English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 10 Hours | 2.36 GB
VGG, ResNet, Inception, SSD, RetinaNet, Neural Style Transfer, GANs +More in Tensorflow, Keras, and Python
Latest update: Instead of SSD, I show you how to use RetinaNet, which is better and more modern. I show you both how to use a pretrained model and how to train one yourself with a custom dataset on Google Colab.
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
Table of Contents
Welcome
1 Introduction
2 Outline and Perspective
3 How to Succeed in this Course
Review
4 Review of CNNs
5 Where to get the code and data
6 Fashion MNIST
7 Review of CNNs in Code
VGG and Transfer Learning
8 VGG Section Intro
9 What’s so special about VGG
10 Transfer Learning
11 Relationship to Greedy Layer-Wise Pretraining
12 Getting the data
13 Code pt 1
14 Code pt 2
15 Code pt 3
16 VGG Section Summary
ResNet (and Inception)
17 ResNet Section Intro
18 Building ResNet – Putting it all together
19 Exercise Apply ResNet
20 Applying ResNet
21 x1 Convolutions
22 Optional Inception
23 Different sized images using the same network
24 ResNet Section Summary
25 ResNet Architecture
26 Building ResNet – Strategy
27 Uh-oh! What Happens if the Implementation Changes
28 Building ResNet – Conv Block Details
29 Building ResNet – Conv Block Code
30 Building ResNet – Identity Block Details
31 Building ResNet – First Few Layers
32 Building ResNet – First Few Layers (Code)
Object Detection (SSD RetinaNet)
33 SSD Section Intro
34 RetinaNet with Custom Dataset (pt 1)
35 RetinaNet with Custom Dataset (pt 2)
36 RetinaNet with Custom Dataset (pt 3)
37 Optional Intersection over Union & Non-max Suppression
38 SSD Section Summary
39 Object Localization
40 What is Object Detection
41 How would you find an object in an image
42 The Problem of Scale
43 The Problem of Shape
44 Update – More Fun and Excitement
45 RetinaNet Notebooks
46 Using Pretrained RetinaNet
Neural Style Transfer
47 Style Transfer Section Intro
48 Style Transfer Theory
49 Optimizing the Loss
50 Code pt 1
51 Code pt 2
52 Code pt 3
53 Style Transfer Section Summary
Class Activation Maps
54 Class Activation Maps (Theory)
55 Class Activation Maps (Code)
GANs (Generative Adversarial Networks)
56 GAN Theory
57 GAN Colab Notebook
58 GAN Code
Object Localization Project
59 Localization Introduction and Outline
60 Localization Code (pt 4)
61 Localization Code Outline (pt 5)
62 Localization Code (pt 5)
63 Localization Code Outline (pt 6)
64 Localization Code (pt 6)
65 Localization Code Outline (pt 7)
66 Localization Code (pt 7)
67 Localization Code Outline (pt 1)
68 Object Localization Colab Notebooks
69 Localization Code (pt 1)
70 Localization Code Outline (pt 2)
71 Localization Code (pt 2)
72 Localization Code Outline (pt 3)
73 Localization Code (pt 3)
74 Localization Code Outline (pt 4)
Basics Review
75 (Review) Tensorflow Basics
76 (Review) Tensorflow Neural Network in Code
77 (Review) Keras Discussion
78 (Review) Keras Neural Network in Code
79 (Review) Keras Functional API
80 (Review) How to easily convert Keras into Tensorflow 2.0 code
Appendix FAQ
81 What is the Appendix
82 What order should I take your courses in (part 1)
83 What order should I take your courses in (part 2)
84 BONUS Where to get discount coupons and FREE deep learning material
85 Windows-Focused Environment Setup 2018
86 How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
87 How to Succeed in this Course (Long Version)
88 How to Code by Yourself (part 1)
89 How to Code by Yourself (part 2)
90 Proof that using Jupyter Notebook is the same as not using it
91 Is this for Beginners or Experts Academic or Practical Fast or slow-paced
92 Python 2 vs Python 3
Resolve the captcha to access the links!