Chapters
Chapters

Chapters

Hide chapters

Machine Learning by Tutorials

Second Edition · iOS 13 · Swift 5.1 · Xcode 11

Before You Begin

Section 0: 3 chapters
Show chapters Hide chapters

Section I: Machine Learning with Images

Section 1: 10 chapters
Show chapters Hide chapters

Section II: Machine Learning with Sequences

Section 2: 3 chapters
Show chapters Hide chapters

Section III: Natural Language Processing

Section 3: 5 chapters
Show chapters Hide chapters

5. Digging Deeper into Turi Create
Written by Audrey Tam & Matthijs Hollemans

Heads up... You’re accessing parts of this content for free, with some sections shown as scrambled text.

Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.

Unlock now

Heads up... You’re accessing parts of this content for free, with some sections shown as scrambled text.

Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.

Unlock now

In this chapter, you’ll use the SqueezeNet base model to train the snacks classifier, then explore more ways to evaluate its results.

You’ll also try to improve the model’s accuracy, first with more iterations, then by tweaking some of the underlying Turi Create source code. The SqueezeNet model overfits at a much lower training accuracy than VisionFeaturePrint_Screen, so any improvements will be easier to see.

You’ll also use the Netron tool to view the model — a SqueezeNet-based model has a lot more inside it than the Create ML version from last chapter.

Getting started

You can continue to use the turienv environment, Jupyter notebook, and snacks dataset from the previous chapter, or start fresh with the DiggingDeeper_starter notebook in this chapter’s starter folder.

If you skipped Chapter 4, “Getting Started with Python & Turi Create,” the quickest way to set up the turienv environment is to perform these commands from a Terminal window:

$ cd /path/to/chapter/resources
$ conda env create --file=starter/turienv.yaml
$ conda activate turienv
$ jupyter notebook

In the web browser window that opens, navigate to the starter/notebook folder for this chapter, and open DiggingDeeper_starter.ipynb.

If you downloaded the snacks dataset for a previous chapter, copy or move it into starter/notebook. Otherwise, double-click starter/notebook/snacks-download-link.webloc to download and unzip the snacks dataset in your default download location, then move the snacks folder into starter/notebook.

Note: In this book we’re using Turi Create version 5.6. Other versions may give different results or even errors. This is why we suggest using the turienv that comes with the book.

Transfer learning with SqueezeNet

If you’re not continuing from the previous chapter’s notebook, then run the following cells one by one.

Getting individual predictions

So far, you’ve just repeated the steps from the previous chapter. The evaluate() metrics give you an idea of the model’s overall accuracy but you can get a lot more information about individual predictions. Especially interesting are predictions where the model is wrong, but has very high confidence that it’s right. Knowing where the model is wrong can help you improve your training dataset.

Sso atvarujyise evaqeapeol xeynuc
Bho ibyafildoji ixuvoezean kostah

Predicting and classifying

Turi Create models have other functions, in addition to evaluate(). Enter and run these commands in the next cell, and wait a while:

xwamax?
bkagid?

Jci pael ah dke DMxaqo boyw yqanxudiluliuf ficuqpn
Wvo taiv es jfu LBlofu sucd cnothugurumiiw mevemcw

Xomouxhb otccockers bzo qwahhazanevior fewovpg
Mobeiggz evpfotfotl yli ykojdocegaraur jumedlw

Unmqonmilx hfu lixcunok tkibraquhabaod facokdm
Eyrsikwozg qka cuptosub gvepdahimumeay rinuscq

Sorting the prediction probabilities

Turi Create’s predict() method can also give you the probability distribution for each image. Enter and run these lines, then wait a while:

Puv xuka jyifofumiqeaz duw jgu zevepj azapo.
Gol wage cfepunasulioj fuw vmu widovq umana.

Using a fixed validation set

Turi Create extracts a random validation dataset from the training dataset — 5% of the images. The problem with using a small random validation set is that sometimes you get great results, but only because — this time! — the validation dataset just happens to be in your favor.

Increasing max iterations

So, is a validation accuracy of 63% good? Meh, not really. Turi Create knows it, too — at the end of the training output it says:

Confusing apples with oranges?

Kvu dusqivoej yuwzam
Gje bedfabuef horzaz

Computing recall for each class

Turi Create’s evaluate() function gives you the overall test dataset accuracy but, as mentioned in the AI Ethics section of the first chapter, accuracy might be much lower or higher for specific subsets of the dataset. With a bit of code, you can get the accuracies for the individual classes from the confusion matrix:

Training the classifier with regularization

A typical hyperparameter that machine learning practitioners like to play with is the amount of regularization that’s being used by the model. Regularization helps to prevent overfitting. Since overfitting seemed to be an issue for our model, it will be instructive to play with this regularization setting.

Wrangling Turi Create code

Saving the extracted features

Wouldn’t it be nice if there was a way we could save time during the training phase, and not have to continuously regenerate the features extracted by SqueezeNet? Well, as promised, in this section, you’ll learn how to save the intermediate SFrame to disk, and reload it, just before experimenting with the classifier.

Inspecting the extracted features

Let’s see what these features actually look like — enter and run this command:

Kka niek ek mte uwyxiscip ziujiqil zugwe
Mse fual uv xpu ebvcihmoc fuayugoc kecci

Training the classifier

Now you’re ready to train the classifier! Enter and run this statement:

Saving the model

You can save the model as a Turi Create model:

A peek behind the curtain

SqueezeNet and VisionFeaturePrint_Screen are convolutional neural networks. In the coming chapters, you’ll learn more about how these networks work internally, and you’ll see how to build one from scratch. In the meantime, it might be fun to take a peek inside your Core ML model.

Atoqm Qunbok ge efijavu xho .bqlecoy qema
Upexd Besxez jo odigose dlu .tjriwoc rezi

Challenges

Challenge 1: Binary classifier

Remember the healthy/unhealthy snacks model? Try to train that binary classifier using Turi Create. The approach is actually very similar to what you did in this chapter. The only difference is that you need to assign the label “healthy” or “unhealthy” to each row in the training data SFrame.

Challenge 2: ResNet50-based model

Train the 20-class classifier using the ResNet-50 model and see if that gets a better validation and test set score. Use model_type="resnet-50" when creating the classifier object. How many FPS does this get in the app compared to the SqueezeNet-based model?

Challenge 3: Use another dataset

Create your own training, validation, and test datasets from Google Open Images or some other image source. I suggest keeping the number of categories limited.

Key points

4. Getting Started with Python & Turi Create
6. Taking Control of Training with Keras
Have a technical question? Want to report a bug? You can ask questions and report bugs to the book authors in our official book forum here.
© 2026 Kodeco Inc.

You’re accessing parts of this content for free, with some sections shown as scrambled text. Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.

Unlock now