Chainer Info

What is Chainer?

Chainer is a flexible framework for neural networks. One major goal is flexibility, so it must enable us to write complex architectures simply and intuitively.

More info here

ref Chainer.wiki - Chainer Wiki

Table of Contents

• Tutorials
• Models/Projects
• Examples
• Libraries
• Videos
• Papers
• Blog posts
• Community
• Books

Tutorials

• [Chainer Tutorial Offical document]http://docs.chainer.org/en/latest/tutorial/index.html) - Chainer Tutorial Offical document

Hands-on

• hido/chainer-handson - Chainer Hands-on
• iwiwi/chainer-handson - Chainer Hands-on(JP CPU only)

Models/Projects

Preferred Networks official

• ChainerRL - ChainerRL is a deep reinforcement learning library built on top of Chainer.
• ChainerCV - Versatile set of tools for Deep Learning based Computer Vision
• Paint Chainer - Paints Chainer is line drawing colorizer using chainer.

Chainer External Examples

Preferred NetWorks Research

• LSGAN - Least Squares Generative Adversarial Network implemented in Chainer
• Chainer-gogh - Implementation of "A neural algorithm of Artistic style"
• Chainer Graph CNN - Chainer implementation of 'Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering' (https://arxiv.org/abs/1606.09375)
• chainer-segnet - SegNet implementation & experiments in Chainer
• chainer-pix2pix - chainer implementation of pix2pix

Examples

Method	Codes
Cifar10	mitmul/chainer-cifar10
Deep pose	mitmul/DeepPose
Deep Q-Network (DQN)	ugo-nama-kun/DQN-chainer
Image super-resolution	mrkn/chainer-srcnn
Image super-resolution	Hi-king/chainer_superresolution
Overfeat	darashi/chainer-example-overfeat-classify
Recurrent neural network (RNN)	yusuketomoto/chainer-char-rnn
Variational autoencoder (VAE)	RyotaKatoh/chainer-Variational-AutoEncoder
VGG	mitmul/chainer-imagenet-vgg
Machine Translation, word segmentation, and language model	odashi/chainer_examples
ResNet	yasunorikudo/chainer-ResNet
DenseNet	yasunorikudo/chainer-DenseNet
ResDrop	yasunorikudo/chainer-ResDrop
Convolution Filter Visualization	mitmul/chainer-conv-vis
Siamese Network	mitmul/chainer-siamese
Support Vector Machine (SVM)	mitmul/chainer-svm
Fast R-CNN	mitmul/chainer-fast-rcnn
Fast R-CNN	apple2373/chainer-simple-fast-rnn
Faster R-CNN	mitmul/chainer-faster-rcnn
Group Equivariant Convolutional Neural Networks	tscohen/GrouPy
Perceptual Losses for Real-Time Style Transfer and Super-Resolution	yusuketomoto/chainer-fast-neuralstyle
illustration2vec	rezoo/illustration2vec
StyleNet (A Neural Algorithm of Artistic Style)	apple2373/chainer_stylenet
StyleNet (A Neural Algorithm of Artistic Style)	mattya/chainer-gogh
Show and Tell	apple2373/chainer_caption_generation
Deep Predictive Coding Networks	chainer-prednet
BinaryNet	hillbig/binary_net
Variational Auto-Encoder (VAE), Generative Adversarial Nets (GAN), VAE-GAN	stitchfix/fauxtograph
Generative Adversarial Nets (GAN)	rezoo/data.py
Deep Convolutional Generative Adversarial Network (DCGAN)	mattya/chainer-DCGAN
Fluid simulation	mattya/chainer-fluid
Convolutional Autoencoder	ktnyt/chainer_ca.py
RNN Language Model	odashi/chainer_rnnlm.py
Neural Encoder-Decoder Machine Translation	odashi/chainer_encoder_decoder.py
LSTM variants	prajdabre/chainer_examples
Stacked Denoising Autoencoder	tochikuji/chainer-libDNN
Chainer Hands-on	hido/chainer-handson
Recurrent Attention Model	masaki-y/ram
Fully Convolutional Networks	wkentaro/fcn
Generative Adversarial Networks with Denoising Feature Matching	hvy/chainer-gan-denoising-feature-matching
Visualizing and Understanding Convolutional Networks	hvy/chainer-visualization
Chainer GAN Trainer	hvy/chainer-gan-trainer
QRNN	jekbradbury/qrnn.py
Deep Feature Interpolation for Image Content Changes	dsanno/chainer-dfi
SegNet	mitmul/chainer-segnet
WGAN	musyoku/wasserstein-gan
IMSAT	weihua916/imsat
LSGAN	musyoku/LSGAN

