課程資料
- 可獲發
- *證書的發放與分配,依課程提供者的政策及安排而定。
課程簡介
Train image classification, object detection & regression models in Python, convert to TensorFlow Lite & use in Flutter
Build AI-Powered Mobile Apps with Flutter & TensorFlow Lite
Do you want to train custom Machine Learning models and bring them to life in real Android & iOS apps? This course takes you from zero to building smart, predictive, and vision-powered Flutter apps — all using TensorFlow Lite.
What You’ll Learn
Train Image Classification, Object Detection, and Regression models in Python from scratch.
Convert trained models to TensorFlow Lite for mobile use.
Integrate ML models into Flutter apps for Android & iOS.
Use ML Kit for object detection in real-time camera feeds.
Build real projects like:
House Price Prediction
Fuel Efficiency Estimator
Custom Image Classification App
Object Detection App with live camera feed
Course Outline
ML & AI Basics – Learn core concepts, neural networks, and deep learning.
Data Preparation – Use NumPy, Pandas, and Matplotlib for dataset handling.
Model Training – Train regression and vision models with TensorFlow.
TensorFlow Lite Conversion – Make your models mobile-ready.
Flutter Integration – Load and use models in Android & iOS apps.
Real Projects – Step-by-step guided apps for real-world use cases.
Who Is This For?
Flutter developers who want to integrate AI into their apps.
Beginners in ML who want practical, mobile-focused projects.
Developers aiming to expand their portfolio with AI-driven apps.
By the end of this course, you’ll be able to train, convert, and deploy your own ML models into beautiful Flutter apps — ready for the Play Store or App Store.
課程章節
- 21 個章節
- 139 堂課
- 第 1 章 Introduction
- 第 2 章 Machine Learning & Deep Learning for Flutter
- 第 3 章 Python Programming Language for Flutter
- 第 4 章 Data Science Libraries for Flutter
- 第 5 章 Tensorflow & Tensorflow Lite for Flutter
- 第 6 章 Training a basic regression model for Flutter
- 第 7 章 Setup for MacOS
- 第 8 章 Setup for Windows
- 第 9 章 Using First Regression Model in Flutter
- 第 10 章 Training a Fuel Efficiency Prediction Model for Flutter
- 第 11 章 Fuel Efficiency Prediction Flutter Application
- 第 12 章 Training House Price Prediction Model for Flutter
- 第 13 章 House Price Prediction Flutter Application
- 第 14 章 Training Our First Image Classification Model for Flutter
- 第 15 章 Training Models for Flutter Using Transfer Learning in Google Colab
- 第 16 章 Choosing or Capturing Images in Flutter on Android & IOS
- 第 17 章 Using Image Classification Models in Flutter With Images
- 第 18 章 Displaying live camera footage in Flutter
- 第 19 章 Realtime Image Classification in Flutter
- 第 20 章 Object Detection In Flutter With Images
- 第 21 章 Realtime Object Detection In Flutter
課程內容
- Train Machine Learning models for Flutter Applications
- Train Image Classification and Object Detection Models for Flutter Apps
- Train Linear Regression Models for Flutter Apps
- Integrate Tensorflow Lite models in Flutter for both Android & IOS
- Use Computer Vision Models in Flutter with both Images and Live Camera Footage
- Train a machine learning model and build a fuel efficiency prediction Flutter Application
- Train a machine learning model and build a house price prediction Flutter Application
- Analysing & using advance regression models in Flutter Applications
- Train Any Prediction Model & use it in Flutter Applications
- Data Collection & Preprocessing for ML model training for Flutter Application
- Basics of Machine Learning & Deep Learning for training Machine learning Models for Flutter
- Understand the working of artificial neural networks for training machine learning for Flutter
- Basic syntax of Python programming language to train ML models for Flutter
- Use of data science libraries like numpy, pandas and matplotlib
- Train a fruit classification model and build a Fruit Recognition Flutter Application
此課程所涵蓋的技能
評價
-
VVolkan Usanmaz
I got really good information about ML and ML libraries and learned some python code except flutter This course is good to have on your library
-
PPiyush Kumar Singh
no really!! As your pronanounciation was not correct for many time. Also you every time chose shortcut to teach various concept without thinking that the user have understood or not
-
BBridgerland Web Development
Some things were out of date to the point that the videos could not be easily followed.
-
GGabriel Laurito
I had been trying implement ML Object Detection on my own, and it was quite hard. This course explain super clear and easy all step to reach it.