Deep Learning Computer Vision™ CNN, OpenCV, YOLO, SSD & GANs
4.2 (1,369 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.
8,420 students enrolled

Deep Learning Computer Vision™ CNN, OpenCV, YOLO, SSD & GANs

2020 Update with TensorFlow 2.0 Support. Become a Pro at Deep Learning Computer Vision! Includes 20+ Real World Projects
4.2 (1,369 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.
8,420 students enrolled
Created by Rajeev D. Ratan
Last updated 6/2020
English [Auto]
Current price: $139.99 Original price: $199.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 14 hours on-demand video
  • 23 articles
  • 5 downloadable resources
  • 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
  • Learn by completing 26 advanced computer vision projects including Emotion, Age & Gender Classification, London Underground Sign Detection, Monkey Breed, Flowers, Fruits , Simpsons Characters and many more!
  • Advanced Deep Learning Computer Vision Techniques such as Transfer Learning and using pre-trained models (VGG, MobileNet, InceptionV3, ResNet50) on ImageNet and re-create popular CNNs such as AlexNet, LeNet, VGG and U-Net.
  • Understand how Neural Networks, Convolutional Neural Networks, R-CNNs , SSDs, YOLO & GANs with my easy to follow explanations
  • Become familiar with other frameworks (PyTorch, Caffe, MXNET, CV APIs), Cloud GPUs and get an overview of the Computer Vision World
  • How to use the Python library Keras to build complex Deep Learning Networks (using Tensorflow backend)
  • How to do Neural Style Transfer, DeepDream and use GANs to Age Faces up to 60+
  • How to create, label, annotate, train your own Image Datasets, perfect for University Projects and Startups
  • How to use OpenCV with a FREE Optional course with almost 4 hours of video
  • How to use CNNs like U-Net to perform Image Segmentation which is extremely useful in Medical Imaging application
  • How to use TensorFlow's Object Detection API and Create A Custom Object Detector in YOLO
  • Facial Recognition with VGGFace
  • Use Cloud GPUs on PaperSpace for 100X Speed Increase vs CPU
  • Build a Computer Vision API and Web App and host it on AWS using an EC2 Instance
Course content
Expand all 178 lectures 14:43:21
+ Introduction
1 lecture 10:13

An introduction to Computer Vision and Deep Learning. Learn how Deep Learning is changing the world and why you need to do this course.

Preview 10:13
+ Intro to Computer Vision & Deep Learning
4 lectures 20:54

Introduction to Computer Vision & Deep Learning chapter overview.

Preview 00:40

Learn what makes Computer Vision so hard.

What is Computer Vision and What Makes it Hard

Learn what exactly are images and how computers store and interpret image data.

What are Images?

Learn about OpenCV, OpenVINO, what they're used for and their limitations.

Intro to OpenCV, OpenVINO™ & their Limitations
+ Installation Guide
6 lectures 25:42
New Install Guide Update 2020 - Tensorflow 2.0
Windows install guide NEW 2020 UPDATE

How to set up your Deep Learning Ubuntu Virtual Machine

Setting up your Deep Learning Virtual Machine (Download Code, VM & Slides here!)
Optional - Troubleshooting Guide for VM Setup & for resolving some MacOS Issues
Optional - Manual Setup of Ubuntu Virtual Machine
Optional - Setting up a shared drive with your Host OS
+ Handwriting Recognition
4 lectures 13:45
Get Started! Handwriting Recognition, Simple Object Classification OpenCV Demo

Run your own (pre-trained) handwritten digit classification on a real world image!

Experiment with a Handwriting Classifier

Classify 10 Types of Images using the CIFAR10 Dataset

Experiment with a Image Classifier

Run a simple but fun OpenCV Demo that turns your webcam feed into a live sketch!

