Duration
21 hours (usually 3 days including breaks)
Requirements
- Experience with Swift programming
- Experience with mobile application development
- An iOS device running v12 or higher
Audience
- Developers
- Data scientists who wish to develop AI-enabled mobile applications on iOS
Overview
TensorFlow Lite is an open source deep learning framework for mobile devices and embedded systems.
This instructor-led, live training (online or onsite) is aimed at developers who wish to use TensorFlow Lite to develop iOS mobile applications with deep learning capabilities.
By the end of this training, participants will be able to:
- Install and configure TensorFlow Lite.
- Understand the principles behind TensorFlow and machine learning on mobile devices.
- Load TensorFlow Models onto an iOS device.
- Run an iOS application capable of detecting and classifying an object captured through the device’s camera.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Course Outline
Introduction
- Tensorflow vs Tensorflow Lite
Overview of TensorFlow Lite Features and Workflow
- Recap of machine learning and deep learning concepts
- How on-device low-latency inference is achieved
- End-to-end model building and deployment
Preparing the Development Environment
- Starting a Swift project
- Adding TensorFlow to the project
Capturing an Image with a Device Camera
- How camera input is captured
- Overview of classes and methods
- Running inference on a frame (performing image classification)
Creating an App for Object Detection
- Selecting a TensorFlow Model
- Converting the TensorFlow Model
- Loading the TensorFlow Model onto a Mobile Device
- Loading a Pre-trained TensorFlow Model
Creating an App for Image Classification
- Selecting a TensorFlow Model
- Converting the TensorFlow Model
- Loading the TensorFlow Model onto a Mobile Device
- Loading a Pre-trained TensorFlow Model
Customizing the Model and Data
- Pre-processing a dataset
- Setting the hyperparameters
Optimizing the TensorFlow Model
- Measuring performance against a benchmark
- Measuring accuracy
- Retraining a TensorFlow model
Exploring Alternative Models
- Choosing a different model
- Training a model to recognize new classes (transfer learning)
- Obtaining training images for new labels
Deploying the AI Enabled iOS App
- Performing image classification in the field
Troubleshooting
Summary and Conclusion