.Net Foundation ML.NET, 23 Sep 2019

Previous Meeting Next Meeting

⏯

youtube image

►

From YouTube: Deep learning with ML.NET: Image Classification | ML.NET [8 of 8]

Description

Deep learning enables many more scenarios using sound, images, text and other data types. Learn how to build an Image Classification model to classify flowers (daisies, roses etc.).

Follow Pranav Rastogi: https://twitter.com/rustd

Watch the entire series here: https://aka.ms/dotnet3-mlnet
Download Visual Studio 2019 here: https://aka.ms/VisualStudio-dotnetconf19
Download .NET Core 3.0 here: https://aka.ms/Dotnet3

Learn more about ML .NET:
Image classification with ML.NET: https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/image-classification?&WT.mc_id=Educationalmlnet-c9-niner
What is Model Builder and how does it work? https://docs.microsoft.com/en-us/dotnet/machine-learning/automate-training-with-model-builder?&WT.mc_id=Educationalmlnet-c9-niner
ML.NET Model Builder: https://dotnet.microsoft.com/apps/machinelearning-ai/ml-dotnet/model-builder?&WT.mc_id=Educationalmlnet-c9-niner
Get started with ML.NET: https://dotnet.microsoft.com/learn/ml-dotnet/get-started-tutorial/intro?&WT.mc_id=Educationalmlnet-c9-niner
GitHub Repo ML .NET: https://github.com/dotnet/machinelearning
GitHub Repo ML.NET Samples: https://github.com/dotnet/machinelearning-samples/blob/master/README.md

Follow us:
 Twitter: https://twitter.com/dotnet
Facebook: https://www.facebook.com/Dotnet/
Blogs: https://devblogs.microsoft.com/dotnet/?WT.mc_id=Educationalmlnet-c9-niner
Shows and Podcasts: https://channel9.msdn.com/Shows/On-NET/?&WT.mc_id=Educationalmlnet-c9-niner

Useful Links:
Learn .NET: https://dotnet.microsoft.com/learn?&WT.mc_id=Educationalmlnet-c9-niner
.NET Community: https://dotnet.microsoft.com/platform/community?&WT.mc_id=Educationalmlnet-c9-niner
.NET Documentation: https://docs.microsoft.com/en-us/dotnet/?&WT.mc_id=Educationalmlnet-c9-niner

A

In this video, we will take a look at the deep learning support in ml.net by building an image classification, model.

A

Deep learning with ml.net has enabled developers to.

A

Use machine learning across a wide variety of domains, all the way from sound, vision, text,.

A

Nlp, which is natural language processing,, and a lot more.

A

So now you can use deep learning to classify or understand sounds,.

A

You can classify music,, you can predict music or music notes,.

A

You can understand vision, so you.

A

Can classify images or you can detect objects.

A

If it is going to make online cataloging.

A

Or inventory management, much more easier,.

A

It can also understand text., so you can do semantic, or analysis, or you can do entity recognition,.

A

Or you can do sentiment, analysis, or you can do price prediction, or you can classify documents,, and you can also teach machines to learn as well.

A

So deep learning has opened up a large set.

A

Of scenarios that were not possible before.

A

Image classification is a very popular example of deep learning.

A

Simply put, image classification allows.

A

You to classify images into one or more category.

A

In this example,, what we're doing is we are classifying.

A

Images into whether the image.

A

Is a flower and we're categorizing the type of flower,.

A

Whether it's daisy,, a rose, or a tulip.

A

The way to build a model with deep learning is around,.

A

You have your input data, which is your training data.

A

Which has lots of images which we have labeled in folders,.

A

And we feed all these images into a training process which is going to train a custom model.

A

For you that you can use to predict.

A

What category of flower does a particular image belong to.

A

So, let's see an example of how can we.

A

Build custom model for image classification.

A

This is a console app where I'll.

A

Build this machine learning model or this deep learning, model.

A

What I have over here is a dataset where I have went ahead and captured a bunch of flower images and I've categorized them into each flower. Type.

A

So here it's a folder of daisy, which has all pictures of a daisy, flower.

A

Here's a picture of dandelion which has all pictures of dandelion.

A

Here's a picture of folder of rose which has all the roses pictures.

A

What we're going to do in this example is we're going to.

A

Train the model on this data set.

A

So it's going to understand all characteristics of what.

A

Makes this flower a daisy flower or not and.

A

Then we're going to use the trained model on entirely new data to predict. What's going to be the flower type.

A

As we have learned in the ml.net journey,.

A

The first step is to create an ml context., so you can create a context.. The second step is around loading, the images..

A

So here I'm loading all the images that I just showed you from this flower photos, folder.

A

The next step is around choosing.

A

Your algorithm and specifying your label,.

A

Column, or the column to predict.

A

in this case,, what I'm doing is the label key is basically the image path.

A

Or the folder names and then the model I'm going to choose is a resonate model..

A

So in this case, I'm doing transfer learning where I'm using one of.

A

These pre-built models from the ecosystem to build a model for my own scenario.

A

Once I have defined this pipeline,, I can go ahead and call pipeline.fit which is going to train this model, and then I.

A

Can evaluate the model by printing out the metrics.

A

Of what was the accuracy of the model like.?

A

The last step is around trying the model which is creating a prediction engine and then.

A

Calling the predict function on one of the images that I.

A

Have in my image for a prediction, folder.

A

So let's go ahead and run this app and then see how the model was.

A

Trained and how does it perform on my test dataset as well.

A

So let's go ahead and start this application.

A

So what's happening behind the scenes in the training process.

A

Is this program is taking all the images and it's.

A

Extracting all the features from all the images and then it's going to run.

A

A classification algorithm at the end of the process to.

A

Classify all these images into one of the many categories.

A

So what has happened so far is now.

A

The training process is about to finish, and we get some output metrics over here, where the accuracy of the model was around.

A

83 percent, with some helpful guide that the closer to one it is the better it is.

A

What you're seeing over here is the model was run on some images.

A

In this case,, the model was also run on this rare flower picture, which looks like a rose over here.

A

Then, what the output of the model.

A

Or the prediction was a label of rows with.

A

A confidence, level or accuracy level of.

A

62 percent that it's a rose.

A

So what we find over here was.

A

A program to use deep learning to train an image classification, model.

A

This concludes our series on ml.net..

A

I hope you learned a lot about machine learning and are excited to use machine learning in your apps. be sure to check out our other series on c#.net,, asp.net, and more.