Deep Learning CNN: Convolutional Neural Networks with Python

Deep Learning CNN: Convolutional Neural Networks with Python

by AI Sciences
Released August 2022
Publisher(s): Packt Publishing
ISBN: 9781803243726

Watch it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

Convolutional Neural Networks (CNNs) are considered game-changers in the field of computer vision, particularly after AlexNet in 2012. They are everywhere now, ranging from audio processing to more advanced reinforcement learning. So, the understanding of CNNs becomes almost inevitable in all fields of data science. With this course, you can take your career to the next level with an expert grip on the concepts and implementations of CNNs in data science.

The course starts with introducing and jotting down the importance of Convolutional Neural Networks (CNNs) in data science. You will then look at some classical computer vision techniques such as image processing and object detection. It will be followed by deep neural networks with topics such as perceptron and multi-layered perceptron. Then, you will move ahead with learning in-depth about CNNs. You will first look at the architecture of a CNN, then gradient descent in CNN, get introduced to TensorFlow, classical CNNs, transfer learning, and a case study with YOLO.

Finally, you will work on two projects: Neural Style Transfer (using TensorFlow-hub) and Face Verification (using VGGFace2).

By the end of this course, you will have understood the methodology of CNNs with data science using real datasets. Apart from this, you will easily be able to relate the concepts and theories in computer vision with CNNs.

What You Will Learn

  • Understand the importance of CNNs in data science
  • Explore the reasons to shift from classical computer vision to CNNs
  • Learn concepts from the beginning with comprehensive unfolding with examples in Python
  • Study the evolutions of CNNs from LeNet (1990s) to MobileNets (2020s)
  • Deep-dive into CNNs with examples of training CNNs from scratch
  • Build your own applications for human face verification and neural style transfer

Audience

This course is designed for beginners in data science and deep learning. Any individual who wants to learn CNNs with real datasets in data science, learn CNNs along with its implementation in realistic projects, and master their data speak will gain a lot from this course.

No prior knowledge is needed. You start from the basics and slowly build your knowledge of the subject. A willingness to learn and practice is just the prerequisite for this course.

About The Author

AI Sciences: AI Sciences are experts, PhDs, and artificial intelligence practitioners, including computer science, machine learning, and Statistics. Some work in big companies such as Amazon, Google, Facebook, Microsoft, KPMG, BCG, and IBM.

AI sciences produce a series of courses dedicated to beginners and newcomers on techniques and methods of machine learning, statistics, artificial intelligence, and data science. They aim to help those who wish to understand techniques more easily and start with less theory and less extended reading. Today, they publish more comprehensive courses on specific topics for wider audiences.

Their courses have successfully helped more than 100,000 students master AI and data science.

