https://github.com/Microsoft/CNTK
Revision 154838b6b9a9b0d850f0d1a48202613185243503 authored by Lewei Lu on 05 July 2017, 09:12:22 UTC, committed by Lewei Lu on 13 July 2017, 06:41:39 UTC
1 parent f3a2b16
Raw File
Tip revision: 154838b6b9a9b0d850f0d1a48202613185243503 authored by Lewei Lu on 05 July 2017, 09:12:22 UTC
update bn-inception python script
Tip revision: 154838b
README.md
[![Join the chat at https://gitter.im/Microsoft/CNTK](https://badges.gitter.im/Microsoft/CNTK.svg)](https://gitter.im/Microsoft/CNTK?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)

## Latest news 

***2017-06-26.*** A great class for getting started with both Deep Learning and CNTK, [Deep Learning Explained](https://www.edx.org/course/deep-learning-explained-microsoft-dat236x) 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](https://docs.microsoft.com/en-us/cognitive-toolkit/ReleaseNotes/CNTK_2_0_Release_Notes), and get the Release from the [CNTK Releases page](https://github.com/Microsoft/CNTK/releases).

See [all news](https://docs.microsoft.com/en-us/cognitive-toolkit/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](https://docs.microsoft.com/en-us/cognitive-toolkit/Setup-CNTK-on-your-machine)
    * Windows [Python-only](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-windows-python) / [Script-driven](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-windows-binary-script) / [Manual](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-windows-binary-manual) 
    * Linux [Python-only](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-linux-python) / [Script-driven](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-linux-binary-script) / [Manual](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-linux-binary-manual) / [Docker](https://docs.microsoft.com/en-us/cognitive-toolkit/cntk-docker-containers)
* [CNTK backend for Keras](https://docs.microsoft.com/en-us/cognitive-toolkit/using-cntk-with-keras)
* [Setup CNTK development environment](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-development-environment) 
    * Windows [Script-driven](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-cntk-with-script-on-windows) / [Manual](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-cntk-on-windows) 
    * Linux [Manual](https://docs.microsoft.com/en-us/cognitive-toolkit/setup-cntk-on-linux)

## Learning CNTK 

You may learn more about CNTK with the following resources: 
* [General documentation](https://docs.microsoft.com/en-us/cognitive-toolkit/)
* [Python API documentation](https://cntk.ai/pythondocs/)
* [BrainScript documentation](https://docs.microsoft.com/en-us/cognitive-toolkit/Using-CNTK-with-BrainScript)
* [Evaluation documentation (C++, C#/.NET, Python, Java)](https://docs.microsoft.com/en-us/cognitive-toolkit/CNTK-Evaluation-Overview) 
* [Manual](https://github.com/Microsoft/CNTK/tree/master/Manual)
* [Tutorials](https://docs.microsoft.com/en-us/cognitive-toolkit/tutorials)
* [Examples](https://docs.microsoft.com/en-us/cognitive-toolkit/Examples)
* [Blog](https://www.microsoft.com/en-us/cognitive-toolkit/blog/)
* [Presentations](https://docs.microsoft.com/en-us/cognitive-toolkit/Presentations)
* [License](./LICENSE.md)

## More information 

* [Reasons to switch from TensorFlow to CNTK](https://docs.microsoft.com/en-us/cognitive-toolkit/reasons-to-switch-from-tensorflow-to-cntk) 
* [Contribute to CNTK](https://docs.microsoft.com/en-us/cognitive-toolkit/Contributing-to-CNTK)
* [FAQ](https://docs.microsoft.com/en-us/cognitive-toolkit/CNTK-FAQ)
* [Feedback](https://docs.microsoft.com/en-us/cognitive-toolkit/Feedback-Channels)

## 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](https://opensource.microsoft.com/codeofconduct/). For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
back to top