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

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.

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 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.

"If you can't implement it, you don't understand it"

Or as the great physicist Richard Feynman said: "What I cannot create, I do not understand".
My courses are the ONLY courses where you will learn how to implement machine learning algorithms from scratch
Other courses will teach you how to plug in your data into a library, but do you really need help with 3 lines of code?
After doing the same thing with 10 datasets, you realize you didn't learn 10 things. You learned 1 thing, and just repeated the same 3 lines of code 10 times...

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 "Machine Learning and AI Prerequisite Roadmap" (available in the FAQ of any of my courses, including the free Numpy course)

UNIQUE FEATURES

Every line of code explained in detail - email me any time if you disagree
No wasted time "typing" on the keyboard like other courses - let's be honest, nobody can really write code worth learning about in just 20 minutes from scratch
Not afraid of university-level math - get important details about algorithms that other courses leave out

What's inside

Learning objectives

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

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

Syllabus

Welcome

Introduction

Outline and Perspective

How to Succeed in this Course

Google Colab & Getting Setup

Get Your Hands Dirty, Practical Coding Experience, Data Links

How to use Github & Extra Coding Tips (Optional)

Where to get the code, notebooks, and data

Intro to Google Colab, how to use a GPU or TPU for free

Uploading your own data to Google Colab

Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn?

Temporary 403 Errors

Machine Learning Basics Review

What is Machine Learning?

Code Preparation (Classification Theory)

Beginner's Code Preamble

Classification Notebook

Code Preparation (Regression Theory)

Regression Notebook

The Neuron

How does a model "learn"?

Making Predictions

Saving and Loading a Model

Suggestion Box

Artificial Neural Networks (ANN) Review

Artificial Neural Networks Section Introduction

Forward Propagation

The Geometrical Picture

Activation Functions

Multiclass Classification

How to Represent Images

Color Mixing Clarification

Code Preparation (ANN)

ANN for Image Classification

ANN for Regression

Convolutional Neural Networks (CNN) Review

What is Convolution? (part 1)

What is Convolution? (part 2)

What is Convolution? (part 3)

Convolution on Color Images

CNN Architecture

CNN Code Preparation

CNN for Fashion MNIST

CNN for CIFAR-10

Data Augmentation

Batch Normalization

Improving CIFAR-10 Results

VGG and Transfer Learning

VGG Section Intro

What's so special about VGG?

Transfer Learning

Relationship to Greedy Layer-Wise Pretraining

Getting the data

Code pt 1

Code pt 2

Code pt 3

VGG Section Summary

ResNet (and Inception)

ResNet Section Intro

ResNet Architecture

Transfer Learning with ResNet in Code

Blood Cell Images Dataset

How to Build ResNet in Code

1x1 Convolutions

Optional: Inception

Different sized images using the same network

ResNet Section Summary

Object Detection (SSD / RetinaNet)

SSD Section Intro

Object Localization

What is Object Detection?

How would you find an object in an image?

The Problem of Scale

The Problem of Shape

SSD Tensorflow Object Detection API (pt 1)

SSD Tensorflow Object Detection API (pt 2)

SSD for Video Object Detection

Optional: Intersection over Union & Non-max Suppression

SSD Section Summary

Neural Style Transfer

Style Transfer Section Intro

Style Transfer Theory

Optimizing the Loss

Style Transfer Section Summary

Class Activation Maps

Class Activation Maps (Theory)

Class Activation Maps (Code)

GANs (Generative Adversarial Networks)

GAN Theory

GAN Code

Object Localization Project

Localization Introduction and Outline

Localization Code Outline (pt 1)

Localization Code (pt 1)

Localization Code Outline (pt 2)

Localization Code (pt 2)

Localization Code Outline (pt 3)

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

This course covers key foundational concepts in computer vision

Teaches neural networks through CNN applications

Introduces students to VGG, ResNet, and Inception

Teaches students about SSD and retina net object detection algorithms

Covers style transfer theory and GAN basics

Explores real-world computer vision applications such as medical diagnostics and self-driving vehicles

Reviews summary

Comprehensive computer vision course

Learners say that this computer vision course provides a comprehensive introduction to advanced topics. Noteworthy coding assignments help learners master various methods and techniques.

