dotnet-architecture/mnisttensorcntk

MNIST for ML Beginners using C#

This sample is a very simple WPF application which recognizes hand-written digits using the pre-built MNIST convolutional model. The MNIST problem is Machine Learning's Hello World program.

MNIST is a simple computer vision dataset which consists of hand written digits like as shown below.

This tutorial comes with a pre-built CNTK model which is trained to look at these hand-written digits and predict what these digits are.

CNTK is a deep learning library in which this model is built in. For now, we will just basically load this model as a resource into your .NET application and evaluate on it. Follow the steps below to get going.

Get Started

Step 1: Download and Install

If you are new to .NET, go ahead and download Visual Studio 2017 and select only the '.NET desktop development' section as shown below.

Step 2: Download MNIST tutorial code

Clone or download this github repo. Open up the MNIST solution (MNIST.sln) file in Visual Studio 2017.                

Step 3: Understand Solution Structure

This solution consits of two projects 'Digitz' (C# project building a windows app using the CNTK pre-built MNIST model) and 'Training' (Python project, which generates the MNIST model using CNTK). Don't worry about the Python project for now.

   

Step 4: Configure and build your Project for Launch

Set the start-up project to be 'Digitz' project as shown below and then go ahead and build your application by using the right-click 'build' option.

Step 5: Launch MNIST application

Launch the app by clicking the green start button at the top or F5 on your keyboard. Draw out a hand-written digit and click 'Recognize' to see if this works for you!

Congrats! you have just completed the helloworld program for Machine Learning.

TL;DR

The sample provides you an example of how you can use Machine Learning and AI in your .NET apps today. The sample basically loads the pre-built model 'digit.model' and takes the bitmap image that user draws out, converts that into an optimized multi-dimensional exchange type Tensor and then calls CNTK evaluate method to evaluate on the model.

The evaluate method from CNTK returns a list of floats (0 - 9) predicting the confidence for each of these digits. The highest confidence digit is then displayed in the app.

This sample also introduces Tensor, Tensor is an exchange type for homogenous multi-dimensional data for 1 to N dimensions. The motivation behind introducing Tensor is to make it easy for Machine Learning library vendors like CNTK, Tensorflow, Caffe, Scikit-Learn to port their libraries over to .NET with minimal dependencies in place.  Tensor is designed to provide the following characteristics.

To learn more about Tensor follow our blog post and GitHub repo.

To follow a video tutorial on this app being used you can also follow this video. https://channel9.msdn.com/Events/Connect/2017/t126

mnisttensorcntk's Issues

Unknown Subtype: {E2A2EEF0-14BE-4BFE-B65C-5669125F62A7}

When I trying to open project in VS I receive next error:

The project file 'D:\tmp\MNISTTensorCNTK-master\MNISTTensorCNTK-master\Training\Training.pyproj' cannot be opened.

There is a missing project subtype.
Subtype: '{E2A2EEF0-14BE-4BFE-B65C-5669125F62A7}' is unsupported by this installation.

I installed all stuff related Python but still same.
Even trying to remove this guid from types in Training.pyproj but looks like VS automatically adds it back, because of error still same

Link in Readme is broken

The Tensor link in the TLDR part of the readme is navigating to a page that can not be found.

Original url: https://blogs.msdn.microsoft.com/dotnet/2017/11/15/introducing-tensor-for-machine-learning-and-ai-libraries

Is this the new url? : https://blogs.msdn.microsoft.com/dotnet/2017/11/15/introducing-tensor-for-multi-dimensional-machine-learning-and-ai-data/

Link for Tensor in readme.md is broken

Link for Tensor (https://blogs.msdn.microsoft.com/dotnet/2017/11/15/introducing-tensor-for-machine-learning-and-ai-libraries) is broken. I hope (https://blogs.msdn.microsoft.com/dotnet/2017/11/15/introducing-tensor-for-multi-dimensional-machine-learning-and-ai-data/) is correct link.

Model training

How was the digit.model created ? Is it possible to train and optimize the model ?

Error

缺少一个项目子类型。
子类型: 此安装不支持“{E2A2EEF0-14BE-4BFE-B65C-5669125F62A7}”。

Python Project Fails to Load in Visual Studio

I attempted to download and build the MNISTTensorCNTK solution.

I am unfamiliar with using Python in Visual Studio. The Python project within this solution says "Load Failed", and when I try to reload the project, a popup says there is a missing project subtype

Googling the missing subtype was unsuccessful.

I've tried 2 separate computers, and I've tried repair installation, and adding/modifying Python in

Visual Studio.

Please advise on possible solutions.