// //
Chainer: A flexible framework for neural networks

Bridge the gap between algorithms and implementations of deep learning


Chainer supports CUDA computation. It only requires a few lines of code to leverage a GPU. It also runs on multiple GPUs with 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 the ability of backpropagation. It makes code intuitive and easy to debug.

Quick Start

Install Chainer:

pip install chainer

Run the MNIST example:

wget https://github.com/chainer/chainer/archive/v4.1.0.tar.gz
tar xzf v4.1.0.tar.gz
python chainer-4.1.0/examples/mnist/train_mnist.py

Learn more from the official documentation.

Extension Libraries

An extension package that enables multi-node distributed deep learning.
A library that implements various state-of-the-art deep reinforcement algorithms.
A collection of tools to train and run neural networks for computer vision tasks.


Introduction to Chainer

Old Slides

Companies supporting Chainer