Deep Learning: Advanced Computer Vision (GANs, SSD, +More!)
4.5 (2,861 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
18,990 students enrolled

Deep Learning: Advanced Computer Vision (GANs, SSD, +More!)

VGG, ResNet, Inception, SSD, RetinaNet, Neural Style Transfer, GANs +More in Tensorflow, Keras, and Python
Highest Rated
4.5 (2,861 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
18,990 students enrolled
Last updated 6/2020
English
English [Auto], Italian [Auto], 3 more
  • Polish [Auto]
  • Portuguese [Auto]
  • Spanish [Auto]
Current price: $119.99 Original price: $199.99 Discount: 40% off
3 days left at this price!
30-Day Money-Back Guarantee
This course includes
  • 10 hours on-demand video
  • 3 articles
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
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
Course content
Expand all 93 lectures 10:08:14
+ Review
4 lectures 23:29
Review of CNNs
10:34
Where to get the code and data
02:26
Fashion MNIST
03:29
Review of CNNs in Code
07:00
+ VGG and Transfer Learning
10 lectures 44:23
VGG Section Intro
03:04
What's so special about VGG?
07:00
Transfer Learning
08:22
Relationship to Greedy Layer-Wise Pretraining
02:19
Getting the data
02:17
Code pt 1
09:23
Code pt 2
03:41
Code pt 3
03:27
VGG Section Summary
01:47
Suggestion Box
03:03
+ ResNet (and Inception)
16 lectures 01:06:45
ResNet Section Intro
02:49
ResNet Architecture
12:45
Building ResNet - Strategy
02:25
Uh-oh! What Happens if the Implementation Changes?
05:16
Building ResNet - Conv Block Details
03:34
Building ResNet - Conv Block Code
06:08
Building ResNet - Identity Block Details
01:23
Building ResNet - First Few Layers
02:27
Building ResNet - First Few Layers (Code)
04:15
Building ResNet - Putting it all together
04:19
Exercise: Apply ResNet
01:16
Applying ResNet
02:39
1x1 Convolutions
04:03
Optional: Inception
06:47
Different sized images using the same network
04:12
ResNet Section Summary
02:27
+ Object Detection (SSD / RetinaNet)
14 lectures 01:16:41
Object Localization
06:36
What is Object Detection?
02:53
How would you find an object in an image?
08:40
The Problem of Scale
03:47
The Problem of Shape
03:52
2020 Update - More Fun and Excitement
05:45
RetinaNet Notebooks
00:01
Using Pretrained RetinaNet
11:14
RetinaNet with Custom Dataset (pt 1)
04:26
RetinaNet with Custom Dataset (pt 2)
09:20
RetinaNet with Custom Dataset (pt 3)
07:05
Optional: Intersection over Union & Non-max Suppression
05:06
SSD Section Summary
02:52
+ Neural Style Transfer
7 lectures 43:27
Style Transfer Theory
11:23
Optimizing the Loss
08:02
Code pt 1
07:46
Code pt 2
07:13
Code pt 3
03:50
Style Transfer Section Summary
02:21
+ Class Activation Maps
2 lectures 17:03
Class Activation Maps (Theory)
07:09
Class Activation Maps (Code)
09:54
+ GANs (Generative Adversarial Networks)
3 lectures 28:01
GAN Theory
15:51
GAN Colab Notebook
00:00
GAN Code
12:10
+ Object Localization Project
16 lectures 01:50:31
Localization Introduction and Outline
13:37
Localization Code Outline (pt 1)
10:39
Object Localization Colab Notebooks
00:02
Localization Code (pt 1)
09:10
Localization Code Outline (pt 2)
04:52
Localization Code (pt 2)
11:03
Localization Code Outline (pt 3)
03:18
Localization Code (pt 3)
04:16
Localization Code Outline (pt 4)
03:19
Localization Code (pt 4)
02:06
Localization Code Outline (pt 5)
07:42
Localization Code (pt 5)
08:39
Localization Code Outline (pt 6)
07:06
Localization Code (pt 6)
07:37
Localization Code Outline (pt 7)
04:58
Localization Code (pt 7)
12:07
+ Basics Review
6 lectures 36:50
(Review) Tensorflow Basics
07:27
(Review) Tensorflow Neural Network in Code
09:43
(Review) Keras Discussion
06:48
(Review) Keras Neural Network in Code
06:37
(Review) Keras Functional API
04:26
(Review) How to easily convert Keras into Tensorflow 2.0 code
01:49
Requirements
  • Know how to build, train, and use a CNN using some library (preferably in Python)
  • Understand basic theoretical concepts behind convolution and neural networks
  • Decent Python coding skills, preferably in data science and the Numpy Stack
Description

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.

I hope you’re excited to learn about these advanced applications of CNNs, I’ll see you in class!


AWESOME FACTS:

  • One of the major themes of this course is that we’re moving away from the CNN itself, to systems involving CNNs.

  • Instead of focusing on the detailed inner workings of CNNs (which we've already done), we'll focus on high-level building blocks. The result? Almost zero math.

  • Another result? No complicated low-level code such as that written in TensorflowTheano, or PyTorch (although some optional exercises may contain them for the very advanced students). Most of the course will be in Keras which means a lot of the tedious, repetitive stuff is written for you.


Suggested Prerequisites:

  • Know how to build, train, and use a CNN using some library (preferably in Python)

  • Understand basic theoretical concepts behind convolution and neural networks

  • Decent Python coding skills, preferably in data science and the Numpy Stack


WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

  • Check out the lecture "What order should I take your courses in?" (available in the Appendix of any of my courses, including the free Numpy course)


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