OpenCV Demo – Live Sketch with Webcam
+ OpenCV Tutorial - Learn Classic Computer Vision & Face Detection (OPTIONAL)
41 lectures 03:31:21
Setup OpenCV
What are Images?
How are Images Formed
Storing Images on Computers
Getting Started with OpenCV - A Brief OpenCV Intro
Grayscaling - Converting Color Images To Shades of Gray
Understanding Color Spaces - The Many Ways Color Images Are Stored Digitally
Histogram representation of Images - Visualizing the Components of Images
Creating Images & Drawing on Images - Make Squares, Circles, Polygons & Add Text
Transformations, Affine And Non-Affine - The Many Ways We Can Change Images
Image Translations - Moving Images Up, Down. Left And Right
Rotations - How To Spin Your Image Around And Do Horizontal Flipping
Scaling, Re-sizing and Interpolations - Understand How Re-Sizing Affects Quality
Image Pyramids - Another Way of Re-Sizing
Cropping - Cut Out The Image The Regions You Want or Don't Want
Arithmetic Operations - Brightening and Darkening Images
Bitwise Operations - How Image Masking Works
Blurring - The Many Ways We Can Blur Images & Why It's Important
Sharpening - Reverse Your Images Blurs
Thresholding (Binarization) - Making Certain Images Areas Black or White
Dilation, Erosion, Opening/Closing - Importance of Thickening/Thinning Lines
Edge Detection using Image Gradients & Canny Edge Detection
Perspective & Affine Transforms - Take An Off Angle Shot & Make It Look Top Down
Mini Project 1 - Live Sketch App - Turn your Webcam Feed Into A Pencil Drawing
Segmentation and Contours - Extract Defined Shapes In Your Image
Sorting Contours - Sort Those Shapes By Size
Approximating Contours & Finding Their Convex Hull - Clean Up Messy Contours
Matching Contour Shapes - Match Shapes In Images Even When Distorted
Mini Project 2 - Identify Shapes (Square, Rectangle, Circle, Triangle & Stars)
Line Detection - Detect Straight Lines E.g. The Lines On A Sudoku Game

Identify circles in an image

Circle Detection
Blob Detection - Detect The Center of Flowers
Mini Project 3 - Counting Circles and Ellipses
Object Detection Overview
Mini Project # 4 - Finding Waldo (Quickly Find A Specific Pattern In An Image)
Feature Description Theory - How We Digitally Represent Objects
Finding Corners - Why Corners In Images Are Important to Object Detection
Histogram of Oriented Gradients - Another Novel Way Of Representing Images
HAAR Cascade Classifiers - Learn How Classifiers Work And Why They're Amazing
Face and Eye Detection - Detect Human Faces and Eyes In Any Image
Mini Project 6 - Car and Pedestrian Detection in Videos
+ Neural Networks Explained
12 lectures 01:34:02

Neural Networks Chapter Overview

Neural Networks Chapter Overview

A Brief introduction to Machine Learning, the types of Machine Learning and the ML process.

Machine Learning Overview

Understand Forward Propagation

Neural Networks Explained

Understand Forward Propagation

Forward Propagation

Understand Activation Functions and why they're needed.

Activation Functions

Understand the importance of Loss Functions.

Training Part 1 – Loss Functions

Understand the importance of Backpropagation.

Training Part 2 – Backpropagation and Gradient Descent

Work through the Math of Backpropagation

Backpropagation & Learning Rates – A Worked Example
  • Understand Regularization, Overfitting and Generalization

  • Why we need Test Data

Regularization, Overfitting, Generalization and Test Datasets

Understand the terms Epochs, Iterations and Batch Sizes

Epochs, Iterations and Batch Sizes

Know how to assess your NN's performance by understanding Classification Reports and the Confusion Matrix.

Measuring Performance and the Confusion Matrix

Chapter review and the best practices or rules of thumb when it comes to training a Neural Network.

Review and Best Practices
+ Convolutional Neural Networks (CNNs) Explained
9 lectures 41:59

Convolutional Neural Networks Chapter Overview

Convolutional Neural Networks Chapter Overview

Introduction to Convolutional Neural Networks

Convolutional Neural Networks Introduction

What are Convolutions, Image Features and Feature Maps.

Convolutions & Image Features

What is depth, stride and pooling and how they relate to feature maps generation.

Depth, Stride and Padding

Understand how ReLU works


Understand the importance of the Pooling or downsampling layer.


