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
18
votes
1 answer

Has Microsoft abandoned CNTK?

I want to know if CNTK dead? Release notes on GitHub dated 03/31/2019: "Today’s 2.7 release will be the last main release of CNTK." I've spent months developing software using CNTK and now it appears to be a waste of time and money. I've search for…
rwbta
  • 181
  • 1
  • 4
15
votes
4 answers

Is it possible to install CNTK on a macbook?

It is possible to install Microsoft CNTK on a macbook? I have OS X El Capitan. The official Microsoft documentation at https://github.com/Microsoft/CNTK/wiki/Setup-CNTK-on-your-machine doesn't provide any information for mac users. Thank you
Victor
  • 360
  • 3
  • 16
13
votes
2 answers

How best to deal with "None of the above" in Image Classification?

This seems to be a fundamental question which some of you out there must have an opinion on. I have an image classifier implemented in CNTK with 48 classes. If the image does not match any of the 48 classes very well, then I'd like to be able to…
Tullhead
  • 565
  • 2
  • 7
  • 17
11
votes
1 answer

Why are deep learning libraries so huge?

I've recently downloaded all packages from PyPI. One interesting observation was that of the Top-15 of the biggest packages, all execept one are deep learning packages: mxnet: mxnet-cu90 (600 MB), mxnet-cu92, mxnet-cu101mkl, mxnet-cu101 (and 6 more…
Martin Thoma
  • 124,992
  • 159
  • 614
  • 958
10
votes
1 answer

CNTK Complaining about Dynamic Axis in LSTM

I'm trying to implement an LSTM in CNTK (using Python) to classify a sequence. Input: Features are fixed length sequences of numbers (a time series) Labels are vectors of one-hot values Network: input = input_variable(input_dim) label =…
Tiny
  • 197
  • 7
10
votes
1 answer

Wrap CNTK Applications

I've gone through the documentation of Microsoft's OpenSource AI Library CNTK and did understand how to create and train neural networks. I've also understood, how to "save" the trained results into an output directory. However, I don't see a way to…
Nex
  • 421
  • 1
  • 4
  • 17
8
votes
0 answers

CNTK C# API: How does TrainingParameterScheduleDouble work?

I'm trying to understand how TrainingParameterScheduleDouble works in the CNTK C# API. Unfortunately, there is no documentation and the previous SO thread here appears to be incorrect/incomplete, so I've tried to reverse engineer the behavior…
Brian Berns
  • 15,499
  • 2
  • 30
  • 40
8
votes
1 answer

Add CNTK virtualenv to Visual Studio Python project

I followed Setup CNTK on Windows, and confirmed that I can run CTNK from my local command prompt. C:\local\Anaconda3-4.1.1-Windows-x86_64\envs\cntk-py34>.\Scripts\activate.bat (root) C:\local\Anaconda3-4.1.1-Windows-x86_64\envs\cntk-py34>set…
Naoto Usuyama
  • 845
  • 1
  • 7
  • 13
6
votes
3 answers

cython_bbox.so: undefined symbol: _Py_ZeroStruct

I try to do all these steps because I want a different version python 3.5 on linux to run the code in this example https://learn.microsoft.com/en-us/cognitive-toolkit/Object-Detection-using-Fast-R-CNN If you need a different version you can compile…
samira
  • 91
  • 1
  • 2
  • 7
5
votes
1 answer

Cannot Install CNTK

When I try to install CNTK using pip, it gives me the following error - Could not find a version that satisfies the requirement cntk (from versions: ) No matching distribution found for cntk I'm using Python 3.7 and windows 10.
Jaydeep Borkar
  • 79
  • 1
  • 2
  • 8
5
votes
1 answer

How to train a network with multiple output layers in CNTK?

Objective: To train a neural network as shown in the image below, for an image classification task. (Input dimension can be seen in the image.) I have been able to create the network, but am facing problems below: Specifying the loss and…
Arko Chakraborti
  • 403
  • 5
  • 19
5
votes
1 answer

How exactly does the CNTK "times" function work?

I am teaching myself CNTK by going through this tutorial. There is a function defined as def linear_layer(input_var, output_dim): input_dim = input_var.shape[0] weight_param = C.parameter(shape=(input_dim, output_dim)) bias_param =…
Chechy Levas
  • 2,206
  • 1
  • 13
  • 28
5
votes
1 answer

CNTK out of memory error when model.fit() is called second time

I am using Keras and CNTK(backend) my code is like this: def run_han(embeddings_index, fname, opt) ... sentence_input = Input(shape=(MAX_SENT_LENGTH,), dtype='int32') embedded_sequences = embedding_layer(sentence_input) l_lstm =…
Kjyong
  • 195
  • 1
  • 8
5
votes
1 answer

CNTK absolute error

To find the loss during training a model we can use cntk.squared_error() function, like this: loss = cntk.squared_error(z, l) But I am interested in finding the loss in terms of absolute error. The below code doesn't work: loss =…
Ank
  • 1,864
  • 4
  • 31
  • 51
5
votes
3 answers

How to save a Keras model in the CNTK format

Is there a way to save a Keras model to the format of CNTK so that we can load it by using CNTK's API? I have tried this code below but it failed: a = Input(shape=(224,224,3)) b = Conv2D(64, (2,2), name='conv1')(a) model = Model(inputs=a,…
logen
  • 76
  • 1
  • 5
1
2 3
33 34