microsoft/CNTK: Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit - CNTK

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

cntk cognitive-toolkit c-plus-plus c-sharp deep-learning deep-neural-networks distributed java machine-learning neural-network python

Перейти к файлу

Lewei Lu 95254021f5 update sample.json		2017-07-13 14:55:15 +08:00
Dependencies/CNTKCustomMKL	updating links to old wiki - referencing now the doc site	2017-06-07 15:55:34 +02:00
Documentation	Fix typos	2017-06-23 16:44:56 +09:00
Examples	update readme.md	2017-07-13 14:55:15 +08:00
Manual	Integrate nikosk/man4 into master	2017-07-07 22:50:15 -07:00
Scripts	txt2ctf.py: flush and close output	2017-07-10 13:11:29 +02:00
Source	bug fix for clone with freeze	2017-07-12 11:26:11 -07:00
Tests	Updated the test tollerance	2017-07-12 14:01:55 -07:00
Tools	update sample.json	2017-07-13 14:55:15 +08:00
Tutorials	Reduce test code in tutorials and fixes	2017-07-07 13:44:58 -07:00
bindings	Integrate nikosk/clone_freeze2 into master	2017-07-12 17:33:59 -07:00
.clang-format	…
.gitattributes	CNTK v2 library: Add a non-SSE/AVX version of the halide_convolve static library for windows and use that by default to enable the tests to be run on machines without AVX support.	2017-05-30 11:02:35 -07:00
.gitignore	Adding a manual for explicit training loop and Function.train	2017-06-28 09:44:15 +02:00
.gitmodules	GitHub Repo as 1bit SGD Repo	2017-01-19 20:10:35 +01:00
CNTK.Common.props	Bump version numbers	2017-06-01 15:12:14 +02:00
CNTK.Cpp.props	fix quoting problem	2017-03-28 09:36:34 +02:00
CNTK.sln	Add more check and cleanup solution.	2017-06-06 18:35:10 -07:00
CONTRIBUTING.md	updating links to old wiki - referencing now the doc site	2017-06-07 15:55:34 +02:00
CppCntk.vssettings	…
LICENSE.md	…
Makefile	addressed CR comments	2017-06-07 16:50:37 +02:00
README.md	Update README.md	2017-06-28 11:54:20 -07:00
configure	Tools/devInstall/Linux/install-swig.sh: added	2017-07-07 13:16:12 +02:00

README.md

Latest news

2017-06-26. A great class for getting started with both Deep Learning and CNTK, Deep Learning Explained is now available on edX.

2017-06-01. CNTK 2.0 is released. The first production release of Cognitive Toolkit v.2. See more in the Release Notes, and get the Release from the CNTK Releases page.

See all news

Introduction

The Microsoft Cognitive Toolkit (https://cntk.ai), 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.

Installation

Setup CNTK
- Windows Python-only / Script-driven / Manual
- Linux Python-only / Script-driven / Manual / Docker
CNTK backend for Keras
Setup CNTK development environment
- Windows Script-driven / Manual
- Linux Manual

Learning CNTK

You may learn more about CNTK with the following resources:

More information

Disclaimer

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

Microsoft Open Source Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.