Advanced Deep Learning and Computer Vision

14,496 Learners

Course Overview

Advanced Deep Learning and Computer Vision

Course Curriculum

Course Content

  • Section 01 - Self Learning Curriculum

    Preview

    • Lesson 01 - Introduction to Computer Vision with OpenCV

      01:00:34Preview
      • 1.01 Course Overview
        04:30
      • 1.02 Setting Up Your Computer Vision Tools Python OpenCV Tensor
        08:55
      • 1.03 Image Formation and Digital Representation
        08:21
      • 1.04 Getting Started with OpenCV Four
        03:51
      • 1.05 Getting Started with OpenCV Four - Practical
        12:11
      • 1.06 Understanding Color Spaces and Applying Grayscaling
        04:49
      • 1.07 Understanding Color Spaces and Applying Grayscaling - Practical
        07:34
      • 1.08 Creating and Drawing on Images with OpenCV
        10:23

    • Lesson 02 - Introduction to Images

      01:51:08Preview
      • 2.01 Grayscale Image
        03:33
      • 2.02 Quiz Grayscale Image
        00:42
      • 2.03 Solution Grayscale Image
        01:20
      • 2.04 Grayscale Spectrum
        08:28
      • 2.05 Reading Manipulating and Saving Grayscale Image using Matplotlib Python
        14:18
      • 2.06 Quiz Reading Manipulating and Saving Grayscale Image using Matplotlib Python
        00:45
      • 2.07 Solution Reading Manipulating and Saving Grayscale Image using Matplotlib Python
        03:27
      • 2.08 Reading Manipulating and Saving Grayscale Image using OpenCV Python
        09:12
      • 2.09 Introduction to RGB Images
        05:49
      • 2.10 Quiz Introduction to RGB Images
        00:48
      • 2.11 Solution Introduction to RGB Images
        02:09
      • 2.12 RGB Color Images Matplotlib and OpenCV
        14:48
      • 2.13 Quiz RGB Color Images Matplotlib and OpenCV
        01:10
      • 2.14 Solution RGB Color Images Matplotlib and OpenCV
        04:23
      • 2.15 RGB to HSV theory and Algorithm
        06:11
      • 2.16 RGB to HSV Algorithm Implementation using Python
        10:06
      • 2.17 Quiz RGB to HSV Algorithm Implementation using Python
        00:47
      • 2.18 Solution RGB to HSV Algorithm Implementation using Python
        01:10
      • 2.19 Red Rose Extraction or Segmentation using HSV Python
        11:23
      • 2.20 Quiz Red Rose Extraction or Segmentation using HSV Python
        02:27
      • 2.21 Solution Red Rose Extraction or Segmentation using HSV Python
        02:04
      • 2.22 Hyper Spectral Images
        06:08

    • Lesson 03 - Image Manipulations in OpenCV Operations

      01:10:18Preview
      • 3.01 Translations Rotations and Transformations
        13:09
      • 3.02 Scaling Resizing Interpolations and Cropping
        05:34
      • 3.03 Scaling Resizing Interpolations and Cropping - Practical
        09:14
      • 3.04 Arithmetic and Bitwise Operations
        06:31
      • 3.05 Blurring and Sharpening Images
        04:35
      • 3.06 Blurring and Sharpening Images - Practical
        06:29
      • 3.07 Thresholding Binarization and Adaptive Thresholding
        04:18
      • 3.08 Thresholding Binarization and Adaptive Thresholding - Practical
        06:47
      • 3.09 Dilation Erosion and Edge Detection
        06:22
      • 3.10 Dilation Erosion and Edge Detection - Practical
        07:19

    • Lesson 04 - Image Segmentation and Object Detection in OpenCV

      50:22Preview
      • 4.01 Segmentation and Contours
        07:04
      • 4.02 Segmentation and Contours - Practical
        03:57
      • 4.03 Sorting and Approximating Contours
        03:00
      • 4.04 Sorting and Approximating Contours - Practical
        08:59
      • 4.05 Line Circle and Blob Detection
        03:30
      • 4.06 Line Circle and Blob Detection - Practical
        04:42
      • 4.07 Object Detection with HAAR Cascade Classifiers
        07:10
      • 4.08 Face and Eye Detection
        07:17
      • 4.09 Car and People Detection
        04:43

    • Lesson 05 - Deep Learning Transfer Learning and Object Detection

      01:03:16Preview
      • 5.01 Pre-Trained ImageNet Models
        09:25
      • 5.02 Introduction to Transfer Learning
        05:26
      • 5.03 Implementing Transfer Learning on CIFAR-Ten
        08:00
      • 5.04 R-CNNs SSDs and YOLO
        15:48
      • 5.05 Implementing Object Detection with SSDs and YOLO
        08:58
      • 5.06 Neural Art Style Transfer
        15:39