Table of contents

  1. Chapter 1 : Introduction to the Course
    1. Course Overview
    2. Introduction to Instructor
    3. Why CNN
    4. Focus of the Course
  2. Chapter 2 : Image Processing
    1. Gray-Scale Images
    2. Gray-Scale Images Quiz
    3. Gray-Scale Images Solution
    4. RGB Images
    5. RGB Images Quiz
    6. RGB Images Solution
    7. Reading and Showing Images in Python
    8. Reading and Showing Images in Python Quiz
    9. Reading and Showing Images in Python Solution
    10. Converting an Image to Grayscale in Python
    11. Converting an Image to Grayscale in Python Quiz
    12. Converting an Image to Grayscale in Python Solution
    13. Image Formation
    14. Image Formation Quiz
    15. Image Formation Solution
    16. Image Blurring 1
    17. Image Blurring 1 Quiz
    18. Image Blurring 1 Solution
    19. Image Blurring 2
    20. Image Blurring 2 Quiz
    21. Image Blurring 2 Solution
    22. General Image Filtering
    23. Convolution
    24. Edge Detection
    25. Image Sharpening
    26. Implementation of Image Blurring Edge Detection Image Sharpening in Python
    27. Parametric Shape Detection
    28. Image Processing
    29. Image Processing Activity
    30. Image Processing Activity Solution
  3. Chapter 3 : Object Detection
    1. Introduction to Object Detection
    2. Classification Pipeline
    3. Classification Pipeline Quiz
    4. Classification Pipeline Solution
    5. Sliding Window Implementation
    6. Shift Scale Rotation Invariance
    7. Shift Scale Rotation Invariance Exercise
    8. Person Detection
    9. HOG Features
    10. HOG Features Exercise
    11. Hand Engineering Versus CNNs
    12. Object Detection Activity
  4. Chapter 4 : Deep Neural Network Overview
    1. Neuron and Perceptron
    2. DNN Architecture
    3. DNN Architecture Quiz
    4. DNN Architecture Solution
    5. FeedForward FullyConnected MLP
    6. Calculating Number of Weights of DNN
    7. Calculating Number of Weights of DNN Quiz
    8. Calculating Number of Weights of DNN Solution
    9. Number of Neurons Versus Number of Layers
    10. Discriminative Versus Generative Learning
    11. Universal Approximation Theorem
    12. Why Depth
    13. Decision Boundary in DNN
    14. Decision Boundary in DNN Quiz
    15. Decision Boundary in DNN Solution
    16. BiasTerm
    17. BiasTerm Quiz
    18. BiasTerm Solution
    19. Activation Function
    20. Activation Function Quiz
    21. Activation Function Solution
    22. DNN Training Parameters
    23. DNN Training Parameters Quiz
    24. DNN Training Parameters Solution
    25. Gradient Descent
    26. Backpropagation
    27. Training DNN Animation
    28. Weight Initialization
    29. Weight Initialization Quiz
    30. Weight Initialization Solution
    31. Batch MiniBatch Stochastic Gradient Descent
    32. Batch Normalization
    33. Rprop and Momentum
    34. Rprop and Momentum Quiz
    35. Rprop and Momentum Solution
    36. Convergence Animation
    37. DropOut, Early Stopping and Hyperparameters
    38. DropOut, Early Stopping and Hyperparameters Quiz
    39. DropOut, Early Stopping and Hyperparameters Solution
  5. Chapter 5 : Deep Neural Network Architecture
    1. Convolution Revisited
    2. Implementing Convolution in Python Revisited
    3. Why Convolution
    4. Filters Padding Strides
    5. Padding Image
    6. Pooling Tensors
    7. CNN Example
    8. Convolution and Pooling Details
    9. MaxPooling Exercise
    10. NonVectorized Implementations of Conv2d and Pool2d
    11. Deep Neural Network Architecture Activity
  6. Chapter 6 : Gradient Descent in CNNs
    1. Example Setup
    2. Why Derivatives
    3. Why Derivatives Quiz
    4. Why Derivatives Solution
    5. What Is Chain Rule
    6. Applying Chain Rule
    7. Gradients of MaxPooling Layer
    8. Gradients of MaxPooling Layer Quiz
    9. Gradients of MaxPooling Layer Solution
    10. Gradients of Convolutional Layer
    11. Extending to Multiple Filters
    12. Extending to Multiple Layers
    13. Extending to Multiple Layers Quiz
    14. Extending to Multiple Layers Solution
    15. Implementation in NumPy ForwardPass
    16. Implementation in NumPy BackwardPass 1
    17. Implementation in NumPy BackwardPass 2
    18. Implementation in NumPy BackwardPass 3
    19. Implementation in NumPy BackwardPass 4
    20. Implementation in NumPy BackwardPass 5
    21. Gradient Descent in CNNs Activity
  7. Chapter 7 : Introduction to TensorFlow
    1. Introduction to TensorFlow
    2. FashionMNIST Example Plan Neural Network
    3. FashionMNIST Example CNN
    4. Introduction to TensorFlow Activity
  8. Chapter 8 : Classical CNNs
    1. LeNet
    2. LeNet Quiz
    3. LeNet Solution
    4. AlexNet
    5. VGG
    6. InceptionNet
    7. GoogLeNet
    8. Resnet
    9. Classical CNNs Activity
  9. Chapter 9 : Transfer Learning
    1. What Is Transfer learning
    2. Why Transfer Learning
    3. ImageNet Challenge
    4. Practical Tips
    5. Project in TensorFlow
    6. Transfer Learning Activity
  10. Chapter 10 : YOLO
    1. Image Classification Revisited
    2. Sliding Window Object Localization
    3. Sliding Window Efficient Implementation
    4. YOLO Introduction
    5. YOLO Training Data Generation
    6. YOLO Anchor Boxes
    7. YOLO Algorithm
    8. YOLO Non-Maxima Suppression
    9. RCNN
    10. YOLO Activity
  11. Chapter 11 : Face Verification
    1. Problem Setup
    2. Project Implementation
    3. Face Verification Activity
  12. Chapter 12 : Neural Style Transfer
    1. Problem Setup
    2. Implementation TensorFlow Hub
    3. Thank You and Conclusion

Product information

  • Title: Deep Learning CNN: Convolutional Neural Networks with Python
  • Author(s): AI Sciences
  • Release date: August 2022
  • Publisher(s): Packt Publishing
  • ISBN: 9781803243726