Description

Use deep learning, Computer Vision, and machine learning techniques to build an autonomous car with Python

Self-driving cars have emerged to be one of the most transformative technologies. Fueled by deep learning algorithms, they are rapidly developing and creating new opportunities in the mobility sector. Deep learning jobs command some of the highest salaries in the development world. This is the first and one of the only courses that make practical use of deep learning and applies it to building a self-driving car. You'll learn and master deep learning in this fun and exciting course with top instructor Rayan Slim. Having trained thousands of students, Rayan is a highly rated and experienced instructor who follows a learning-by-doing approach. By the end of the course, you will have built a fully functional self-driving car powered entirely by deep learning. This powerful simulation will impress even the most senior developers and ensure you have hands-on skills in neural networks that you can bring to any project or company. This course will show you how to do the following:
- Use Computer Vision techniques via OpenCV to identify lane lines for a self-driving car
- Train a perceptron-based neural network to classify between binary classes
- Train convolutional neural networks to identify various traffic signs
- Train deep neural networks to fit complex datasets
- Master Keras, a power neural network library written in Python
- Build and train a fully functional self-driving car All the code and supporting files for this course are available at https://github.com/PacktPublishing/The-Complete-Self-Driving-Car-Course---Applied-Deep-Learning

What You Will Learn

Apply Computer Vision and deep learning techniques to build automotive-related algorithms
Understand, build, and train convolutional neural networks with Keras.
Simulate a fully functional self-driving car with convolutional neural networks and Computer Vision
Train a deep learning model that can identify up to 43 different traffic signs
Use essential Computer Vision techniques to identify lane lines on a road
Build and train powerful neural networks with Keras
Understand neural networks at the most fundamental, perceptron-based level

Audience

This course is for anyone with an interest in deep learning and Computer Vision. Anyone (no matter the skill level) who wants to transition into the field of artificial intelligence, including entrepreneurs with an interest in working on some of the most cutting-edge technologies, will find this course useful.

Approach

This is the first, and the only, course that makes practical use of deep learning, and applies it to building a self-driving car, one of the most disruptive technologies in the world today. This course is designed to help students with no experience in programming or mathematics become accomplished, deep learning developers.

Key Features

The transition from a beginner to deep learning expert * Learn through demonstrations as your instructor completes each task with you * No experience required

Github Repo

https://github.com/packtpublishing/the-complete-self-driving-car-course---applied-deep-learning

Course Outline

1. Introduction

In this section, the author suggest as to why we should take the course.

1. Why This Course?

Introduction: Why This Course?

2. Installation

In this section, we look into installation on Mac and Windows.

1. Overview

Installation: Overview

2. Anaconda Distribution - Mac

Installation: Anaconda Distribution - Mac

3. Anaconda Distribution - Windows

Installation: Anaconda Distribution - Windows

4. Text Editor

Installation: Text Editor

5. Outro

Installation: Outro

3. Python Crash Course

In this section, the author covers Python and provides a crash course on this.

