News

March 2017

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.

February 2017

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.

2017-02-08. V 2.0 Beta 10 Release available at Docker Hub
CNTK V 2.0 Beta 10 Runtime packages are now available as Public Images at Docker Hub.
See more on CNTK as Docker Images in this Wiki article.

2017-02-01. V 2.0 Beta 10 Release
Highlights of this Release:

• New and updated core and Python API features (Operators with UserFunctions, Tensorboard support, Python API Fast R CNN).
• Improved speed of CrossEntropyWithSoftmax and ClassificationError for sparse labels.
• New Tutorials and Examples:
  • A Python version of the deconvolution layer and image auto encoder example was added (Example 07_Deconvolution in Image - Getting Started).
  • A Python distributed training example for image classification using AlexNet was added, cf. here
  • Basic implementation of Generative Adversarial Networks (GAN) networks
  • Training with Sampled Softmax
• New CNTK NuGet Packages.

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

January 2017

2017-01-25. V 2.0 Beta 9 Release available at Docker Hub
CNTK V 2.0 Beta 9 Runtime packages are now available as Public Images at Docker Hub.
See more on CNTK as Docker Images in this Wiki article.

2017-01-25. 1bit-SGD Code is relocated to GitHub. Submodule configuration update is required for affected users
This news is related to users who are working with CNTK code base. If you use Binary or Docker Runtime Images installation you may ignore it.

Effective January 25, 2017 CNTK 1-bit Stochastic Gradient Descent (1bit-SGD) and BlockMomentumSGD code is moved to a new Repository in GitHub.

If you cloned CNTK Repository with 1bit-SGD enabled prior to January 25, 2017 you need to update git submodule configuration as described in this Wiki article.

2017-01-20. V 2.0 Beta 9 Release
Highlights of this Release:

• Default Python version is now 3.5 (relates to default parameters in client installations as well as Runtime Images at Docker Hub).
• New and updated core and Python API features.
• New Tutorials and Examples:
  • Deconvolution layer and image auto encoder example using deconvolution and unpooling (Example 07_Deconvolution in Image - Getting Started).
  • Basic autoencoder with MNIST data.
  • LSTM Timeseries with Simulated Data (Part A). (More will come in the next Releases)
• New CNTK NuGet Packages.

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

2017-01-19. V 2.0 Beta 8 Release available at Docker Hub
CNTK V 2.0 Beta 8 Runtime packages are now available as Public Images at Docker Hub.
See more on CNTK as Docker Images in this Wiki article.

2017-01-16. V 2.0 Beta 8 Release
Highlights of this Release:

• Support of Python v. 2.7, 3.4, and 3.5. See binary and source setup instructions to find out about how to select Python version.
• New Python API features.
• New Python example Feature extraction using a trained model in Python API.
• Support of Visual Studio 2015 for Windows version.
• Introduction of C# API in CNTK Evaluation Library and a new set of CNTK NuGet Packages.
• CNTK Runtime packages are now available as Public Images at Docker Hub. (Beta 7 is currently available; Beta 8 Images availability will be announced separately in a few days)
• Version 3 of CNTK Custom MKL Library is available.

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

2017-01-10. CNTK for Windows supports Visual 2015

If you pull or merge the master branch, CNTK will now require Visual Studio 2015 to build on Windows. There are two ways to move your development environment to Visual Studio 2015:

• Migrate VS2013 to VS2015: This gives you a fine grained control over where components are installed
• Script driven setup: This gives you an mostly automated migration to Visual Studio 2015

Earlier News

• News of 2016