A training workshop on the design and implementation of computer vision applications for object detection and recognition, using modern deep learning tools and technologies. Topics include an introduction to object detection and recognition, using R-CNN and the inception models, SSD architecture and MobileNet, and approaches for training deep learning models for object classification.

PREREQUISITE : Pass "STEP 3 : Math & Statistics for Data Science" course or Have basic knowledge in Deep Learning

Lesson 1 Introduction to Object Detection & Recognition (6 hours)
  1.1. Overview of object detection tasks & pipelines
  1.2. Object detection using YOLO
  1.3. Overview of object recognition
  1.4. Example: Face recognition using FaceNet
Lesson 2 R-CNN & the Inception Models (6 hours)
  2.1. Understanding R-CNN family of algorithms
  2.2. Object detection using R-CNN & pre-trained models
  2.3. Understanding Inception models
  2.4. Training an Inception model for object recognition
Lesson 3 SSD Architecture & MobileNet Models (6 hours)
  3.1. Overview of SSD architecture
  3.2. Object detection using SSD: OpenCV’s Caffe Model example
  3.3. Understanding MobileNet models
  3.4. Training MobileNet for object recognition
Lesson 4 Object Classification (6 hours)
  4.1. Overview of object classification problems
  4.2. Importance of feature extraction: feature embeddings
  4.3. Training a deep learning model for feature extraction
  4.4. Pipelining object detection & classification for real-world applications