The course relies heavily on coding assignments for learning.

"The instructor emphasizes coding as the must way to master techniques. It is true!"

Course effectively presents advanced concepts such as VGG, transfer learning, and GANs.

"Very good course introducing advanced topics like VGG, transfer learning and the modern GAN..."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Deep Learning: Advanced Computer Vision (GANs, SSD, +More!) with these activities:

Compile a list of useful resources for Object Detection and Computer Vision

Show steps

Gather valuable materials to support your learning.

Browse courses on Object Detection

Show steps

Search for online tutorials, articles, and documentation on object detection and computer vision.
Bookmark or save relevant resources for future reference.
Organize your compilation into categories or topics.

Identify and connect with mentors in the field of Computer Vision or Deep Learning

Show steps

Seek guidance and support from experienced professionals.

Browse courses on Mentorship

Show steps

Attend networking events or join online communities.
Reach out to potential mentors and express your interest in learning from them.
Build relationships with mentors and seek their advice and feedback.

Read 'Deep Learning' by Ian Goodfellow, Yoshua Bengio, and Aaron Courville

Show steps

Gain a comprehensive understanding of the foundations and applications of deep learning.

View Deep Learning on Amazon

Show steps

Read the book thoroughly, taking notes and highlighting important concepts.
Complete the exercises and assignments provided in the book.
Discuss the content with peers or a mentor to reinforce your understanding.

Five other activities

Expand to see all activities and additional details

Show all eight activities

Review Convolutional Neural Networks (CNNs)

Show steps

Start the course prepared by revisiting the topic of CNNs.

Browse courses on Convolutional Neural Networks

Show steps

Review the basics of CNNs, including their architecture and how they work.
Go through a tutorial or refresher course on CNNs.
Complete a few practice exercises to test your understanding.

Attend a meetup or conference on Computer Vision or Deep Learning

Show steps

Connect with professionals in the field and learn about the latest advancements.

Browse courses on Computer Vision

Show steps

Find a relevant meetup or conference.
Attend the event and actively participate in discussions.
Network with other attendees and exchange knowledge.

Complete TensorFlow or PyTorch tutorials on Object Detection

Show steps

Expand your knowledge of object detection through hands-on practice.

Browse courses on Object Detection

Show steps

Choose a TensorFlow or PyTorch tutorial on object detection.
Follow the tutorial step-by-step, implementing the code and understanding the concepts.
Experiment with different parameters and models to see how they affect the results.

Solve leetcode problems related to CNNs and Object Detection

Show steps

Sharpen your problem-solving skills by applying CNNs and object detection to coding challenges.

Show steps

Identify leetcode problems that involve CNNs or object detection.
Attempt to solve the problems on your own.
Review solutions and discuss approaches with peers or mentors.

Build a small object detection project using TensorFlow or PyTorch

Show steps

Apply your knowledge by developing a practical project that demonstrates your understanding of object detection.

Browse courses on Object Detection

Show steps

Define the scope and goals of your project.
Gather the necessary data and resources.
Implement the object detection model and train it on your data.
Evaluate the performance of your model and make improvements.
Document your project and share it with others.

Career center

Learners who complete Deep Learning: Advanced Computer Vision (GANs, SSD, +More!) will develop knowledge and skills that may be useful to these careers:

Deep Learning Engineer

Deep Learning Engineers are responsible for designing and developing deep learning models. This course can help you develop the skills necessary to succeed as a Deep Learning Engineer by providing you with a deep understanding of the theory and practice of deep learning. You will also gain experience in implementing deep learning algorithms in Python, which is a popular language for deep learning.

