Android 11 TensorFlow lite and Firebase Machine Learning Kit, Develop Machine Learning Models, and 20+ Android applications using Machine Learning
This is the complete course on Android machine learning for 2021.
You will learn how to use machine learning in Android as well as training your own image recognition models for Android applications without any prior knowledge of machine learning. Because The Complete 2021 Android Machine Learning Course is designed this way, you don’t need a prior understanding of machine learning.
Mobile app development in modern times is impossible without using machine learning. It is rare to see an application without the use of ML. We need to learn how to integrate ML models into Android apps, so that we can make sure they perform well. You will learn that in this Complete 2021 Android Machine Learning Course. A major benefit of this is that you do not need to know anything about machine learning to integrate it into your Android applications.
The Complete 2021 Android Machine Learning Course is divided into four main parts.
- Image and live camera footage
- Pre-Trained Tensorflow Lite models use in Android
- Firebase ML Kit use in Android
- Training Image Classification models for Android
1: Images and live camera footage
In the first section, you will learn how to handle images as well as live camera footage in Android so that later we can use them with machine learning models. We’ll learn how to do those things in that section
- Choose images from the gallery in Android
- Capture images using the camera in Android
- Displaying live camera footage in Android applications using camera2 API
- Accessing frames of live camera footage in Android
2: Pre-Trained Tensorflow Lite
We will learn in this section how to use pre-trained machine learning models in Android after learning how to use images and live camera footage in the previous section.
- Image classification (Both with images and live camera footage)
- Object detection (Both with images and live camera footage)
- Image segmentation
3: Quantization and Delegates
Apart from that, we will cover all the important concepts related to Tensorflow lite like
- Using floating-point and quantized model in Android
- Use the use of Tensorflow lite Delegates to improve model performance
4: Regression In Android
After that, we will learn to use regression models in Android and build a couple of applications including a
- Fuel Efficiency Predictor for Vehicles.
5: Firebase ML Kit
Then the next section is related to the Firebase ML Kit. In this section, we will explore
- Firebase ML Kit
- Features of Firebase ML Kit
Then we are going to explore those features and build a number of applications including
- Image Labeling Android to recognize different things
- Barcode Scanning Android to scan barcodes and QR codes
- Pose Estimation Android to detect human body joints
- Selfie Segmentation Android to separate the background from the foreground
- Digital Ink Recognition Android to recognize handwritten text
- Object Detection Android to detect and track objects
- Text Recognition Android to recognize text in images
- Smart Reply Android to add auto reply suggestion
- Text Translation Android to translate between different languages
- Face Detection Android to detect faces, facial landmarks, and facial expressions
We will also be developing a clone of the popular document scanning application CamScanner in addition to these applications. In that application, we will automatically crop documents based on their text content and improve the visibility of documents.
6: Training Image Classification Models
As part of the third section, we will learn how to train our own Image Classification models without any prior knowledge of Machine Learning.
So in that section, we will learn to train ML models using two different approaches.
Dog breed Recognition using Teachable Machine
- Firstly we will train a dog breed recognition model using a teachable machine.
- Build a Live Feed Dog Breed Recognition Android Application.
Fruit Recognition using Transfer Learning
- Using transfer learning we will retrain the MobileNet model to recognize different fruits.
- Build a live feed fruit recognition Android application using that trained model
Images and Live Camera Footage
During The Complete 2021 Android Machine Learning Coursethis course, you will learn how to use Machine Learning models with images and live camera footage, so you can create simple and live feed Android applications.
The course is completely up to date and we have used the latest Android 11 throughout The Complete 2021 Android Machine Learning Course.
Programming languages Java and Kotlin are used in the development of The Complete 2021 Android Machine Learning Course. In other words, everything is available in English and Spanish.
These are tools we will be using throughout The Complete 2021 Android Machine Learning Course
- Android Studio to develop Android Applications
- Google collab to train Image Recognition models.
- Netron to analyze mobile machine learning models
By the end of The Complete 2021 Android Machine Learning Course, you will be able
- Use Firebase ML kit inside Android applications using both Java and Kotlin
- Use pre-trained Tensorflow lite models inside Android & IOS applications using Java and Kotlin
- Train your own Image classification models and build Android applications.
Furthermore, you will have a portfolio of over 20+ machine learning-based Android applications that you can show potential employers.
This is The Complete 2021 Android Machine Learning Course for you if
- You want to make smart Android apps
- You are interested in becoming a modern-day Android developer, a freelancer, launching your own projects, or just want to try your hand at making real smart mobile apps
- You have no prior programming experience, or some but from a different language/platform
- You want a course that teaches you the use of machine learning and computer vision in Android app development, in an integrated curriculum that will give you a deep understanding of all the key concepts an Android developer needs to know to have a successful career
Who can take this course:
- Beginner Android ( Java or Kotlin ) developer with very little knowledge of Android app development.
- Intermediate Android ( Java or Kotlin ) developer wanted to build a powerful Machine Learning-based application in Android
- Experienced Android ( Java or Kotlin ) developers wanted to use Machine Learning models inside their Android applications.
- Anyone who took a basic Android ( Java or Kotlin ) mobile app development course before (like Android ( Java or Kotlin ) app development course by angela yu or other such courses).
Unlike any other Android app development course, The Complete 2021 Android Machine Learning Course will teach you what matters the most.
So what are you waiting for? Click on the Join button and start learning.
Who this course is for:
- Beginner Android Developer curious about Machine learning and computer vision use in Android
- Intermediate Android developers looking to enhance their skillset
- Experienced Professional want to integrate Machine Learning in their Android Applications
What you’ll learn
- Learn use of machine learning and computer vision models in Android to build beautiful real world smart android applications
- Learn to train Image Recognition models without knowing any background knowledge of machine learning
- Use computer vision models in Android with Images and Live Camera Footage
- Use of Tensorflow lite models in Android Applications
- Use of Tensorflow lite delegates to improve model performance
- Use of Floating point and quantized models in Android
- Build Cam Scanner clone
- Add smart reply, selfie segmentation, text translation, face detection, text recognition, pose estimation in Android
- Use of Firebase ML Kit in Android and the Features it Provides
- Build live feed image classification and object detection applications
- Recognize hand written text in Android using Digital Ink Recognition
- 20+ Machine Learning based Android Application
Created by Hamza Asif
Last updated 8/2021
Size: 7.9 GB