Understand the importance of the Fully Connected or Dense Layer

The Fully Connected Layer

Understand what goes on when training a CNN

Training CNNs

How do we go about creating our own CNN designs

Designing Your Own CNN
+ Build CNNs in Python using Keras
12 lectures 52:12

Building a CNN in Keras   

Building a CNN in Keras

Overview on Keras and TensorFlow

Introduction to Keras & Tensorflow

How to build a Handwriting Recognition classifier CNN in Python using Keras

Building a Handwriting Recognition CNN

How to load datasets into Python

Loading Our Data

How to preprocess your data to work with Keras

Getting our data in ‘Shape’

What is hot-one-encoding and why it's needed.

Hot One Encoding

How to build and compile our models

Building & Compiling Our Model

How the training process works in Keras

Training Our Classifier

How to plot our Loss and Accuracy graphs

Plotting Loss and Accuracy Charts

How to save and load saved your models

Saving and Loading Your Model

How to plot a visual representation of your model

Displaying Your Model Visually

Building a Simple Image Classifier using CIFAR10

Building a Simple Image Classifier using CIFAR10
+ What CNNs 'see' - Filter Visualizations, Heatmaps and Salience Maps
5 lectures 27:00

Visualizing What CNNs 'see' & Filter Visualizations chapter overview

Introduction to Visualizing What CNNs 'see' & Filter Visualizations

What are and how to plot Saliency Maps & Class Activation Maps   

Saliency Maps & Class Activation Maps

How to create Filter Visualizations

Saliency Maps & Class Activation Maps
Filter Visualizations

How to create Heat Map Visualizations of Class Activations

Heat Map Visualizations of Class Activations
+ Data Augmentation: Cats vs Dogs
5 lectures 25:42

Data Augmentation Chapter Overview

Data Augmentation Chapter Overview

How to take an dataset and split it into Training and Test segments with their associated labels.

Splitting Data into Test and Training Datasets

How to build a Cats vs Dogs classifier

Train a Cats vs. Dogs Classifier

How to use Data Augmentation in Keras

Boosting Accuracy with Data Augmentation

How to view and create different types of augmentative image data using Keras

Types of Data Augmentation
  • Basic programming knowledge is a plus but not a requirement
  • High school level math, College level would be a bonus
  • Atleast 20GB storage space for Virtual Machine and Datasets
  • A Windows, MacOS or Linux OS

Update: June-2020

  • TensorFlow 2.0 Compatible Code

  • Windows install guide for TensorFlow2.0 (with Keras), OpenCV4 and Dlib

Deep Learning Computer Vision™ Use Python & Keras to implement CNNs, YOLO, TFOD, R-CNNs, SSDs & GANs + A Free Introduction to OpenCV.

If you want to learn all the latest 2019 concepts in applying Deep Learning to Computer Vision, look no further - this is the course for you! You'll get hands  the following Deep Learning frameworks in Python:

  • Keras

  • Tensorflow 2.0

  • TensorFlow Object Detection API

  • YOLO (DarkNet and DarkFlow)

  • OpenCV4

All in an easy to use virtual machine, with all libraries pre-installed!


Apr 2019 Updates:

  • How to set up a Cloud GPU on PaperSpace and Train a CIFAR10 AlexNet CNN almost 100 times faster!

  • Build a Computer Vision API and Web App and host it on AWS using an EC2 Instance!

Mar 2019 Updates:

Newly added Facial Recognition & Credit Card Number Reader Projects

  • Recognize multiple persons using your webcam

  • Facial Recognition on the Friends TV Show Characters

  • Take a picture of a Credit Card, extract and identify the numbers on that card!


Computer vision applications involving Deep Learning are booming!

Having Machines that can 'see' will change our world and revolutionize almost every industry out there. Machines or robots that can see will be able to:

  • Perform surgery and accurately analyze and diagnose you from medical scans.

