91d990182d
commit a08e22e7b812891dd641cc512198528a3cd1cddc
Author: TJ <tix@microsoft.com>
Date: Thu Jul 19 17:53:21 2018 -0700
Enabled example tests for linux
commit 2b0b7c49f7ab3ad8ba40684efdaf4c4e4fd2265f
Author: Tix <tix@microsoft.com>
Date: Thu Jun 28 18:30:51 2018 -0700
Enabled V2 lib CS unit tests on linux
|
||
|---|---|---|
| .. | ||
| CSTrainingCPUOnlyExamples | ||
| CSTrainingGPUExamples | ||
| Common | ||
| CNTKLibraryCSharpTrainingExamples.sln | ||
| README.md | ||
README.md
CNTK C#/.NET API training examples
Overview
This folder contains examples using CNTK C# API to build, train, and evaluate CNTK neural network models.
Getting the Data and Model
Data and model preparation are done with python scripts.
To install CIFAR10 dataset, change directory to Examples\Image\DataSets\CIFAR-10, run:
python install_cifar10.py
To install VGG flower and animal data and to download the ResNet model, change directory to Examples\Image\TransferLearning, run:
python install_data_and_model.py
Build and Run Examples
- Install Nuget package CNTK.CPUOnly version v2.2.0 or higher for CSTrainingCPUOnlyExamples.
- Install Nuget package CNTK.GPU version v2.2.0 or higher for CSTrainingGPUExamples
- Run following examples:
LogisticRegression
A hello-world example to train and evaluate a logistic regression model using C#/API. See CNTK 101: Logistic Regression and ML Primer for more details.
MNISTClassifier
This class shows how to build and train a classifier for handwriting data (MNIST).
CifarResNetClassifier
This class shows how to do image classification using ResNet. The model being built is a lite version of Deep Residual Learning for Image Recognition. See Python Tutorials for more details.
TransferLearning
This class demonstrates transfer learning using a pretrained ResNet model. See Python Tutorials for more details.
LSTMSequenceClassifier
This class shows how to build a recurrent neural network model from ground up and how to train the model.