    • Lesson 06 - Optimal Generalization

      01:07:21Preview
      • 6.01 The Problem of Overfitting
        02:44
      • 6.02 Reduce Overfitting by Constraining Complexity
        01:57
      • 6.03 Regularization Approaches for Neural Networks
        02:35
      • 6.04 Penalize Large Weights via Regularization
        02:05
      • 6.05 How to Penalize Large Weights
        01:58
      • 6.06 Tips for Using Weight Regularization
        02:14
      • 6.07 Demo Weight Regularization Case Study Part One
        01:32
      • 6.08 Demo Weight Regularization Case Study Part Two
        04:01
      • 6.09 Activity Regularization
        02:11
      • 6.10 Encouraging Smaller Activations
        02:48
      • 6.11 Tips for Activity Regularization
        02:48
      • 6.12 Activity Regularization in Keras
        02:35
      • 6.13 Demo Activity Regularization Case Study
        03:19
      • 6.14 Forcing Small Weights
        02:45
      • 6.15 How to Use a Weight Constraint
        01:19
      • 6.16 Tips for Applying Weight Constraints
        01:30
      • 6.17 Weight Constraints in Keras
        01:42
      • 6.18 Demo Weight Constraint Case Study
        02:56
      • 6.19 Dropout
        02:02
      • 6.20 Dropout Mechanics
        01:27
      • 6.21 Dropout Tips
        02:21
      • 6.22 Dropout in Keras
        02:53
      • 6.23 Demo Dropout Case Study
        02:43
      • 6.24 Noise Regularization
        02:46
      • 6.25 How to Add Noise
        02:59
      • 6.26 Noise Tips
        01:46
      • 6.27 Adding Noise in Keras
        02:07
      • 6.28 Demo Noise Regularization Case Study
        03:18

    • Lesson 07 - Intro to Tensors PyTorch

      30:55Preview
      • 7.01 Intro
        00:18
      • 7.02 One Dimensional Tensors
        08:44
      • 7.03 Vector Operations
        05:23
      • 7.04 Two Dimensional Tensors
        05:30
      • 7.05 Slicing ThreeD Tensors
        03:03
      • 7.06 Matrix Multiplication
        03:21
      • 7.07 Gradient with PyTorch
        04:23
      • 7.08 Outro
        00:13

    • Lesson 08 - Linear Regression PyTorch

      53:48Preview
      • 8.01 Intro
        00:44
      • 8.02 Making Predictions
        06:15
      • 8.03 Linear Class
        04:29
      • 8.04 Custom Modules
        08:09
      • 8.05 Creating Dataset
        10:35
      • 8.06 Loss Function
        03:33
      • 8.07 Gradient Descent
        04:41
      • 8.08 Mean Squared Error
        03:15
      • 8.09 Training - Code Implementation
        11:36
      • 8.10 Outro
        00:31

    • Lesson 09 - Perceptrons PyTorch

      51:06Preview
      • 9.01 Intro
        00:31
      • 9.02 What is Deep Learning
        01:19
      • 9.03 Creating Dataset
        09:34
      • 9.04 Perceptron Model
        11:56
      • 9.05 Model Setup
        11:22
      • 9.06 Model Training
        10:38
      • 9.07 Model Testing
        05:23
      • 9.08 Outro
        00:23

    • Lesson 10 - Deep Neural Networks - PyTorch

      54:01Preview
      • 10.01 Intro
        00:28
      • 10.02 Non-Linear Boundaries
        02:56
      • 10.03 Architecture
        09:06
      • 10.04 Feedforward Process
        07:46
      • 10.05 Error Function
        04:10
      • 10.06 Backpropagation
        05:03
      • 10.07 Code Implementation
        08:49
      • 10.08 Testing Model
        15:21
      • 10.09 Outro
        00:22

  • Section 02 - Live Class Curriculum

    Preview

    • Lesson 01: Course Introduction

      • Learning Path
      • Program Components

    • Lesson 02: Introduction to Computer Vision

      • Introduction to Computer Vision
      • Discussion
      • Human Vision and Computer Vision
      • Computer Vision Tasks
      • Components of CV
      • Tools to perform computer vision tasks
      • Applications of Computer Vision
      • Challenges
      • Expectations from the learners
      • Key Takeaways

