DeLU is a general-purpose PyTorch library that simplifes development and training of deep learning models. DeLU is a toolbox, not a framework:

• DeLU provides functions and classes that facilitate training loops, reproducibility, tensor manipulations and other typical aspects of deep learning projects.
• there is no need to "rebuild your project around DeLU": you can start using DeLU by picking individual tools that you find helpful.

DeLU is tested and battle-tested in research projects. The public API is still evolving, and backward-incompatible changes are possible.

• Website
• Learn DeLU
• Classification task example (MNIST)
• Code

pip install delu

Dependencies: see pyproject.toml in the repository.

• Help to resolve issues
• Report bugs and issues
• Post questions, ideas and feedback

If your contribution includes pull requests, see CONTRIBUTING.md

@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},
}