Skip to content

Commit

Permalink
Tools/samples.json: edited
Browse files Browse the repository at this point in the history
  • Loading branch information
@mahilleb-msft
mahilleb-msft committed Jan 3, 2017
1 parent e792cfa commit 38d14a6
Showing 1 changed file with 109 additions and 53 deletions.
162 changes: 109 additions & 53 deletions Tools/samples.json
View file
Original file line number Diff line number Diff line change
@@ -1,119 +1,151 @@
[
{
"category": [""],
"name": "CNTK Evaluation on Azure",
"name": "Model Evaluation on Azure",
"url": "https://github.com/Microsoft/CNTK/wiki/Evaluate-a-model-in-an-Azure-WebApi",
"description": "Host an already trained CNTK model on Azure.",
"language": [],
"type": ["Tutorial"]
},
{
"category": [""],
"name": "Using the C# Eval Client",
"url": "https://github.com/Microsoft/CNTK/wiki/Managed-Evaluation-Interface",
"description": "Evaluation or inference of an already trained CNTK model.",
"name": "Model Evaluation in C#",
"url": "https://github.com/Microsoft/CNTK/wiki/EvalDLL-Evaluation-on-Windows#using-the-evaldll-c-library",
"description": "Evaluation or inference of an already trained CNTK model in C#.",
"language": ["C#"],
"type": ["Example"]
},
{
"category": [""],
"name": "Using the C++ Eval Client",
"url": "https://github.com/Microsoft/CNTK/wiki/Native-Evaluation-Interface",
"description": "Evaluation or inference of an already trained CNTK model.",
"name": "Model Evaluation in C++",
"url": "https://github.com/Microsoft/CNTK/wiki/Native-EvalDLL-API",
"description": "Evaluation or inference of an already trained CNTK model in C++.",
"language": ["C++"],
"type": ["Example"]
},
{
"category": [""],
"name": "Video action recognition",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Video/GettingStarted",
"description": "Train a Basic 3-D convolutional neural network for video action recognition on the UCF11 dataset.",
"language": ["Python"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "AlexNet",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/Classification/AlexNet",
"description": "CNN based network by Alex Krizhevsky winning model of ILSVRC2012 classification task.",
"description": "CNN based network by Alex Krizhevsky. This was the winning model of the ILSVRC2012 classification task.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "ConvNet",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/Classification/ConvNet#cntk-examples-imageclassificationconvnet",
"description": "One of the most popular neural networks for image-related tasks.",
"language": ["BrainScript"],
"description": "A popular convolutional neural network for image-related tasks.",
"language": ["Python", "BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "Fast R-CNN",
"url": "https://github.com/Microsoft/CNTK/wiki/Object-Detection-using-Fast-R-CNN",
"description": "Training object detection from images by adapting pre-trained classification models on arbitrarily sized region-of-interest using ROI pulling.",
"description": "Train object detection from images by adapting pre-trained classification models on arbitrarily sized regions of interest using ROI pooling.",
"language": ["BrainScript"],
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Image"],
"name": "GoogLeNet (Inception V3)",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/Classification/GoogLeNet#cntk-examples-imageclassificationgooglenet",
"description": "GoogLeNet (Inception V3) network for image classification.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "MLP",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/Classification/MLP#cntk-examples-imageclassificationmlp",
"description": "Multilayer perceptron is a permutation invariant model using a feed-forward neural network that consists of multiple layers of nodes in a directed graph, where each layer fully connected to the next one.",
"language": ["BrainScript"],
"description": "Training a multilayer perceptron (MLP) network for image classification.",
"language": ["Python", "BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "MNIST CNN OCR",
"url": "https://github.com/Microsoft/CNTK/wiki/Tutorial2",
"description": "Use CNN on a OCR problem.",
"description": "Use CNN on an OCR problem.",
"language": ["Python", "BrainScript"],
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Image"],
"name": "MNIST Feed Forward OCR",
"url": "https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_103A_MNIST_DataLoader.ipynb",
"description": "Use Feed Forward networks on a OCR problem.",
"url": "https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_103B_MNIST_FeedForwardNetwork.ipynb",
"description": "Use Feed Forward networks on an OCR problem.",
"language": ["Python"],
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Image"],
"name": "Image Recognition",
"url": "https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_201B_CIFAR-10_ImageHandsOn.ipynb",
"description": "Hands-on lab that shows how to implement an image recognition task using convolutional neural networks.",
"language": ["Python"],
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Image"],
"name": "Neural Artistic Style Transfer",
"url": "https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_205_Artistic_Style_Transfer.ipynb",
"description": "This tutorial shows how to transfer the style of one image to another. This allows us to take our ordinary photos and render them in the style of famous images or paintings.",
"language": ["Python"],