Tools and extensions

• Deel; A High level deep neural network description language
• DEEPstation
• chainer_imagenet_tools
• scikit-chainer
• chainer-libDNN

Videos

Only Japanese

• Chainer の Trainer 解説とNStepLSTM について Published on Mar 15, 2017
• Chainer Meetup #04 Published on Feb 23, 2017
• 1014：深層学習フレームワークChainerの導入と化合物活性予測への応用 Published on Dec 2, 2015

Papers

Conference	Paper title	Codes	comments
arXiv only	Temporal Generative Adversarial Nets
arXiv only	Reasoning with Memory Augmented Neural Networks for Language Comprehension
arXiv only	PMI Matrix Approximations with Applications to Neural Language Modeling
arXiv only	Neural Tree Indexers for Text Understanding	NTI
arXiv only	Neural Semantic Encoders
arXiv only	Networked Intelligence: Towards Autonomous Cyber Physical Systems
arXiv only	Modeling the dynamics of human brain activity with recurrent neural networks
arXiv only	A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast
arXiv only	Convolutional Neural Networks using Logarithmic Data Representation
CoNLL 2016	context2vec: Learning Generic Context Embedding with Bidirectional LSTM
CoNLL 2016	Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec
ECCV 2016 Workshop	Deep Impression: Audiovisual Deep Residual Networks for Multimodal Apparent Personality Trait Recognition		“3rd place in Looking at People ECCV Challenge”
ECCV 2016 Workshop	Learning Joint Representations of Videos and Sentences with Web Image Search
EMNLP 2016	Incorporating Discrete Translation Lexicons into Neural Machine Translation
EMNLP 2016	Controlling Output Length in Neural Encoder-Decoders
EMNLP 2016	Insertion Position Selection Model for Flexible Non-Terminals in Dependency Tree-to-Tree Machine Translation
ICLR 2016	Learning Representations Using Complex-Valued Nets
ICLR 2017 under review	Dynamic Coattention Networks For Qustion Answering
ICLR 2017 under review	SqueezeNet: AlexNet-level Accuracy with 50x Fewer Parameters and < 0.5MB Model Size
ICLR 2017 under review	Quasi-Recurrent Neural Networks
ICLR 2017	Steerable CNNs		Chainer is not referred in the paper, but the authors kindly informed us.
NIPS 2016 Workshop	f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
OPT 2016	QSGD: Randomized Quantization for Communication-Optimal Stochastic Gradient Descent
PETRA 2016	Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition
PASJ 2016	Machine-learning Selection of Optical Transients in Subaru/Hyper Suprime-Cam Survey		PASJ: Publications of the Astronomical Society of Japan
Space Weather 2016	A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast
NAACL 2016	Dynamic Entity Representation with Max-pooling Improves Machine Reading
SemEval 2016	Feature-based Model versus Convolutional Neural Network for Stance Detection
ACL 2016	Cross-Lingual Image Caption Generation
ACL 2016	Composing Distributed Representations of Relational Patterns
ACL 2016	Generating Natural Language Descriptions for Semantic Representations of Human Brain Activity
WMT 2016	MetaMind Neural Machine Translation System for WMT 2016
ICML 2016	Group Equivariant Convolutional Networks	GitHub	Chainer is not referred in the paper, but the authors kindly informed us.

Official announcements

• Chainer document - An introduction to Chainer
• Chainer blogs

Community

• Introduction to Chainer: Neural Networks in Python
• The DIY Guide to Chainer
• CHAINER CHARACTER EMBEDDINGS
• A Fontastic Voyage: Generative Fonts with Adversarial Networks

Community

Global

• @ChainerOfficial on Twitter
• Mailing List
• Slack

Japan

• @ChainerJP on Twitter
• Mailing List
• Slack
• connpass

Books

• Chainerによる実践深層学習 by 新納浩幸