eve-mli: making learning interesting

Eve is an open-source deep learning framework used to devise and modify a network architecture in a flexible and interesting way.

We provide several jupyter notebooks under ./examples to demonstrate how to build various network structures.

The most features of Eve are that: it provides a well defined framework which make your network structure can be upgraded along with the learning of weights.

Any contributions to Eve is welcome!

Installation

Install from PyPI:

pip install eve-mli
# pip install git+git@github.com:densechen/eve-mli.git

Developers can download and install the latest version from:

GitHub:

git clone https://github.com/densechen/eve-mli.git
cd eve-mli
python setup.py install

Gitee:

git clone https://gitee.com/densechen/eve-mli.git
cd eve-mli
python setup.py install

Vailidate installation:

python -c "import eve; print(eve.__version__)"

About the project

The documentation can be found here. (Auto-building of documentation fails sometimes, you can build it manually via cd docs; make html).

The project remains in development. We encourage more volunteers to come together!

The first official version of eve-mli will be released very soon.

About the authors

Dengsheng Chen Master @ National University of Defense Technology densechen@foxmail.com

References

PyTorch

stable-baselines3

spikingjelly

Model-Compression-Deploy