Home

The Microsoft Cognitive Toolkit

The Microsoft Cognitive Toolkit - CNTK - is a unified deep-learning toolkit by Microsoft Research. This video provides a high-level view of the toolkit.

It can be included as a library in your Python or C++ programs, or used as a standalone machine learning tool through its own model describtion language (BrainScript).

CNTK supports 64-bit Linux or 64-bit Windows operating systems. To install you can either choose pre-compiled binary packages, or compile the Toolkit from the source provided in Github.

Here are a few pages to get started:

• Setting up CNTK on your machine
• Tutorials, Examples, etc..
  • Try the tutorials on Azure Notebooks with pre-installed CNTK
• The CNTK Library APIs
  • Using CNTK from Python
  • Using CNTK from C++
• CNTK as a machine learning tool through [BrainScript](./Using CNTK with BrainScript)
• How to contribute to CNTK
• Give us feedback through these channels.

Note to search the pages of this Wiki, in the search box, type: Language:Markdown yourSearchText

This Wiki is the most up-to-date information about the Microsoft Cognitive Toolkit. For more background refer to the tutorials provided. A general introduction to computational networks and the core algorithms in CNTK, or to cite the work, please refer to the Microsoft Technical Report MSR-TR-2014-112: ["An Introduction to Computational Networks and the Computational Network Toolkit"] (http://research.microsoft.com/apps/pubs/?id=226641). The source of this report is in the Git repository folder.
It is updated less frequently and shouldn't be used the most up-to-date source of information.

What's New

2017-03-15. V 2.0 Beta 15 Release
Highlights of this Release:

• • Added support for TensorBoard output in BrainScript. Read more here.
• Learners can now be implemented in pure Python by means of UserLearners. Read more here.
• New debugging helpers: dump_function(), dump_signature().
• Tensors can be indexed using advanced indexing. E.g. x[[0,2,3]] would return a tensor that contains the first, third and fourth element of the first axis.
• Significant updates in the Layers Library of Pythin API. See Release Notes for detailed description.
• Updates and new examples in C# API.
• Various bug fixes.

See more in the Release Notes.
Get the Release from the CNTK Releases page.

2017-02-28. V 2.0 Beta 12 Release available at Docker Hub
CNTK V 2.0 Beta 12 Runtime packages are now available as Public Images at Docker Hub.
See more on CNTK as Docker Images in this Wiki article.

2017-02-23. V 2.0 Beta 12 Release
Highlights of this Release:

• New and updated features: new activation functions, support of Argmax and Argmin, improved performance of numpy interop, new functionality of existing operators, and more.
• CNTK for CPU on Windows can now be installed via pip install on Anaconda 3. Other configurations will be enabled soon.
• HTK deserializers are now exposed in Python. All deserializers are exposed in C++.
• The memory pool implementation of CNTK has been updated with a new global optimization algorithm. Hyper memory compression has been removed.
• New features in C++ API.
• New Eval examples for RNN models.
• New CNTK NuGet Packages with CNTK V2 C++ Library.

See more in the Release Notes.
Get the Release from the CNTK Releases page.

2017-02-13. V 2.0 Beta 11 Release available at Docker Hub
CNTK V 2.0 Beta 11 Runtime packages are now available as Public Images at Docker Hub.
See more on CNTK as Docker Images in this Wiki article.

2017-02-10. V 2.0 Beta 11 Release
Highlights of this Release:

• New and updated features: reduce_prod, reductions across all axes, denominator sharing, memory improvement, & more...
• New Tutorials and Examples:
  • Transfer learning example to train custom image classifiers.
• New CNTK NuGet Packages.
  • Note a breaking change due to Assembly Strong Name enabling. See Release Notes.

See more in the Release Notes.
Get the Release from the CNTK Releases page.

See all news.