Introduction:
Computer Vision is undergoing rapid advances in recent years. In advanced computer vision training course, you will learn state of the art computer vision techniques such Region-based CNN and YOLO techniques. You will also learn about convolutional neural network and transfer learning.
Computer Vision is a field of Artificial Intelligence and Computer Science that aims at giving computers a visual understanding of the world. Computer Vision has been used in face recognition, autonomous cars, image search, optical character recognition, robotics vision, machine vision, and many applications.
Course Objectives:
- ConvNET
- Transfer Learning
- R-CNN Based Object Detection
- YOLO Based Object Detection
Duration
7 hours, 1 Day Course
Mode of Delivery
Classroom-based, Instructor-led Training
Course Outlines
- Overview of Computer Vision
- Computer Vision Tasks
- Computer Vision Applications
- Setup Google Colab for Keras
- ConvNet
- What is ConvNET?
- ConvNET Architecture
- Image Classification for HandWritten Digits
- Image Classification for Cats and Dogs Small Dataset
- ImageDataGenerator
- Fit Generator
- Overfitting Issue
- Dropout & Data Augmentation
- Mini Project – Convnet with User Own Images
- Transfer Learning
- What is Transfer Learning
- Transfer Learning with VGG16 Model
- Fine Tuning VGG16 Model for Cats and Dogs Small Dataset
- Mini Project – Transfer Learning with User Own Images
- R-CNN
- R-CNN
- Fast R-CNN
- Faster R-CNN
- Mask R-CNN
- Mask R-CNN Demo
- YOLO
- What is YOLO
- YOLO Algorithm
- Anchor Boxes
- IOU
- Non Max Suppression
- YOLO v3 Demo