index.rst

Chainer -- A flexible framework of neural networks

Chainer is a powerful, flexible and intuitive deep learning framework.

• 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.

Note

As announced, Chainer is under the maintenance phase and further development will be limited to bug-fixes and maintenance only.

.. toctree::
   :maxdepth: 2
   :caption: Tutorials

   glance
   guides/index

.. toctree::
   :maxdepth: 2
   :caption: Examples

   examples/index
   Colab Notebook Examples <https://chainer-colab-notebook.readthedocs.io/en/latest/>
   Awesome Chainer <https://github.com/chainer-community/awesome-chainer>

.. toctree::
   :maxdepth: 2
   :caption: References

   reference/index
   install
   chainerx/index
   chainermn/index
   onnx_chainer/index

.. toctree::
   :maxdepth: 1
   :caption: Other

   compatibility
   contribution
   tips
   performance
   upgrade
   license

Indices and tables

• :ref:`genindex`
• :ref:`modindex`
• :ref:`search`

.. toctree::
   :maxdepth: 1
   :caption: Community

   Slack Chat <https://bit.ly/go-chainer-slack>
   Forums <https://groups.google.com/forum/#!forum/chainer>