DeLU

DeLU is a general-purpose library for PyTorch users. DeLU simplifies training loops, facilitates reproducibility, helps with models evaluation and other typical Deep Learning tasks. DeLU is a toolbox, not a framework:

• your training loop stays the same (regardless of whether it is powered by a simple Python loop or by a specialized framework)

• you can start by using any single tool you need, there is no “central concept”

• you can replace tools from DeLU with custom solutions at any moment

NOTE: DeLU is tested (and battle-tested in research projects), but the interface is not stable yet, so backward-incompatible changes in future releases are possible.

Overview

• Website

• Learn DeLU

• Classification task example (MNIST)

• Code

Installation

pip install delu

Dependencies: see pyproject.toml in the repository.

How to contribute

• Help to resolve issues

• Report bugs and issues

• Post questions, ideas and feedback

If your contribution includes pull requests, see CONTRIBUTING.md

How to cite

@article{gorishniy2020delu,
    title={DeLU: a Lightweight Toolbox for Deep Learning Researchers and Practitioners},
    author={Yury Gorishniy},
    journal={GitHub},
    volume={Yura52/delu},
    url={https://github.com/Yura52/delu},
    year={2020},
}

---

Indices and Tables

• Index

• Module Index