!

Modules

Tensor

Contains all the code for creating our implementation of the PyTorch tensor class, which is a general list of any dimension to which backpropagation applies.

NN

Contains all the deep learning layers needed to create various AI models. So far, we have implemented:

  • Linear: The linear layer of logistic regresion.

Additional Notes

This project is written in Python without any parallelization, so the performance of the modules is not comparable to PyTorch. Its sole purpose is to serve as a valuable tool for understanding how deep learning models work under the hood.

Contributing

Contributions are welcome! Please open an issue or submit a pull request for any improvements, suggestions, or addition to our cause.