    • Lesson 03: Image formation and processing

      • Imaging system
      • Pinhole projection
      • Use of thin lenses
      • Problems with lenses
      • Perspective Imaging
      • Image Sensing
      • Image Resolution and Types of Sensors
      • Image as a function
      • Image gradient
      • Digital and Colored Images
      • RGB and HSV Models
      • Introduction to OpenCV
      • Reading and Writing an Image
      • Image Enhancements and Restoration
      • Image Manipulation
      • Pixel Processing
      • Thresholding
      • Convolution
      • Cany Edge Detection
      • Hough Transformation

    • Lesson 04: Revisiting ConvNets

      • CNN Building Blocks and Importance for CV
      • Convolution
      • Stride
      • Pooling
      • Flatten Layer
      • Practical aspects of CNN
      • Implementation on TensorFlow

    • Lesson 05: CNN Architectures and Transfer Learning

      • CNN Architectures and Transfer Learning
      • Advances in CNN Architectures
      • Data Augmentation
      • Batch Norm
      • Skip Connections
      • Bottleneck Layers
      • Classical CNN Architectures - LeNet-5, AlexNet
      • Advanced Architectures - Inception and GoogleNet
      • Advanced Architectures - ResNet
      • Transfer Learning
      • Implementation
      • Different approaches to transfer learning

    • Lesson 06: Object detection

      • Difference between classification, detection and segmentation
      • General Framework - Regional proposal
      • General Framework - Feature extraction and network prediction
      • Non-maximum Suppression
      • Object-Detector Evaluation Metrics
      • R-CNN
      • Fast R-CNN
      • Faster R-CNN
      • Real-time object detection using YOLO

    • Lesson 07: Image Segmentation

      • Defining image segmentation
      • Semantic segmentation using U-Net
      • Instance segmentation using Mask R-CNN

    • Lesson 08: Variational AutoEncoder

      • Overview
      • VAE and other AutoEncoders
      • Cost function of Variational AutoEncoder
      • KL Divergence Loss
      • Train a Variational AutoEncoder

    • Lesson 09: Generating images with Neural Style

      • What is Neural Style Transfer?
      • Loss function
      • Implementation

    • Lesson 10: Working with Deep Generative Models

      • What are GAN's
      • Basic Architecture
      • Applications of GAN
      • Training GAN
      • Popular GAN Architectures
      • DCGAN
      • Progressive GAN
      • Style GAN
      • Cycle GAN
      • Challenges with GAN training

    • Lesson 11: Optical character recognition

      • Introduction to OCR
      • Traditional OCR challenges
      • AI-driven OCR Pipeline
      • Image processing for text extraction
      • Segmentation
      • Line Segmentation
      • Word Segmentation
      • Python Libraries for OCR
      • Pytesseract
      • Keras OCR
      • Easy OCR
      • Evaluation of OCR
      • Character Error Rate and Word Error Rate
      • Implementation on Google Cloud
      • Implementation on AWS

    • Lesson 12: Distributed and Parallel Computing for Deep Learning Models

      • Introduction to CUDA architecture
      • Introduction to GPU
      • Benefits of GPUs
      • Distributed parallel training: parallelism and distribution
      • Introduction to tf.distribute
      • Model Parallelism and Data Parallelism
      • Distributed Training Across Multiple GPU's
      • Commonly used terms
      • Implementation of Data Parallelism
      • Synchronous and Asynchronous training
      • Parallelism in Hardware Platforms
      • Details Around all Strategies under tf.distribute
      • Federated Learning

    • Lesson 13: Explainable AI(XAI)

      • Introduction to XAI
      • How XAI helps
      • Methods of Explainability
      • LIME for model Explainability
      • SHAP for model explainability
      • Introduction to explainability using TCAV
      • Open XAI frameworks

    • Lesson 14: Deploying Deep Learning Models and Beyond

      • Importance of model deployment and key steps
      • Prepare Model for Deployment
      • Platforms for Model Deployment
      • AWS
      • Google Cloud AI
      • Azure
      • Nvidea

Contact Us

1-844-532-7688

( Toll Free )

Why Online Bootcamp

  • Develop skills for real career growthCutting-edge curriculum designed in guidance with industry and academia to develop job-ready skills
  • Learn from experts active in their field, not out-of-touch trainersLeading practitioners who bring current best practices and case studies to sessions that fit into your work schedule.
  • Learn by working on real-world problemsCapstone projects involving real world data sets with virtual labs for hands-on learning
  • Structured guidance ensuring learning never stops24x7 Learning support from mentors and a community of like-minded peers to resolve any conceptual doubts

Related Programs

  • Disclaimer
  • PMP, PMI, PMBOK, CAPM, PgMP, PfMP, ACP, PBA, RMP, SP, and OPM3 are registered marks of the Project Management Institute, Inc.