Chapter 8. Fritz

We have gone through mobile machine learning SDKs offered by Google—TensorFlow for mobile—and Apple—Core ML—in the previous chapters and got a good understanding of them. We looked at the basic architecture of those products, the key features they offer, and also tried a few tasks/programs using those SDKs. Based on what we have explored on the mobile machine learning frameworks and tools so far, we will be able to identify a few gaps that make it difficult to carry out mobile machine learning deployments and subsequent maintenance and support of those deployments. Let me list a few for you:

• Once we create the machine learning model and import it into the Android or iOS application, if there is any change that needs to be done to the model that was imported into the mobile application, how do you think this change will be implemented and upgraded to the application that is deployed and being used in the field? How is it possible to update/upgrade the model without redeploying...

Introduction to Fritz

Fritz is a free end-to-end platform that enables us to create machine learning-powered mobile applications easily. It is a platform that enables on-device machine learning, that is, it helps to create mobile machine learning applications that can completely work on mobile devices. It supports both iOS and Android platforms.

Prebuilt ML models

Fritz provides built-in ML models that can be directly used in mobile applications. Here are the two important models that Fritz supports:

• Object detection: You can identify objects of interest in an image or each frame of a live video. This helps you to know what objects are in an image, and where they are within the image. The object-detection feature makes predictions completely on-device and requires no internet connection.
• Image labeling: You can identify the contents of an image or each frame of live video. This also works completely offline and requires no internet connection.

Ability to use custom models

Fritz provides us with...

Hand-on samples using Fritz

In this section, we will try using Fritz and the models that we've already created for iOS and Android using Core ML and TensorFlow for mobile and build iOS and Android mobile applications using Fritz. Along with this, we will see how to use the Fritz built-in models, such as object detection and image labeling.

Using the existing TensorFlow for mobile model in an Android application using Fritz

In this section, we are going to see how to use a TensorFlow for mobile model that we already have created in an Android mobile application using the Fritz toolkit. We are going to take the sample model that we created using TensorFlow for mobile to do the summation (a+b). We will go through the detailed steps required to achieve this objective.

Registering with Fritz

In order to use Fritz, you must sign up for an account at the Fritz web portal:

1. Go to https://fritz.ai/
2. Click on Login on the top menu 
3. Click on Create an account
4. Enter your details and submit
5. Create a new project...

Summary

In this chapter, we learned about Fritz, an end-to-end platform that enables us to create machine learning applications. We also looked at pre-built ML models and how to use custom models in Fritz. Then, we explored how we can implement Fritz in Core ML in iOS and Android. Finally, we created two applications using the Fritz library: one using a pre-built fritz model, and the other using a Core ML model for iOS. In the next chapter, we will learn about neural networks and their uses for mobile applications and machine learning.