Questions tagged [cntk]

Microsoft Cognitive Toolkit (CNTK) is an open source library for commercial-grade distributed deep learning. It became open source in January 2016. In March, 2019, Microsoft announced that version 2.7 was to be the last release of CNTK.

Microsoft Cognitive Toolkit (CNTK) is an open source library for commercial-grade distributed deep learning. It 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).

CNTK 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.

In March 2019, Microsoft announced that version 2.7 was to be the last release of CNTK.

More information

Blogs:

503 questions
-1
votes
1 answer

what neural network model for the picture below are supported by cntk?

what neural network model for the picture below are supported by cntk? which of them are supported by higher level API,and which are supported by core or lower level only? neural network model:
yingxing.bao
  • 67
  • 1
  • 1
  • 5
-1
votes
2 answers

how to freeze parameters

I need to freeze some of layer's parameters during training. I tried to set needs_gradient attribute by model.L1.b.needs_gradient = False but I get the following exception: AttributeError Traceback (most recent call…
-1
votes
4 answers

How to improve this cntk xor implementation

I've implemented the "xor problem" with cntk (python). Currently it solves the problem only occasionally. How could I implement a more reliable network? I guess the problem gets solved whenever the starting random weights are near optimal. I have…
Vasco
  • 395
  • 2
  • 13
-1
votes
1 answer

rnn sequence retrieval with tensorflow or cntk

Having a list of constant length sequences(array of 192 int), I want to retrieve the nearest complete sequence matching partial input : Example with 4 sequences : 1,4,3,2 1,2,3,4 1,2,3,4 1,2,1,4 input -> 1,2 output ->1,2,3,4 Is seq2seq…
-2
votes
2 answers

VGA card(GPU) for Microsoft Cognitive CNTK/TensorFlow

Where can I purchase good VGA card(GPU) for Microsoft Cognitive CNTK/TensorFlow programming? can you suggest commonly used GPU model with affordable price?
-2
votes
1 answer

Using Multiple GPUs with C++ cntk

I'm trying to gradually move over from brainscript to the C++ interface for cntk. The complete lack of documentation doesn't help. My latest project is multi-gpu training. There's an example for single GPU training. What is the best strategy for…
-2
votes
1 answer

learning rate setting with CNTK 2.1.0 GPU, VS 2015 update 3, C++, Window

I referred "https://github.com/Microsoft/CNTK/blob/master/Tests/UnitTests/V2LibraryTests/FeedForwardTests.cpp" In the "TestFeedForwardNetworkCreation" Function, I can not find a method of setting learning rate. std::vector
-2
votes
3 answers

CNTK 2.0 beta 7 installation error - install.ps1 not digitally signed

I downloaded cntk 2.0 beta 7. when executing .\install.ps1, got this error for install.ps1 not digitally signed: Windows PowerShell Copyright (C) 2016 Microsoft Corporation. All rights reserved. PS C:> cd .\local\cntk\Scripts\install\windows\ PS…
1 2 3
33
34