English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 115 Lessons (17h 10m) | 5.94 GB
VGG, ResNet, Inception, SSD, RetinaNet, Neural Style Transfer, GANs +More in Tensorflow, Keras, and Python
Ever wondered how AI technologies like OpenAI ChatGPT, GPT-4, DALL-E, Midjourney, and Stable Diffusion really work? In this course, you will learn the foundations of these groundbreaking applications.
This is one of the most exciting courses I’ve done and it really shows how fast and how far deep learning has come over the years.
When I first started my deep learning series, I didn’t ever consider that I’d make two courses on convolutional neural networks.
I think what you’ll find is that, this course is so entirely different from the previous one, you will be impressed at just how much material we have to cover.
Let me give you a quick rundown of what this course is all about:
We’re going to bridge the gap between the basic CNN architecture you already know and love, to modern, novel architectures such as VGG, ResNet, and Inception (named after the movie which by the way, is also great!)
We’re going to apply these to images of blood cells, and create a system that is a better medical expert than either you or I. This brings up a fascinating idea: that the doctors of the future are not humans, but robots.
In this course, you’ll see how we can turn a CNN into an object detection system, that not only classifies images but can locate each object in an image and predict its label.
You can imagine that such a task is a basic prerequisite for self-driving vehicles. (It must be able to detect cars, pedestrians, bicycles, traffic lights, etc. in real-time)
We’ll be looking at a state-of-the-art algorithm called SSD which is both faster and more accurate than its predecessors.
Another very popular computer vision task that makes use of CNNs is called neural style transfer.
This is where you take one image called the content image, and another image called the style image, and you combine these to make an entirely new image, that is as if you hired a painter to paint the content of the first image with the style of the other. Unlike a human painter, this can be done in a matter of seconds.
I will also introduce you to the now-famous GAN architecture (Generative Adversarial Networks), where you will learn some of the technology behind how neural networks are used to generate state-of-the-art, photo-realistic images.
Currently, we also implement object localization, which is an essential first step toward implementing a full object detection system.
What you’ll learn
- Understand and apply transfer learning
- Understand and use state-of-the-art convolutional neural nets such as VGG, ResNet and Inception
- Understand and use object detection algorithms like SSD
- Understand and apply neural style transfer
- Understand state-of-the-art computer vision topics
- Class Activation Maps
- GANs (Generative Adversarial Networks)
- Object Localization Implementation Project
- Understand important foundations for OpenAI ChatGPT, GPT-4, DALL-E, Midjourney, and Stable Diffusion
Who this course is for:
- Students and professionals who want to take their knowledge of computer vision and deep learning to the next level
- Anyone who wants to learn about object detection algorithms like SSD and YOLO
- Anyone who wants to learn how to write code for neural style transfer
- Anyone who wants to use transfer learning
- Anyone who wants to shorten training time and build state-of-the-art computer vision nets fast
Table of Contents
Welcome
1 Introduction
2 Outline and Perspective
3 How to Succeed in this Course
Google Colab & Getting Setup
4 Where to get the code, notebooks, and data
5 Intro to Google Colab, how to use a GPU or TPU for free
6 Uploading your own data to Google Colab
7 Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn
8 Temporary 403 Errors
Machine Learning Basics Review
9 What is Machine Learning
10 Code Preparation (Classification Theory)
11 Beginner’s Code Preamble
12 Classification Notebook
13 Code Preparation (Regression Theory)
14 Regression Notebook
15 The Neuron
16 How does a model learn
17 Making Predictions
18 Saving and Loading a Model
19 Suggestion Box
Artificial Neural Networks (ANN) Review
20 Artificial Neural Networks Section Introduction
21 Forward Propagation
22 The Geometrical Picture
23 Activation Functions
24 Multiclass Classification
25 How to Represent Images
26 Color Mixing Clarification
27 Code Preparation (ANN)
28 ANN for Image Classification
29 ANN for Regression
Convolutional Neural Networks (CNN) Review
30 What is Convolution (part 1)
31 What is Convolution (part 2)
32 What is Convolution (part 3)
33 Convolution on Color Images
34 CNN Architecture
35 CNN Code Preparation
36 CNN for Fashion MNIST
37 CNN for CIFAR-10
38 Data Augmentation
39 Batch Normalization
40 Improving CIFAR-10 Results
VGG and Transfer Learning
41 VGG Section Intro
42 What’s so special about VGG
43 Transfer Learning
44 Relationship to Greedy Layer-Wise Pretraining
45 Approaches to Transfer Learning
46 Transfer Learning Code (pt 1)
47 Transfer Learning Code (pt 2)
48 VGG Section Summary
ResNet (and Inception)
49 ResNet Section Intro
50 ResNet Architecture
51 Transfer Learning with ResNet in Code
52 Blood Cell Images Dataset
53 How to Build ResNet in Code
54 x1 Convolutions
55 Optional – Inception
56 Different sized images using the same network
57 ResNet Section Summary
Object Detection (SSD – RetinaNet)
58 SSD Section Intro
59 Object Localization
60 What is Object Detection
61 How would you find an object in an image
62 The Problem of Scale
63 The Problem of Shape
64 SSD Tensorflow Object Detection API (pt 1)
65 SSD Tensorflow Object Detection API (pt 2)
66 SSD for Video Object Detection
67 Optional – Intersection over Union & Non-max Suppression
68 SSD Section Summary
Neural Style Transfer
69 Style Transfer Section Intro
70 Style Transfer Theory
71 Optimizing the Loss
72 Code pt 1
73 Code pt 2
74 Code pt 3
75 Style Transfer Section Summary
Class Activation Maps
76 Class Activation Maps (Theory)
77 Class Activation Maps (Code)
GANs (Generative Adversarial Networks)
78 GAN Theory
79 GAN Code
Object Localization Project
80 Localization Introduction and Outline
81 Localization Code Outline (pt 1)
82 Localization Code (pt 1)
83 Localization Code Outline (pt 2)
84 Localization Code (pt 2)
85 Localization Code Outline (pt 3)
86 Localization Code (pt 3)
87 Localization Code Outline (pt 4)
88 Localization Code (pt 4)
89 Localization Code Outline (pt 5)
90 Localization Code (pt 5)
91 Localization Code Outline (pt 6)
92 Localization Code (pt 6)
93 Localization Code Outline (pt 7)
94 Localization Code (pt 7)
Keras and Tensorflow 2 Basics Review
95 (Review) Tensorflow Basics
96 (Review) Tensorflow Neural Network in Code
97 (Review) Keras Discussion
98 (Review) Keras Neural Network in Code
99 (Review) Keras Functional API
100 (Review) How to easily convert Keras into Tensorflow 2.0 code
Course Conclusion
101 What to Learn Next
Appendix – FAQ Intro
102 What is the Appendix
Setting Up Your Environment (FAQ by Student Request)
103 Pre-Installation Check
104 Anaconda Environment Setup
105 How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
Extra Help With Python Coding for Beginners (FAQ by Student Request)
106 How to Code by Yourself (part 1)
107 How to Code by Yourself (part 2)
108 Proof that using Jupyter Notebook is the same as not using it
109 Python 2 vs Python 3
110 How to use Github & Extra Coding Tips (Optional)
Effective Learning Strategies for Machine Learning (FAQ by Student Request)
111 How to Succeed in this Course (Long Version)
112 Is this for Beginners or Experts Academic or Practical Fast or slow-paced
113 Machine Learning and AI Prerequisite Roadmap (pt 1)
114 Machine Learning and AI Prerequisite Roadmap (pt 2)
Appendix – FAQ Finale
115 BONUS
Resolve the captcha to access the links!
