About the course

There has been a tremendous boom in the applications of Computer Vision now a days.

The applications of Computer Vision range from understanding the environment in a Self - Driving Car to build Facial Recognition based Attention Systems for classrooms in Education Industry.

A question you might ask is: why would I even want to know about Computer Vision ? As a matter of fact, there is an undeniable demand for people who have knowledge in this domain, so that they can bring about disruptive solutions in any industry possible.

Computer Vision systems deal with high variety and volume of data, specifically images or videos.It is represented as bits and blobs which is hard to explain to a machine.As a result, these systems need intricate techniques to make sense of the data and then make data driven decisions.

This course is designed to give you a taste of how the underlying techniques work in current State - of -the - Art Computer Vision systems, and walks you through a few of the remarkable Computer Vision applications in a hands - on manner so that you can create such solutions on your own.

Pre-requisites

This is a beginner friendly course, so it does not assume any familiarity with Computer Vision or Deep Learning algorithms. But, this course assumes that you are comfortable with Python programming.

Highlights

  • Projects

    6 Real Life projects

  • Live Q & A Session

    Every Thursday 9 pm to 10 pm (IST)

Course curriculum

  • 1
    Course Handouts
    • Course Handouts
  • 2
    Introduction to computer vision
    • Welcome to Computer Vision
    • Knowing each other
    • Documentary on Computer Vision FREE PREVIEW
    • Exercise-1
    • Applications of Computer Vision
    • Exercise-2
    • Why Computer Vision is more in Demand?
    • Exercise-3
    • Understand your course content
    • Exercise- 4
  • 3
    Getting ready for the course
    • Getting ready for the course
    • System Requirements
    • Setting up the System on Cloud
    • Setting up locally
    • Accessing the course material
    • Pre-reads for the next modules
  • 4
    Introduction to Neural Network
    • Understanding the problem
    • Getting started with Neural Network
    • Exercise : Getting started with Neural Network
    • Independent and dependent variables
    • Understanding Forward Propogation
    • Exercise : Forward Propogation
    • Math Behind Forward Propagation
    • Exercise : Math Behind Forward Propagation
    • Error and Reason for Error
    • Exercise : Error and Reason for Error
    • Gradient Descent Intuition
    • Understanding Math Behind Gradient Descent
    • Exercise : Gradient Descent
    • Optimizer
    • Exercise : Optimizer
    • Back Propagation
    • Exercise : Back Propagation
    • Why Numpy?
    • Exercise : Why Numpy?
    • Understanding the Steps in Numpy FREE PREVIEW
    • Exercise : Understanding the Steps in Numpy
    • Defining Parameters in Numpy
    • Exercise : Defining Parameters in Numpy
    • Implementing Forward Propagation
    • Exercise : Implementing Forward Propagation
    • Implementing Backward Propagation
    • Exercise : Implementing Backward Propagation
    • Neural network from scratch (Notebook)
    • Why Keras?
    • Exercise : Why Keras?
    • Neural Networks in Keras
    • Exercise : Neural Network in Keras
    • How to handle image data
    • Exercise : How to handle Image data
    • Exploring the Emergency Classification Dataset
    • Exercise : Exploring the Emergency Classification Dataset
    • Loading and Pre-Processing Dataset
    • Exercise : Loading and Pre-Processing Dataset
    • Solving the challenge
    • Exercise : Solving the challenge
    • Hyperparameter Tuning
    • Exercise : Hyperparameter Tuning
    • Simple Neural Network using keras (Notebook)
    • Summary of the Module
  • 5
    Project I
    • Project I
  • 6
    Introduction to Convolutional Neural Network
    • Why CNN?
    • Exercise : Why CNN?
    • Understanding the working of CNN Filters
    • Exercise : Understanding the working of CNN Filters
    • Introduction to Padding
    • Exercise : Introduction to Padding
    • Padding Strategies
    • Exercise : Padding Strategies
    • Padding Strategies in Keras
    • Exercise : Padding Strategies in Keras
    • Introduction to Pooling
    • Exercise : Introduction to Pooling
    • CNN architecture and its working
    • Exercise : CNN architecture and its working
    • Loading and Pre-Processing Dataset
    • Solving the challenge
    • Exercise : Solving the challenge
    • Hyperparameter Tuning
    • Exercise : Hyperparameter Tuning
    • Convolutional Neural Network in keras (Notebook)
    • Summary of the Module
    • Exercise : Gender Classification using CNN
  • 7
    Introduction to Transfer Learning
    • Introduction to Transfer Learning FREE PREVIEW
    • How to select right pre-trained model?
    • Exercise : How to select right pre-trained model?
    • Steps to solve emergency vs non emergency vehicle classification challenge using transfer learning
    • Exercise : Steps to build the model using transfer learning
    • Solving the challenge using Transfer Learning (Part I)
    • Exercise
    • Solving the challenge using Transfer Learning (Part II)
    • Exercise
    • Solving the challenge using Transfer Learning (Part III)
    • Exercise : Solving the challenge using transfer learning
    • Solving the challenge using transfer learning (Notebook)
    • Different fine tuning techniques
    • Advantages of transfer learning
    • Exercise : Gender Classification using transfer learning
  • 8
    Tips and Tricks to Improve Model Performance
    • Understand areas to improve
    • Exercise : Understand areas to improve
    • Introduction to the Problem
    • Exercise : Introduction to the Problem
    • Implementation and Solution
    • Exercise : Implementation and Solution
    • Introduction to the Problem
    • Exercise : Introduction to the Problem
    • Implementation and Solution
    • Exercise : Implementation and Solution
    • Introduction to the Problem
    • Exercise : Introduction to the Problem
    • Implementation and Solution
    • Exercise : Implementation and Solution
    • Introduction to the Problem
    • Exercise : Introduction to the Problem
    • Introduction to the Problem
    • Exercise : Introduction to the Problem
    • Implementation and Solution
    • Introduction to the Problem
    • Exercise : Introduction to the Problem
    • Implementation and Solution
    • Exercise : Implementation and Solution
    • Wrong Evaluation Metric - Part I
    • Exercise : Wrong Evaluation Metric - Part I
    • Wrong Evaluation Metric - Part II
    • Exercise : Wrong Evaluation Metric : Part II
    • Combining Tips and Tricks
    • Tips and tricks implementation (Notebook)
    • Exercise : Combining the Trips and Tricks
    • Exercise : Improving the model performance on Gender Classification
  • 9
    Horizon of Computer Vision and Case Studies
    • Understanding the Types of Computer Vision Problems
    • Exercise : Understanding the type of problems
    • Approach to solve different type of problems
    • Exercise : Approach to solve different type of problems
    • Understanding the Regression Problem
    • Exploring Facial Keypoint Identification Problem
    • Exercise : Exploring Facial Keypoint Identification Problem
    • Loading and Pre-Processing Dataset
    • Solving the Regression Challenge
    • Exercise : Solving the Regression Challenge
    • Implementation : Facial Keypoint Identification (Notebook)
    • Project II
    • Understanding Object Detection Problem
    • Exercise : Understanding Object Detection Problem Statement
    • Naïve Appoach to solve detection problem
    • Exercise : Naïve Appoach to solve detection problem
    • Exploring Blood Cell Detection Problem
    • Loading and Pre-Processing Dataset
    • Building the model
    • Implementation : Blood cell detection - Part I (Notebook)
    • Other Approaches to solve Detection Problem
    • Exercise : Other Approaches to solve Detection Problem
    • Implementing State-of-the-art Model on Blood Detection
    • Understanding State-of-the-art Model
    • Implementation : Blood cell detection - Part II (Notebook)
    • Exercise : Understanding State-of-the-art Model
    • Project III
  • 10
    Where to go from here?
    • What did we discuss?
    • Where to go from here?
  • 11
    Bonus Material
    • Visualization of Learning and Localization of Convolutional Neural Networks by Sunil Kumar Vuppala
    • Generative Adversarial Networks by Keshav Dhandhania
    • Attention-based Deep Learning Models to Extract Details from Images by Vijay Gabale
    • Diagnosing your Model : Learning How To Debug Deep Learning Models Using Visualisation For Medical Images - By Rohit Ghosh
    • Hack Session: Understanding the Building Blocks of Deep Learning using PyTorch - By Vishnu Subramanian
    • Failing Fast with Deep Learning - By Jaidev Deshpande

