Course Outline

Introduction

Overview of YOLO Pre-trained Models Features and Architecture

  • The YOLO Algorithm
  • Regression-based Algorithms for Object Detection
  • How is YOLO Different from RCNN?

Utilizing the Appropriate YOLO Variant

  • Features and Architecture of YOLOv1-v2
  • Features and Architecture of YOLOv3-v4

Installing and Configuring the IDE for YOLO Implementations

  • The Darknet Implementation
  • The PyTorch and Keras Implementations
  • Executing the OpenCV and NumPy

Overview of Object Detection Using YOLO Pre-trained Models

Building and Customizing Python Command-Line Applications

  • Labeling Images Using the YOLO Framework
  • Image Classification Based on a Dataset

Detecting Objects in Images with YOLO Implementations

  • How do Bounding Boxes Work?
  • How Accurate is YOLO for Instance Segmentation?
  • Parsing the Command-line Arguments

Extracting the YOLO Class Labels, Coordinates, and Dimensions

Displaying the Resulting Images

Detecting Objects in Video Streams with YOLO Implementations

  • How is it Different from Basic Image Processing?

Training and Testing the YOLO Implementations on a Framework

Troubleshooting and Debugging

Summary and Conclusion

Requirements

  • Python 3.x programming experience
  • Basic knowledge of any Python IDEs
  • Experience with Python argparse and command-line arguments
  • Comprehension of computer vision and machine learning libraries
  • An understanding of fundamental object detection algorithms

Audience

  • Backend Developers
  • Data Scientists
  7 Hours
 

Number of participants


Starts

Ends


Dates are subject to availability and take place between 09:30 and 16:30.
Open Training Courses require 5+ participants.

Testimonials (4)

Related Courses

Related Categories