Computer Vision

Computer Vision field includes methods for collecting, processing, interpreting and understanding images, and videos automatically. It mainly focuses on enhancing the ability of a machine. This ability to extract the information means converting the images to textual data, which involves the theory following artificial systems.

Request a quote Review training schedules

Learn more about the course below.

TRAINING SCHEDULES

Computer Vision Training program overview

You will learn to work with real-world data to understand its complexities and be capable of building more data. It will also help you to increase your working capabilities on AI projects and will make you capable to build your own AI solutions.

Overview

Skills

Understand the fundamentals of Computer Vision

The registration process

Once you have completed our simplified enrolment process, you’ll receive an email confirmation with your payment receipt in your registered email ID. You can then access the entire content of the online student portal immediately by logging in to your account on our site. Should you require any assistance please reach out to us via email (support@greycampus.com) or via our online chat system.

The course curriculum

The curriculum for this Computer Vision training incorporates all updates to the certification exam. The following is a list of broad topics covered

  • Challenges in working with Real World data
  • Building information on a Dataset
  • Notebook: Download and Organize Flowers dataset
  • Notebook: Visualize an Image in Keras
  • Using Batch generator to avoid Memory error
  • Exercise: Image Classifier using Batch Generator
  • Notebook: Image Classifier for Flowers Dataset
  • Generating data with Image Augmentation
  • Exercise: Using Image Augmentation for Model training
  • Notebook: Image Augmentation with Keras
  • Notebook: Classifier with Image Augmentation
  • Role of ImageNet in Computer Vision
  • CNN based Models: AlexNet, ZFNet and VGG16
  • GooLeNet: Understanding Inception Module
  • ResNet Architecture
  • Notebook: ResNet Block in Keras
  • Understanding Transfer Learning
  • Exercise: Implementing Transfer Learning
  • Notebook: Image Classifier using Transfer Learning
  • Different ways to use Transfer Learning
  • Object Localization
  • Exercise: Data Pre-processing for Object Localization
  • Exercise: Visualizing Bounding Box in an image
  • Notebook: Pascal Dataset Download & Visualization
  • Exercise: Image Augmentation in Object Localization
  • Notebook: Image Augmentation for Localization
  • Exercise: Building information on Dataset
  • Exercise: Getting data with Single Objects for Object Localization
  • Exercise: Building Model and Visualizing predictions
  • Notebook: Object Localization
  • What is Object Detection
  • R-CNN for Object Detection
  • Faster R-CNN for Detection
  • Single Shot Detectors (SSD)
  • Multibox SSD Architecture
  • Intersection over Union (IoU)
  • TensorFlow Object Detection API
  • Notebook: Object Detection API Installation
  • Selecting Architecture for Model training
  • Exercise: Preparing data in TFRecord format
  • Exercise: Creating a Label Mapping file
  • Notebook: Pascal Dataset - Build Multi Annotations CSV
  • Notebook: Create TFRecord and Label Mapping file
  • Exercise: Model Training using Object Detection API
  • Notebook: Model Training
  • Attention in Seq2Seq Model
  • Alignment Weights in Attention
  • Attention Layer in Seq2Seq Model
  • Exercise: Implement Attention for Training Model
  • Exercise: Implement Attention for Prediction Model