  • Enable self-driving cars

  • Radically change robots allowing us to build robots that can cook, clean and assist us with almost any task

  • Understand what's being seen in CCTV surveillance videos thus performing security, traffic management and a host of other services

  • Create Art with amazing Neural Style Transfers and other innovative types of image generation

  • Simulate many tasks such as Aging faces, modifying live video feeds and realistically replace actors in films

Huge technology companies such as Facebook, Google, Microsoft, Apple, Amazon, and Tesla are all heavily devoting billions to computer vision research.

As a result, the demand for computer vision expertise is growing exponentially!

However, learning computer vision with Deep Learning is hard!

  • Tutorials are too technical and theoretical

  • Code is outdated

  • Beginners just don't know where to start

That's why I made this course!

  • I  spent months developing a proper and complete learning path.

  • I teach all key concepts logically and without overloading you with mathematical theory while using the most up to date methods. 

  • I created a FREE Virtual Machine with all Deep Learning Libraries (Keras, TensorFlow, OpenCV, TFODI, YOLO, Darkflow etc) installed! This will save you hours of painfully complicated installs

  • I teach using practical examples and you'll learn by doing 18 projects!

Projects such as:

  1. Handwritten Digit Classification using MNIST

  2. Image Classification using CIFAR10

  3. Dogs vs Cats classifier

  4. Flower Classifier using Flowers-17

  5. Fashion Classifier using FNIST

  6. Monkey Breed Classifier

  7. Fruit Classifier

  8. Simpsons Character Classifier

  9. Using Pre-trained ImageNet Models to classify a 1000 object classes

  10. Age, Gender and Emotion Classification

  11. Finding the Nuclei in Medical Scans using U-Net

  12. Object Detection using a ResNet50 SSD Model built using TensorFlow Object Detection

  13. Object Detection with YOLO V3

  14. A Custom YOLO Object Detector that Detects London Underground Tube Signs

  15. DeepDream

  16. Neural Style Transfers

  17. GANs - Generate Fake Digits

  18. GANs - Age Faces up to 60+ using Age-cGAN

  19. Face Recognition

  20. Credit Card Digit Reader

  21. Using Cloud GPUs on PaperSpace

  22. Build a Computer Vision API and Web App and host it on AWS using an EC2 Instance!

And OpenCV Projects such as:

  1. Live Sketch

  2. Identifying Shapes

  3. Counting Circles and Ellipses

  4. Finding Waldo

  5. Single Object Detectors using OpenCV

  6. Car and Pedestrian Detector using Cascade Classifiers

So if you want to get an excellent foundation in Computer Vision, look no further.

This is the course for you!

In this course, you will discover the power of Computer Vision in Python, and obtain skills to dramatically increase your career prospects as a Computer Vision developer.


As for Updates and support:

I will be active daily in the 'questions and answers' area of the course, so you are never on your own.    

So, are you ready to get started? Enroll now and start the process of becoming a Master in Computer Vision using Deep Learning today!


What previous students have said my other Udemy Course: 

"I'm amazed at the possibilities. Very educational, learning more than what I ever thought was possible. Now, being able to actually use it in a practical purpose is intriguing... much more to learn & apply"

"Extremely well taught and informative Computer Vision course! I've trawled the web looking for OpenCV python tutorials resources but this course was by far the best amalgamation of relevant lessons and projects. Loved some of the projects and had lots of fun tinkering them."

"Awesome instructor and course. The explanations are really easy to understand and the materials are very easy to follow. Definitely a really good introduction to image processing."

"I am extremely impressed by this course!! I think this is by far the best Computer Vision course on Udemy. I'm a college student who had previously taken a Computer Vision course in undergrad. This 6.5 hour course blows away my college class by miles!!"

"Rajeev did a great job on this course. I had no idea how computer vision worked and now have a good foundation of concepts and knowledge of practical applications. Rajeev is clear and concise which helps make a complicated subject easy to comprehend for anyone wanting to start building applications."


Who this course is for:
  • Programmers, college students or anyone enthusiastic about computer vision and deep learning
  • Those wanting to be on the forefront of the job market for the AI Revolution
  • Those who have an amazing startup or App idea involving computer vision
  • Enthusiastic hobbyists wanting to build fun Computer Vision applications