See salaries and explore the career path for Deep Learning Engineer

Computer Vision Engineer

Computer Vision Engineers are responsible for developing computer vision systems, which can be used to analyze images and videos. This course can help you develop the skills necessary to succeed as a Computer Vision Engineer by providing you with a strong foundation in deep learning and state-of-the-art computer vision techniques. You will also gain experience in implementing computer vision algorithms in Python, which is a popular language for computer vision.

See salaries and explore the career path for Computer Vision Engineer

Machine Learning Engineer

Machine Learning Engineers are responsible for designing and developing machine learning models. This course can help you develop the skills necessary to succeed as a Machine Learning Engineer by providing you with a deep understanding of the theory and practice of machine learning. You will also gain experience in implementing machine learning algorithms in Python, which is a popular language for machine learning.

See salaries and explore the career path for Machine Learning Engineer

Data Scientist

Data Scientists are responsible for collecting and analyzing data in order to provide insights to businesses. This course can help you develop the skills necessary to succeed as a Data Scientist by providing you with a strong foundation in deep learning, which is a powerful tool for analyzing large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Data Scientist

Artificial Intelligence Engineer

Artificial Intelligence Engineers are responsible for designing and developing artificial intelligence systems. This course can help you develop the skills necessary to succeed as an Artificial Intelligence Engineer by providing you with a deep understanding of the theory and practice of artificial intelligence. You will also gain experience in implementing artificial intelligence algorithms in Python, which is a popular language for artificial intelligence.

See salaries and explore the career path for Artificial Intelligence Engineer

Data Analyst

Data Analysts are responsible for collecting, cleaning, and analyzing data in order to provide insights to businesses. This course can help you develop the skills necessary to succeed as a Data Analyst by providing you with a strong foundation in deep learning, which is a powerful tool for analyzing large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Data Analyst

Research Scientist

Research Scientists are responsible for conducting research in a variety of fields, including computer science, engineering, and medicine. This course can help you develop the skills necessary to succeed as a Research Scientist by providing you with a strong foundation in deep learning, which is a powerful tool for analyzing large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Research Scientist

Business Analyst

Business Analysts are responsible for analyzing business processes and identifying opportunities for improvement. This course can help you develop the skills necessary to succeed as a Business Analyst by providing you with a strong foundation in deep learning, which can be used to analyze large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Business Analyst

Software Engineer

Software Engineers are responsible for designing and developing software applications. This course can help you develop the skills necessary to succeed as a Software Engineer by providing you with a strong foundation in deep learning and state-of-the-art computer vision techniques. You will also gain experience in implementing deep learning and computer vision algorithms in Python, which is a popular language for software development.

See salaries and explore the career path for Software Engineer

Marketing Manager

Marketing Managers are responsible for planning and executing marketing campaigns. This course can help you develop the skills necessary to succeed as a Marketing Manager by providing you with a strong foundation in deep learning, which can be used to analyze large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Marketing Manager

Product Manager

Product Managers are responsible for planning and developing products. This course can help you develop the skills necessary to succeed as a Product Manager by providing you with a strong foundation in deep learning, which can be used to analyze large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Product Manager

Finance Manager

Finance Managers are responsible for planning and managing the finances of a company. This course may be useful for you if you are interested in a career in finance by providing you with a strong foundation in deep learning, which can be used to analyze large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Finance Manager

Sales Manager

Sales Managers are responsible for leading sales teams and achieving sales goals. This course may be useful for you if you are interested in a career in sales by providing you with a strong foundation in deep learning, which can be used to analyze large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Sales Manager

Operations Manager

Operations Managers are responsible for planning and managing the operations of a company. This course may be useful for you if you are interested in a career in operations by providing you with a strong foundation in deep learning, which can be used to analyze large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Operations Manager

Human Resources Manager

Human Resources Managers are responsible for planning and managing the human resources of a company. This course may be useful for you if you are interested in a career in human resources by providing you with a strong foundation in deep learning, which can be used to analyze large and complex datasets. You will also learn about state-of-the-art computer vision techniques, which can be used to analyze images and videos.

See salaries and explore the career path for Human Resources Manager