1. Python Crash Course Part 1 - Data Types

Python Crash Course: Python Crash Course Part 1 - Data Types

2. Jupyter Notebooks

Python Crash Course: Jupyter Notebooks

3. Arithmetic Operations

Python Crash Course: Arithmetic Operations

4. Variables

Python Crash Course: Variables

5. Numeric Data Types

Python Crash Course: Numeric Data Types

6. String Data Types

Python Crash Course: String Data Types

7. Booleans

Python Crash Course: Booleans

8. Methods

Python Crash Course: Methods

9. Lists

Python Crash Course: Lists

10. Slicing

Python Crash Course: Slicing

11. Membership Operators

Python Crash Course: Membership Operators

12. Mutability

Python Crash Course: Mutability

13. Mutability II

Python Crash Course: Mutability II

14. Common Functions & Methods

Python Crash Course: Common Functions & Methods

15. Tuples

Python Crash Course: Tuples

16. Sets

Python Crash Course: Sets

17. Dictionaries

Python Crash Course: Dictionaries

18. Compound Data Structures

Python Crash Course: Compound Data Structures

19. Part 1 - Outro

Python Crash Course: Part 1 - Outro

20. Part 2 - Control Flow

Python Crash Course: Part 2 - Control Flow

21. If, else

Python Crash Course: If, else

22. elif

Python Crash Course: elif

23. Complex Comparisons

Python Crash Course: Complex Comparisons

24. For Loops

Python Crash Course: For Loops

25. For Loops II

Python Crash Course: For Loops II

26. While Loops

Python Crash Course: While Loops

27. Break

Python Crash Course: Break

28. Part 2 - Outro

Python Crash Course: Part 2 - Outro

29. Part 3 - Functions

Python Crash Course: Part 3 - Functions

30. Functions

Python Crash Course: Functions

31. Scope

Python Crash Course: Scope

32. Doc Strings

Python Crash Course: Doc Strings

33. Lambda & Higher Order Functions

Python Crash Course: Lambda & Higher Order Functions

34. Part 3 - Outro

Python Crash Course: Part 3 - Outro

4. NumPy Crash Course

In this section, the author provides a crash course on NumPy.

1. Overview

NumPy Crash Course: Overview

2. Vector Addition - Arrays vs Lists

NumPy Crash Course: Vector Addition - Arrays vs Lists

3. Multidimensional Arrays

NumPy Crash Course: Multidimensional Arrays

4. One Dimensional Slicing

NumPy Crash Course: One Dimensional Slicing

5. Reshaping

NumPy Crash Course: Reshaping

6. Multidimensional Slicing

NumPy Crash Course: Multidimensional Slicing

7. Manipulating Array Shapes

NumPy Crash Course: Manipulating Array Shapes

8. Matrix Multiplication

NumPy Crash Course: Matrix Multiplication

9. Stacking

NumPy Crash Course: Stacking

10. Part 4 - Outro

NumPy Crash Course: Part 4 - Outro

5. Computer Vision: Finding Lane Lines

In this section, learn to use Computer Vision techniques via OpenCV to identify lane lines for a self-driving car.

1. Overview

Computer Vision: Finding Lane Lines: Overview

2. Loading Image

Computer Vision: Finding Lane Lines: Loading Image

3. Grayscale Conversion

Computer Vision: Finding Lane Lines: Grayscale Conversion

4. Smoothening Image

Computer Vision: Finding Lane Lines: Smoothening Image

5. Simple Edge Detection

Computer Vision: Finding Lane Lines: Simple Edge Detection

6. Region of Interest

Computer Vision: Finding Lane Lines: Region of Interest

7. Binary Numbers & Bitwise_and

Computer Vision: Finding Lane Lines: Binary Numbers & Bitwise_and

8. Line Detection - Hough Transform

Computer Vision: Finding Lane Lines: Line Detection - Hough Transform

9. Hough Transform II

Computer Vision: Finding Lane Lines: Hough Transform II

10. Optimizing

Computer Vision: Finding Lane Lines: Optimizing

11. Finding Lanes on Video

Computer Vision: Finding Lane Lines: Finding Lanes on Video

12. Part 5 - Conclusion

Computer Vision: Finding Lane Lines: Part 5 - Conclusion

6. The Perceptron

In this section, learn to train a Perceptron-based Neural Network to classify between binary classes.

1. Overview

The Perceptron: Overview

2. Machine Learning

The Perceptron: Machine Learning

3. Supervised Learning - Friendly Example

The Perceptron: Supervised Learning - Friendly Example

4. Classification

The Perceptron: Classification

5. Linear Model

The Perceptron: Linear Model

6. Perceptrons

The Perceptron: Perceptrons

7. Weights

The Perceptron: Weights

8. Project - Initial Stages

The Perceptron: Project - Initial Stages

9. Error Function

The Perceptron: Error Function

10. Sigmoid

The Perceptron: Sigmoid

11. Sigmoid Implementation (Code)

The Perceptron: Sigmoid Implementation (Code)

12. Cross Entropy

The Perceptron: Cross Entropy

13. Cross Entropy (Code)

The Perceptron: Cross Entropy (Code)

14. Gradient Descent

The Perceptron: Gradient Descent

15. Gradient Descent (Code)

The Perceptron: Gradient Descent (Code)

16. Recap

The Perceptron: Recap

17. Part 6 - Conclusion

The Perceptron: Part 6 - Conclusion

7. Keras

In this section, master Keras, a power Neural Network library written in Python.

1. Overview

Keras: Overview

2. Intro to Keras

Keras: Intro to Keras

3. Keras Models

Keras: Keras Models

4. Keras - Predictions

Keras: Keras - Predictions

5. Part 7 - Outro

Keras: Part 7 - Outro

8. Deep Neural Networks

In this section, train in Deep Neural Networks to fit complex datasets.

