Skip to content

Home

Jump to bottom
sayanpa edited this page Mar 28, 2017 · 124 revisions

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.

Important Note: there are breaking changes in master compared to beta15, click here for more information.

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 description 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:

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

To update to the latest CNTK release, use:

pip install --upgrade https://cntk.ai/PythonWheel/CPU-Only/cntk-2.0.beta15.0-cp35-cp35m-linux_x86_64.whl

or follow more detailed installation instruction here.

2017-03-16. V 2.0 Beta 15 Release available at Docker Hub
CNTK V 2.0 Beta 15 Runtime packages are now available as Public Images at Docker Hub.
See more on CNTK as Docker Images in this Wiki article.

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

  • In addition to pre-existing python support, 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.

See all news.

New Documentation Site

Iteration Plans

Clone this wiki locally