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Image"],
"name": "One Conv",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/GettingStarted#02_oneconvcntk",
"description": "This is a simple network example showing one convolutional layer.",
"description": "Simple network with one convolutional layer.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "One Conv BN",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/GettingStarted#04_oneconvbncntk",
"description": "This is a simple network example showing how to add batch normalization to a CNN.",
"description": "Simple network showing how to add batch normalization to a CNN.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "One Conv Dropout",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/GettingStarted#03_oneconvdropoutcntk",
"description": "This is a simple network example showing how to add dropout to a CNN.",
"description": "Simple network showing how to add dropout to a CNN.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "One Hidden",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/GettingStarted#01_onehiddencntk",
"description": "This is a simple network example showing one hidden layer.",
"description": "Simple network with one hidden layer.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "One Regr",
"name": "MNIST Regression",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/GettingStarted#05_oneconvregrcntk",
"description": "This is a simple network example showing how to treat MNIST as a regression problem using Root Mean Square Error.",
"description": "Simple network showing how to treat MNIST as a regression problem using Root Mean Square Error.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Image"],
"name": "RegrSimple",
"name": "Simple Regression",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/Regression#cntk-examples-imageregression",
"description": "A simple neural network to predict the average RGB values of normalized images.",
"language": ["BrainScript"],
Expand All @@ -123,15 +155,15 @@
"category": ["Image"],
"name": "ResNet",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/Classification/ResNet#cntk-examples-imageclassificationresnet",
"description": "Deep residual learning invented by Microsoft Research and winning model of ILSVRC and MS-COCO challenges in 2015.",
"description": "Deep residual learning invented by Microsoft Research. This was the winning model of the ILSVRC and MS-COCO challenges in 2015.",
"language": ["Python", "BrainScript"],
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Image"],
"name": "VGG",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Image/Classification/VGG",
"description": "Deep CNN from University of Oxford winning model for ILSVRC2014 localization task.",
"description": "Deep CNN from University of Oxford. This was the winning model for the ILSVRC2014 localization task.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
Expand All @@ -140,8 +172,16 @@
"name": "Feed Forward Classification",
"url": "https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_102_FeedForward.ipynb",
"description": "Use Feed Forward networks on a classification problem with CNTK and NumPy.",
"language": ["Python", "BrainScript"],
"type": ["Tutorial", "Recipe"]
"language": ["Python"],
"type": ["Tutorial"]
},
{
"category": ["Numeric"],
"name": "Finance Timeseries Basic",
"url": "https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_104_Finance_Timeseries_Basic_with_Pandas_Numpy.ipynb",
"description": "Time Series with Pandas and NumPy",
"language": ["Python"],
"type": ["Tutorial"]
},
{
"category": ["Numeric"],
Expand All @@ -152,130 +192,146 @@
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Image"],
"category": ["Numeric"],
"name": "Reinforcement Learning",
"url": "https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_203_Reinforcement_Learning_Basics.ipynb",
"description": "Inspired by behaviorist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward.",
"description": "Example how software agents could take actions in an environment so as to maximize some notion of cumulative reward.",
"language": ["Python"],
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Speech"],
"name": "AN4 Speech DNN",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/AN4",
"description": "Train a speech recognition DNN acoustic model trained on the CMU AN4 dataset.",
"description": "Train a speech recognition DNN acoustic model on the CMU AN4 dataset.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech"],
"name": "AN4 Speech LSTM",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/AN4",
"description": "Train a speech recognition LSTM acoustic model trained on the CMU AN4 dataset.",
"description": "Train a speech recognition LSTM acoustic model on the CMU AN4 dataset.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech"],
"name": "Kaldi Speech DNN",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/Miscellaneous/AMI",
"description": "Train a speech recognition DNN acoustic model on top of fMLLR features generated using the Kaldi toolchain.",
"description": "Train a speech recognition DNN acoustic model on top of fMLLR features generated with the Kaldi toolchain.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech"],
"name": "Speech Adapt Learn Rate",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/Miscellaneous/TIMIT/config",
"description": "Train a speech recognition model with learning rate adapted based on dev set trained on the TIMIT dataset.",
