Bridge the gap between algorithms and implementations of deep learning


Chainer supports CUDA computation. It only requires few lines of codes to leverage a GPU. It also runs on multiple GPUs with a little effort.


Chainer supports various network architectures including feed-forward nets, convnets, recurrent nets and recursive nets. It also supports per-batch architectures.


Forward computation can include any control flow statements of Python without lacking ability of backpropagation. It makes codes intuitive and easy to debug.

Quick Start

Install Chainer:

pip install chainer

Run the MNIST example:

tar xzf v1.17.0.tar.gz
python chainer-1.17.0/examples/mnist/

Learn more from the official documentation.