This course is designed for anyone eager to train their own YOLOv4 neural network from scratch. You’ll begin with the basics of computer vision and YOLOv4 setup, then move on to real-time image and video detection projects like social distancing monitoring and vehicle tracking with DeepSORT. You’ll also learn to build GUIs with PyQT, label and prepare datasets, and use data augmentation to boost training performance. Finally, you’ll develop a Mask Detection app, applying your skills to real-world problems. By the end, you’ll be able to train and deploy custom YOLOv4 models for research, freelancing, or professional AI projects.
Who should take this course?
This course is designed for data scientists, AI enthusiasts, researchers, and developers who want to specialize in computer vision and object detection using YOLOv4. It’s well-suited for those with a background in Python and deep learning who are looking to apply YOLOv4 to real-world projects such as image recognition, surveillance, autonomous systems, or AI-powered applications. Whether you’re a student exploring advanced AI techniques or a professional aiming to enhance your expertise in computer vision, this course equips you with the skills to master YOLOv4 effectively.
What you will learn
YOLOv4 detection on images
Execute YOLOv4 detection on videos and webcam
How to natively train your own custom YOLOv4 detector
Prepare files to train and set up configuration files
Integrate YOLOv4 with PyQT
Social distancing GUI with PyQT
Course Outline
Introduction to the Course
Introduction
How to Excel in this Course
YOLOv4 Theory
Installation of YOLOv4 Dependencies such as CUDA, Python, OpenCV
Object Detection with YOLOv4
YOLOv4 Object Detection on Image and Video
YOLOv4 Darknet Explanation with Code and Webcam Implementation
Social Distancing Monitoring App
Social Distancing Monitoring Coaching Session
Count Parked Cars
DeepSORT Intuition - How DeepSORT Object Tracking Works
Robust Tracking with YOLOv4 and DeepSORT
YOLOv4 Starter Summary
Evolution of YOLOv1 to YOLOv3
YOLOv5 Chess Piece Detection
Bernie Sanders Detector
Labelling a New Dataset in YOLOv4 Format
Introduction to Data Annotation
YOLOv4 Format for Image Labelling
YOLOv4 Labelling Tools
Web-Scaping Data
Annotating Images with LabelImg
Labelling on Video Using LabelImg
Labelling on Video Using Darklabel
Label Objects on this Video
Annotation Summary
Data Annotation Key Takeaway
Creating Custom Dataset in YOLOv4 Format
Introduction: How to Create Custom Dataset
Toolkit for Downloading Image Datasets
Downloading Images from Specific Classes
Converting Downloaded Files to YOLOv4 format
Data Augmentation Using Rotational Transform
Summary - Key Takeaways for Custom Datasets
Training YOLOv4 Using Darknet Framework
Introduction to Training YOLOV4 with Darknet Framework
Step 1 - Configuring the Files for Training
Step 2 - Creating the obj.names File
Step 3 - Dataset Placement for Training
Step 4 - Train Test Metafiles
Step 5 - Training YOLOv4
Trained YOLOv4 Execution on Image and Video for Mask Detection
Activity: Train on Your Own Dataset
When to Stop Training
Summary - Key Takeaways
PyQT User Interface for Object Detection with YOLOv4
Introduction to Object Detection with PyQt
Installing PyQt
GUI Layout Using PyQt Designer
Integrating PyQt with YOLOv4
Code Explanation
Adding GUI Widgets - Counting Objects
Adding Widgets - Slider Threshold
Adding Widgets - Class Filter Using Checkbox Widget