"description": "Train a speech recognition model with learning rate adapted based on dev set on the TIMIT dataset.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech"],
"name": "Speech Auto Encoder",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/Miscellaneous/TIMIT/config",
"description": "Train autoencoder with bottleneck layer trained on the TIMIT dataset.",
"description": "Train autoencoder with bottleneck layer on the TIMIT dataset.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech"],
"name": "Speech Multi Input",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/Miscellaneous/TIMIT/config",
"description": "Train with 2 different inputs: fbank and mfcc trained on the TIMIT dataset.",
"description": "Train with two different inputs, fbank and mfcc, on the TIMIT dataset.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech"],
"name": "Speech Multi Task",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/Miscellaneous/TIMIT/config",
"description": "Train with multi-task learning with joint prediction of senone labels and dialect region trained on the TIMIT dataset.",
"description": "Train with multi-task learning and joint prediction of senone labels and dialect region on the TIMIT dataset.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech"],
"name": "Speech with PreTrain",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/Miscellaneous/TIMIT/config",
"description": "Pre-train using layerwise discriminative pre-training, then do full network training trained on the TIMIT dataset.",
"description": "Pre-train using layerwise discriminative pre-training, then full network training on the TIMIT dataset.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech"],
"name": "TIMIT Speech DNN",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/Miscellaneous/TIMIT/config",
"description": "Train a speech recognition DNN acoustic model trained on the TIMIT dataset (TrainSimpleNetwork).",
"description": "Train a speech recognition DNN acoustic model on the TIMIT dataset (TrainSimpleNetwork).",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech"],
"name": "TIMIT Speech LSTM",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Speech/Miscellaneous/TIMIT/config",
"description": "Train a speech recognition LSTM acoustic model trained on the TIMIT dataset (TrainNDLNetwork).",
"description": "Train a speech recognition LSTM acoustic model on the TIMIT dataset (TrainNDLNetwork).",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech", "Text"],
"name": "G2P",
"name": "Grapheme to Phoneme (G2P)",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/SequenceToSequence/CMUDict",
"description": "Sequence-to-sequence model with attention mechanism for a grapheme to phoneme translation task on the CMUDict dataset.",
"language": ["BrainScript"],
"language": ["Python", "BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Speech", "Text"],
"name": "Grapheme to Phoneme (G2P)",
"url": "https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_204_Sequence_To_Sequence.ipynb",
"description": "Sequence-to-sequence model with attention mechanism for a grapheme to phoneme translation task on the CMUDict dataset.",
"language": ["Python"],
"type": ["Tutorial"]
},
{
"category": ["Text"],
"name": "RNN ATIS LU",
"name": "LTSM LU on ATIS",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/LanguageUnderstanding/ATIS",
"description": "LSTM based model for language understanding on the ATIS dataset.",
"language": ["Python", "BrainScript"],
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Text"],
"name": "RNN LM",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/SequenceToSequence/PennTreebank",
"description": "Recurrent neural network for language modeling on the Pentreebank dataset.",
"language": ["BrainScript"],
"type": ["Recipe"]
"name": "Language Understanding with Recurrent Networks",
"url": "https://github.com/Microsoft/CNTK/blob/master/Tutorials/CNTK_202_Language_Understanding.ipynb",
"description": "Implement a recurrent network for language understanding of the ATIS dataset.",
"language": ["Python"],
"type": ["Tutorial", "Recipe"]
},
{
"category": ["Text"],
"name": "Sequence Classification",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/SequenceClassification/SimpleExample/Python",
"description": "Creates and trains a LSTM sequence classification model.",
"name": "Neural Character Language Model",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/Text/CharacterLM",
"description": "Create and train a neural character language model.",
"language": ["Python"],
"type": ["Recipe"]
},
{
"category": ["Text"],
"name": "Sequence-to-Sequence",
"url": "https://github.com/Microsoft/CNTK/tree/Examples/SequenceToSequence/CMUDict/Python",
"description": "Creates and trains a sequence to sequence translation model.",
"name": "RNN LM on PennTreebank",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/SequenceToSequence/PennTreebank",
"description": "Recurrent neural network for language modeling on the PennTreebank dataset.",
"language": ["BrainScript"],
"type": ["Recipe"]
},
{
"category": ["Text"],
"name": "Sequence Classification",
"url": "https://github.com/Microsoft/CNTK/tree/master/Examples/SequenceClassification/SimpleExample/Python",
"description": "Create and train an LSTM sequence classification model.",
"language": ["Python"],
"type": ["Recipe"]
}
Expand Down

0 comments on commit 38d14a6

Please sign in to comment.