Chainer – A flexible framework of neural networks

Welcome to the Chainer documentation.

• Certified 99% Python code!
• Define-by-run approach for flexibility and understandable errors
• Standard Numpy syntax
• NVIDIA GPU acceleration, thanks to CuPy

Chainer Documents

• Installation
  • Recommended Environments
  • Requirements
  • Install Chainer
  • Uninstall Chainer
  • Upgrade Chainer
  • Reinstall Chainer
  • Run Chainer with Docker
  • FAQ
• Guides
  • Define-by-Run
  • Variables and Derivatives
  • Links
  • Define your own function
  • Creating Models
  • Optimizer
  • Trainer
  • Trainer Extensions
  • Using GPU(s) in Chainer
  • Type Checks
  • Serializers – saving and loading
  • Customize your own logging
• Neural Net Examples
  • MNIST using Trainer
  • MNIST with a Manual Training Loop
  • Convolutional Network for Visual Recognition Tasks
  • Recurrent Nets and their Computational Graph
  • RNN Language Models
  • Word2Vec: Obtain word embeddings
  • Write a Sequance to Seqeunce (seq2seq) Model
• Reference
  • Variable and Parameter
  • Functions
  • Link and Chains
  • Optimizers
  • Weight Initializers
  • Training Tools
  • Datasets
  • Iterator
  • Serializers
  • Utilities
  • Configuring Chainer
  • Debug Mode
  • Visualization of Computational Graph
  • Caffe Reference Model Support
  • Caffe Model Export Support
  • Assertion and Testing

Other

• API Compatibility Policy
• Contribution Guide
• Tips and FAQs
• Upgrade Guide
• Comparison with Other Frameworks
• License

Indices and tables

• Index
• Module Index
• Search Page

Community

• Slack Chat
• Forums
• Examples in Awesome Chainer