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

VGG, ResNet, Inception, SSD, RetinaNet, Neural Style Transfer, GANs +More Tensorflow, Keras, and Python

Register for this Course

$29.99 $199.99 USD 85% OFF!

Login or signup to register for this course

Have a coupon? Click here.

Course Data

Lectures: 102
Length: 11h 16m
Skill Level: All Levels
Languages: English
Includes: Lifetime access

Course 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.

Finally, I teach you about the controversial technology behind facial recognition - how to identify a person based on a photo of their face.

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


  • 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. (If that's what you're looking for, earlier courses in the series are math-heavy, which was required to understand the inner workings of these building blocks.)
  • Another result? No complicated low-level code such as that written in Tensorflow, Theano, 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

Tips for success:

  • Watch it at 2x.
  • Take handwritten notes. This will drastically increase your ability to retain the information.
  • Write down the equations. If you don't, I guarantee it will just look like gibberish.
  • Ask lots of questions on the discussion board. The more the better!
  • Realize that most exercises will take you days or weeks to complete.
  • Write code yourself, don't just sit there and look at my code.



3 Lectures · 15min
  1. Introduction (02:36) (FREE preview available)
  2. Outline and Perspective (06:50)
  3. How to Succeed in this Course (05:52)


5 Lectures · 25min
  1. Review of CNNs (10:35)
  2. Where to get the code and data (02:27)
  3. Fashion MNIST (02:21)
  4. Review of CNNs in Code (07:00)
  5. Suggestion Box (03:03)

VGG and Transfer Learning

9 Lectures · 41min
  1. VGG Section Intro (03:04)
  2. What's so special about VGG? (07:00)
  3. Transfer Learning (08:23)
  4. Relationship to Greedy Layer-Wise Pretraining (02:19)
  5. Getting the data (02:18)
  6. Code pt 1 (09:24)
  7. Code pt 2 (03:41)
  8. Code pt 3 (03:27)
  9. VGG Section Summary (01:48)

ResNet (and Inception)

16 Lectures · 01hr 06min
  1. ResNet Section Intro (02:50)
  2. ResNet Architecture (12:45)
  3. Building ResNet - Strategy (02:25)
  4. Uh-oh! What Happens if the Implementation Changes? (05:17)
  5. Building ResNet - Conv Block Details (03:34)
  6. Building ResNet - Conv Block Code (06:09)
  7. Building ResNet - Identity Block Details (01:24)
  8. Building ResNet - First Few Layers (02:27)
  9. Building ResNet - First Few Layers (Code) (04:15)
  10. Building ResNet - Putting it all together (04:19)
  11. Exercise: Apply ResNet (01:17)
  12. Applying ResNet (02:40)
  13. 1x1 Convolutions (04:03)
  14. Optional: Inception (06:48)
  15. Different sized images using the same network (04:12)
  16. ResNet Section Summary (02:28)

Object Detection (SSD / RetinaNet)

15 Lectures · 01hr 31min
  1. SSD Section Intro (05:04)
  2. Object Localization (06:37)
  3. What is Object Detection? (02:53)
  4. How would you find an object in an image? (08:41)
  5. The Problem of Scale (03:48)
  6. The Problem of Shape (03:52)
  7. 2020 Update - More Fun and Excitement (05:45)
  8. Using Pretrained RetinaNet (11:14)
  9. RetinaNet with Custom Dataset (pt 1) (04:26)
  10. RetinaNet with Custom Dataset (pt 2) (09:20)
  11. RetinaNet with Custom Dataset (pt 3) (07:05)
  12. SSD in Tensorflow (Legacy) (09:57)
  13. Modifying SSD to work on Video (Legacy) (05:04)
  14. Optional: Intersection over Union & Non-max Suppression (05:06)
  15. SSD Section Summary (02:53)

Neural Style Transfer

7 Lectures · 43min
  1. Style Transfer Section Intro (02:53)
  2. Style Transfer Theory (11:23)
  3. Optimizing the Loss (08:03)
  4. Code pt 1 (07:46)
  5. Code pt 2 (07:13)
  6. Code pt 3 (03:50)
  7. Style Transfer Section Summary (02:21)

Class Activation Maps

2 Lectures · 17min
  1. Class Activation Maps (Theory) (07:09)
  2. Class Activation Maps (Code) (09:54)

Facial Recognition

10 Lectures · 51min
  1. Facial Recognition Section Introduction (03:38)
  2. Siamese Networks (10:17)
  3. Code Outline (05:01)
  4. Loading in the data (04:41)
  5. Splitting the data into train and test (04:24)
  6. Converting the data into pairs (05:02)
  7. Generating Generators (04:20)
  8. Creating the model and loss (03:13)
  9. Accuracy and imbalanced classes (07:08)
  10. Facial Recognition Section Summary (03:28)

GANs (Generative Adversarial Networks)

2 Lectures · 28min
  1. GAN Theory (15:51)
  2. GAN Code (12:11)

Object Localization Project

15 Lectures · 01hr 50min
  1. Localization Introduction and Outline (13:37)
  2. Localization Code Outline (pt 1) (10:39)
  3. Localization Code (pt 1) (09:11)
  4. Localization Code Outline (pt 2) (04:53)
  5. Localization Code (pt 2) (11:03)
  6. Localization Code Outline (pt 3) (03:19)
  7. Localization Code (pt 3) (04:16)
  8. Localization Code Outline (pt 4) (03:19)
  9. Localization Code (pt 4) (02:07)
  10. Localization Code Outline (pt 5) (07:43)
  11. Localization Code (pt 5) (08:39)
  12. Localization Code Outline (pt 6) (07:07)
  13. Localization Code (pt 6) (07:38)
  14. Localization Code Outline (pt 7) (04:58)
  15. Localization Code (pt 7) (12:08)

Basics Review

6 Lectures · 36min
  1. Keras Discussion (06:49)
  2. Keras Neural Network in Code (06:38)
  3. Keras Functional API (04:27)
  4. How to easily convert Keras into Tensorflow 2.0 code (01:49)
  5. TensorFlow Basics: Variables, Functions, Expressions, Optimization (07:27)
  6. Building a neural network in TensorFlow (09:43)

Setting Up Your Environment (Appendix/FAQ by Student Request)

2 Lectures · 37min
  1. Windows-Focused Environment Setup 2018 (20:21)
  2. How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow (17:33)

Extra Help With Python Coding for Beginners (Appendix/FAQ by Student Request)

4 Lectures · 42min
  1. How to Code Yourself (part 1) (15:55)
  2. How to Code Yourself (part 2) (09:24)
  3. Proof that using Jupyter Notebook is the same as not using it (12:29)
  4. Python 2 vs Python 3 (04:38)

Effective Learning Strategies for Machine Learning (Appendix/FAQ by Student Request)

4 Lectures · 59min
  1. How to Succeed in this Course (Long Version) (10:25)
  2. Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced? (22:05)
  3. What order should I take your courses in? (part 1) (11:19)
  4. What order should I take your courses in? (part 2) (16:07)

Appendix / FAQ Finale

2 Lectures · 08min
  1. What is the Appendix? (02:48)
  2. Where to get discount coupons and FREE deep learning material (05:31)


  • Links to Colab Notebooks
  • Super-Resolution and Fast Style Transfer
This website is using cookies. That's Fine