Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
Перейти к файлу
Gaizka Navarro ead48bef6d Remove LoadModel from eval and force use of CreateNetwork instead.
Update description in CSEvalClient to clarify the purpose of the program
2016-03-17 17:08:44 +01:00
Documentation Renames SynchronouseExecutionEngine to NDLBuilderImpl 2016-03-14 09:55:05 +01:00
Examples Remove LoadModel from eval and force use of CreateNetwork instead. 2016-03-17 17:08:44 +01:00
Source Remove LoadModel from eval and force use of CreateNetwork instead. 2016-03-17 17:08:44 +01:00
Tests Remove LoadModel from eval and force use of CreateNetwork instead. 2016-03-17 17:08:44 +01:00
Tools Binary drop script. Linux. Addressed Code Review comments 2016-03-11 13:19:01 +01:00
.clang-format
.gitattributes Binary drop script. Linux. Addressed Code Review comments 2016-03-11 13:19:01 +01:00
.gitignore .gitignore: ignore ReaderTests output 2016-01-18 11:23:34 +01:00
.gitmodules Update location for Source/1BitSGD 2016-01-23 07:23:12 +01:00
CNTK.Cpp.props .vcxproj: let intermediate output go into a common directory 2016-02-10 09:10:07 +01:00
CNTK.sln Updates project dependencies between EvalDLL and ActionsLib 2016-03-17 17:08:44 +01:00
CONTRIBUTING.md Added CONTRIBUTING.md to the root directory 2016-02-17 13:14:44 +01:00
CppCntk.vssettings Update CppCntk.vssettings (wolfma) 2016-01-22 10:08:52 +01:00
LICENSE.md
Makefile Fix makefile (re-add lost changes) 2016-03-17 15:11:44 +01:00
README.md Updated news section. 2016-02-29 11:52:41 -08:00
configure Addressed code review comments. 2016-02-25 10:56:42 -08:00

README.md

CNTK

Latest news

2016-02-29. Added documentation for the ImageReader. Added ZIP files support to the ImageReader.

2016-02-17. CNTK Contribution Guidelines are published.

2016-02-15. The first part of CNTK tutorial is published.

2016-02-10. Another binary release, containing all CNTK flavours is published.

See all news.

What is CNTK

CNTK (http://www.cntk.ai/), the Computational Network Toolkit by Microsoft Research, is a unified deep-learning toolkit that describes neural networks as a series of computational steps via a directed graph. In this directed graph, leaf nodes represent input values or network parameters, while other nodes represent matrix operations upon their inputs. CNTK allows to easily realize and combine popular model types such as feed-forward DNNs, convolutional nets (CNNs), and recurrent networks (RNNs/LSTMs). It implements stochastic gradient descent (SGD, error backpropagation) learning with automatic differentiation and parallelization across multiple GPUs and servers. CNTK has been available under an open-source license since April 2015. It is our hope that the community will take advantage of CNTK to share ideas more quickly through the exchange of open source working code.

Wiki: Go to the CNTK Wiki for all information on CNTK including setup, examples, etc.

License: See LICENSE.md in the root of this repository for the full license information.

Tutorial: Microsoft Computational Network Toolkit (CNTK) @ NIPS 2015 Workshops

Blogs:

Performance

The figure below compares processing speed (frames processed per second) of CNTK to that of four other well-known toolkits. The configuration uses a fully connected 4-layer neural network (see our benchmark scripts) and an effective mini batch size (8192). All results were obtained on the same hardware with the respective latest public software versions as of Dec 3, 2015.

Performance chart

Citation

If you used this toolkit or part of it to do your research, please cite the work as:

Amit Agarwal, Eldar Akchurin, Chris Basoglu, Guoguo Chen, Scott Cyphers, Jasha Droppo, Adam Eversole, Brian Guenter, Mark Hillebrand, T. Ryan Hoens, Xuedong Huang, Zhiheng Huang, Vladimir Ivanov, Alexey Kamenev, Philipp Kranen, Oleksii Kuchaiev, Wolfgang Manousek, Avner May, Bhaskar Mitra, Olivier Nano, Gaizka Navarro, Alexey Orlov, Hari Parthasarathi, Baolin Peng, Marko Radmilac, Alexey Reznichenko, Frank Seide, Michael L. Seltzer, Malcolm Slaney, Andreas Stolcke, Huaming Wang, Yongqiang Wang, Kaisheng Yao, Dong Yu, Yu Zhang, Geoffrey Zweig (in alphabetical order), "An Introduction to Computational Networks and the Computational Network Toolkit", Microsoft Technical Report MSR-TR-2014-112, 2014.

Disclaimer

CNTK is in active use at Microsoft and constantly evolving. There will be bugs.