TensorFlow Lite for iOS Training Course

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