This page provides some useful official resources about Microsoft Cognitive Toolkit. See this page for unofficial resources about CNTK.
Microsoft Cognitive Toolkit, previously known as CNTK (Computational Network Toolkit), is a machine learning and deep learning framework developed by Microsoft Research. Microsoft Cognitive Toolkit describes neural networks as a series of computational steps via a directed graph.
The Microsoft Cognitive Toolkit – CNTK – is a unified deep-learning toolkit by Microsoft Research. This video provides a high-level view of the toolkit.
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 describtion 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.
- CNTK’s wikipage on GitHub
- Setup CNTK on your machine
- Setup CNTK on Linux (Open MPI)
- Updates to installation instructions on Linux #256
- GLIBC not found error for binary installation #731
- CNTK+Kaldi plugin on RH7 #119
- CNTK Usage Overview
- Tutorials (CNTK Python Jupyter notebook tutorials cover a range of different application including image classification, language understanding, reinforcement learning and others.)
- Build your own image classifier using Transfer Learning
- CNTK (Transfer learning) not working with remote desktop #1841
- Recognize flowers and animals in natural scene images using deep transfer learningCNTK 301: Deep transfer learning with pre-trained ResNet model
- Tutorial2
- How to use CNTK
=================Below are some official posts about Microsft Cognitive Toolkit.
- Scalable Deep Learning with Microsoft Cognitive Toolkit
- Deep Learning with Microsoft Cognitive Toolkit CNTK (February 10, 2017)
Notes: Guido’s friend Ruggero used CNTK transfer learning, and he said it is pretty fast on multi-GPUs.