1. Overview

Deep Neural Networks: Overview

2. Non-Linear Boundaries

Deep Neural Networks: Non-Linear Boundaries

3. Architecture

Deep Neural Networks: Architecture

4. Feedforward Process

Deep Neural Networks: Feedforward Process

5. Error Function

Deep Neural Networks: Error Function

6. Backpropagation

Deep Neural Networks: Backpropagation

7. Code Implementation

Deep Neural Networks: Code Implementation

8. Conclusion

Deep Neural Networks: Conclusion

9. Multiclass Classification

In this section, we look into classification through Softmax, cross entropy.

1. Overview

Multiclass Classification: Overview

2. Softmax

Multiclass Classification: Softmax

3. Cross Entropy

Multiclass Classification: Cross Entropy

4. Implementation

Multiclass Classification: Implementation

5. Outro

Multiclass Classification: Outro

10. MNIST Image Recognition

In this section, we look into image recognition through Hyperparmters.

1. Overview

MNIST Image Recognition: Overview

2. MNIST Dataset

MNIST Image Recognition: MNIST Dataset

3. Train & Test

MNIST Image Recognition: Train & Test

4. Hyperparameters

MNIST Image Recognition: Hyperparameters

5. Implementation Part 1

MNIST Image Recognition: Implementation Part 1

6. Implementation Part 2

MNIST Image Recognition: Implementation Part 2

7. Implementation Part 3

MNIST Image Recognition: Implementation Part 3

8. Section 10 - Outro

MNIST Image Recognition: Section 10 - Outro

11. Convolutional Neural Networks

In this section, simulate a fully functional Self-Driving Car with Convolutional Neural Networks and Computer Vision.

1. Overview

Convolutional Neural Networks: Overview

2. Convolutions & MNIST

Convolutional Neural Networks: Convolutions & MNIST

3. Convolutional Layer

Convolutional Neural Networks: Convolutional Layer

4. Convolutions II

Convolutional Neural Networks: Convolutions II

5. Pooling

Convolutional Neural Networks: Pooling

6. Fully Connected Layer

Convolutional Neural Networks: Fully Connected Layer

7. Code Implementation I

Convolutional Neural Networks: Code Implementation I

8. Code Implementation II

Convolutional Neural Networks: Code Implementation II

9. Section 11 - Conclusion

Convolutional Neural Networks: Section 11 - Conclusion

12. Classifying Road Symbols

In this section, train a Deep Learning Model that can identify between 43 different Traffic Signs.

1. Overview

Classifying Road Symbols: Overview

2. Preprocessing Images

Classifying Road Symbols: Preprocessing Images

3. leNet Implementation

Classifying Road Symbols: leNet Implementation

4. Fine-tuning Model

Classifying Road Symbols: Fine-tuning Model

5. Testing

Classifying Road Symbols: Testing

6. Fit Generator

Classifying Road Symbols: Fit Generator

7. Section 12 - Outro

Classifying Road Symbols: Section 12 - Outro

13. Polynomial Regression

In this section, explore more on Polynomial regression.

1. Overview

Polynomial Regression: Overview

2. Implementation

Polynomial Regression: Implementation

3. Section 13 - Conclusion

Polynomial Regression: Section 13 - Conclusion

14. Behavioural Cloning

In this section, we collect data, download and balance data, preprocess images and define Nvidia Model.

1. Overview

Behavioural Cloning: Overview

2. Collecting Data

Behavioural Cloning: Collecting Data

3. Downloading Data

Behavioural Cloning: Downloading Data

4. Balancing Data

Behavioural Cloning: Balancing Data

5. Training & Validation Split

Behavioural Cloning: Training & Validation Split

6. Preprocessing Images

Behavioural Cloning: Preprocessing Images

7. Defining Nvidia Model

Behavioural Cloning: Defining Nvidia Model

8. Flask & Socket.io

Behavioural Cloning: Flask & Socket.io

9. Self Driving Car - Test 1

Behavioural Cloning: Self Driving Car - Test 1

10. Generator - Augmentation Techniques

Behavioural Cloning: Generator - Augmentation Techniques

11. Batch Generator

Behavioural Cloning: Batch Generator

12. Fit Generator

Behavioural Cloning: Fit Generator

13. Outro

Behavioural Cloning: Outro

Course Images

The Complete Self-Driving Car Course - Applied Deep Learning

By Packt

Booking options

Highlights

Description

Course Content

About The Provider

Tags

Reviews