Device-based models with TensorFlow Lite-Course Introduction
Introduction, A conversation with Andrew Ng
()
Prerequisites
Downloading the Ungraded Labs and Programming Assignments
Device-based models with TensorFlow Lite-Machine Learning Models in Mobile and Embedded Systems
A few words from Laurence
()
Features and components of mobile AI
()
Architecture and performance
()
GPU delegates
Optimization Techniques
()
Device-based models with TensorFlow Lite-Taking a look at the saved model format
Saving, converting, and optimizing a model
()
Examples
()
Quantization
()
TF-Select
()
Learn about supported ops and TF-Select
Paths in Optimization
()
Device-based models with TensorFlow Lite-First primer on running models on mobile devices
Running the models
()
Transfer learning
()
Converting a model to TFLite
()
Transfer learning with TFLite
()
Week 1 Wrap up
Device-based models with TensorFlow Lite-Lecture Notes (Optional)
Lecture Notes Week 1
Device-based models with TensorFlow Lite-Graded Exercise - Train Your Own Model and Convert It to TFLite
Exercise Description
Running a TF model in an Android App-Introduction
Introduction, A conversation with Andrew
()
Installation and resources
()
Android fundamentals and installation
Architecture of a model
()
Initializing the Interpreter
()
Preparing the Input
()
Inference and results
()
Running a TF model in an Android App-Basic image classification
Code walkthrough
()
Run the App
()
Running a TF model in an Android App-Classifying camera images
Classifying camera images
()
Initialize and prepare input
()
Running a TF model in an Android App-Code walkthrough - camera image classifier
Demo of camera image classifier
()
Running a TF model in an Android App-Object detection
Initialize model and prepare inputs
()
Inference and results
()
Running a TF model in an Android App-Code walkthrough of an object detection app
Demo of the object detection App
()
Code for the inference and results
()
Week 2 Wrap up
Running a TF model in an Android App-Lecture Notes (Optional)
Lecture Notes Week 2
Running a TF model in an Android App-Optional Exercise: Rock Paper Scissors for Android
Description
Building the TensorFLow model on IOS-Introduction
Introduction, A conversation with Andrew Ng
()
A few words from Laurence
()
What is Swift?
()
TensorFlowLiteSwift
()
Important links
Cats vs Dogs App
()
Taking the initial steps
()
Apple’s developer's site
Scaling the image
()
Apple's API
More steps in the process
()
Building the TensorFLow model on IOS-Next steps
Looking at the App in Xcode
()
What have we done so far and how do we continue?
()
Using the App
()
App architecture
()
Model details
()
More details
Initial steps
()
Camera related functionalities
Final steps
()
Building the TensorFLow model on IOS-Classification and detection
Looking at the code for the image classification App
()
Object classification intro
()
TFL detect App
()
App architecture
()
The Coco dataset
Initial steps
()
Final steps
()
Looking at the code for the object detection model
()
Week 3 Wrap up
Building the TensorFLow model on IOS-Lecture Notes (Optional)
Lecture Notes Week 3
Building the TensorFLow model on IOS-Optional Exercise - Rock, Paper, Scissors on iOS
Description
TensorFlow Lite on devices-Introduction
Introduction, A conversation with Andrew Ng
()
A few words from Laurence
()
Devices
()
Edge TPU models
TensorFlow Lite on devices-Example: Raspberry Pi
Starting to work on a Raspberry Pi
()
How do we start?
()
Options to choose from
Image classification
()
Pre optimized mobileNet
The 4 step process
()
Object detection
()
Object detection model trained on the coco
Back to the 4 step process
()
TensorFlow Lite on devices-Raspberry pi demo
Raspberry Pi demo
()
TensorFlow Lite on devices-Microcontrollers
Microcontrollers
()
Suggested links
[IMPORTANT] Reminder about end of access to Lab Notebooks
Closing words by Laurence
()
TensorFlow Lite on devices-Lecture Notes (Optional)
Lecture Notes Week 4
TensorFlow Lite on devices-Optional Exercise - Rock Paper Scissors on Raspberry Pi
Description
TensorFlow Lite on devices-Course 2 Wrap up
Wrap up
A conversation with Andrew Ng
()