Project-1

Classify Emergency Vehicles from Non-Emergency Vehicles (In-class)

Fatalities due to traffic delays of emergency vehicles such as ambulance & fire brigade is a huge problem. In daily life, we often see that an emergency vehicles face difficulty in passing through traffic. So differentiating a vehicle into an emergency and non emergency category can be an important component in traffic monitoring as well as self drive car systems as reaching on time to their destination is critical for these services. In this project, you will get to design a computer vision system that can do just this.
Project-1

Project-2

Age Prediction of People from closeups of Facial Images

We now have systems that can correctly identify faces in the wild, but they fail to give us the the facial properties to build intelligent systems, like age of the person or their gender. This project will urge you to create algorithms that would power these intelligent systems, specifically by predicting the age of the person directly from an image clipping of his/her face.
Project-2

Project-3

Identify the Location of Red Blood Cells (In-class)

The analysis of blood cells allows the evaluation and diagnosis of a vast number of diseases. But this is generally done manually by skilled operators. In practice, we can automate a part of this process by identifying individual blood cell from a microscopic image. The task of this project will challenge you to find the locations of red blood cells through Deep Learning
Project-3

Instructor(s)

  • Faizan  Shaikh

    Faizan Shaikh

    Faizan is working as a data scientist at Analytics Vidhya. Being a Deep Learning enthusiast, he aims to utilize his skills to push the boundaries of AI research. Faizan is an avid blogger on Analytics Vidhya, and has contributed to many articles to explain complex concepts of Deep Learning in a simple manner. He will be your instructor for the course.
  • Neeraj Singh Sarwan

    Neeraj Singh Sarwan

    Neeraj is working as a data scientist at Analytics Vidhya. He has extensive experience in converting business problems to data problems. He has previously taken several corporate trainings and is also an avid blogger. He's a graduate of IIT-BHU and will be your instructor for the Python and Modeling modules.

FAQ

  • Who should take this course?

    This course is for people who are looking to get into the field of Computer Vision and start building their own Computer Vision applications using Deep Learning.

  • I have a programming experience of 2+ years, but I have no background of Machine learning. Is the course right for me?

    The course does not assume any prior background in Machine Learning. So you are welcome to follow through the course.

  • What is the refund policy?

    The fee for this course is non-refundable.

  • Do I need to take the modules in a specific order?

    We would highly recommend taking the course in the order in which it has been designed to gain the maximum knowledge from it.

  • Do I get a certificate upon completion of the course?

    Yes, you will be given a certificate upon satisfactory completion of the course.

  • What is the fee for this course?

    The price of this course is INR 15,999/-

  • How long I can access the course?

    You will be able to access the course material for six months since the start of the course.

  • When will the classes be held in this course?

    This is an online self-paced course, which you can take any time at your convenience over the 6 months after your purchase.

  • How many hours per week should I dedicate to complete the course?

    If you can put between 6 to 8 hours a week, you should be able to finish the course in 8 to 10 weeks.

Support