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
0
votes
2 answers

Simple CNTK network output similar for all samples

I've been looking in to CNTK and decided to create a create a model for an xor function to make sure I understood the basics. I created the files below but since the model does horribly bad I'm guessing I am missing something fundamental. command =…
nimatt
  • 489
  • 1
  • 4
  • 11
0
votes
1 answer

Image recognition classification in convolution neural network

I am using convolution neural network to train my model with two classes Horse and Lion, i want the model evaluation return "none of the above" if i use a image of a Dog, any idea how should i train my model to accomplish that?
Eddy Ma
  • 98
  • 9
0
votes
2 answers

Can I make CNTK detect overfitting?

CNTK only stops after maxEpochs is reached, and then runs test. Is there a way to make it run test after each epoch to check if it is severely overfitting?
LOST
  • 2,956
  • 3
  • 25
  • 40
0
votes
2 answers

How to run CNTK c# EvalDLL Wrapper program on GPU?

I was successful on training and evaluate networks based on the CIFAR-10 samples. I'm using my own images with specific size . The networks were trained with GPU and able to evaluate with CPU. However, I'm not able to evaluate it with with GPU. The…
Terry1998
  • 53
  • 1
  • 4
0
votes
1 answer

CNTK: /home/me/opencv-3.0.0/include/opencv2/opencv.hpp:46:28: opencv/core.hpp: No such file or directory

I have got an error while building cntk with make all -j4. As specified in the title the error was: /home/me/opencv-3.0.0/include/opencv2/opencv.hpp:46:28: opencv/core.hpp: No such file or directory I followed instructions here and, I have no clue…
user6301652
0
votes
1 answer

Assembly loading fails with CNTK EvalWrapper

I have a .NET assembly with some tests that references CNTK's EvalWrapper.dll. The CNTK build is targeting x64, the .NET test assembly has build target AnyCPU. I have ensured that all required DLLs are available in the build output directory, see…
Anton Schwaighofer
  • 3,119
  • 11
  • 24
0
votes
1 answer

c# Wrapper for CNTK step 2

This is a follow-up question from "c# Wrapper for CNTK step" After adding reference EvalWrapper.dll, The type or namespace name 'IEvaluateModelManagedF' could not be found error went away. The next compile error I encounter is at line …
Terry1998
  • 53
  • 1
  • 4
0
votes
1 answer

Unexpected results from CNTK

I'm running a fairly simple test of CNTK but not getting results that make much sense. My training/test data consist of one feature and one label. The feature is a decimal and the label will be an integer between 0-5. In a majority of cases the…
Opossum Posse
  • 171
  • 1
  • 6
0
votes
1 answer

CNTK: Start of features is set to 1 - mechanism of UCIFastReader

sorry for this rather simple question, however there is yet too little documentation about the usage of Microsoft's OpenSource AI library CNTK. I continue to witness people setting the reader's feature start to 1, while setting the labels start to…
Nex
  • 421
  • 1
  • 4
  • 17
-1
votes
1 answer

CNTK CMD RedirectStandardOutput = true not working

Microsoft have dropped CNTK for ML.NET ( Horrible product ) and ONNX ( Not yet looked at it ). CNTK, best product Microsoft have Open Sourced, but lots of Bugs and Zero Support, sadly! I reluctantly look toward the Stackoverflow community for a…
Rusty Nail
  • 2,692
  • 3
  • 34
  • 55
-1
votes
1 answer

Microsoft CNTK Unsupported Windows Version 8.1

Anaconda version: 3 4.1.1 Python version: 3 5.2 Windows version: 8.1 x64 I've installed Python-only CNTK v2.6 succesfully via PyPI and tested with: python -c "import cntk; print(cntk.__version__)" After that there is an unsupported…
ATES
  • 281
  • 1
  • 11
  • 29
-1
votes
1 answer

Best configuration parameters for a CNN image classification model in CNTK

i have a dataset composed by 2 images for observation. The images have shape (1, 128, 118), they are greyscaled images and there are 11 classes to classify for this problem. What's the best to go with a CNN with data like this? How could i optimally…
Miguel 2488
  • 1,410
  • 1
  • 20
  • 41
-1
votes
1 answer

Getting loss for test image

I'm trying to get the loss from a test image in Faster R-CNN. If I run copy.copy(trainer.previous_minibatch_loss_average) right after trainer.train_minibatch(data) then I can get the loss out for the trained image(mb=1). When I try to do the exact…
Gronborg
  • 1
  • 1
-1
votes
2 answers

How to "flatten" variable

Sometimes, usually after convolution layer, there can be found shapes in form ( width, height, depth) where depth is a number of filters from convolution operation. I want to reproduce GoogleNet inception module and "squish" (width, height, depth)…
Dmitrii
  • 321
  • 6
  • 17
-1
votes
2 answers

CNTK Sequences in C#

I made a working script in python to train a CNTK Model with some data samples. Now I'm trying to translate it to C# in CNTK V2.2 but I'm getting different results. This is what I got in Python to create a model: def…
1 2 3
33
34