Description

This course is about developing core skills that will stay with you for a lifetime. It is designed such that you can watch the material and follow along step-by-step. It focuses on the implementation of YOLOv4 to get you up and running. You'll be an object detecting ninja in no time and be able to graduate to more advanced content.

This course is a perfect fit if you want to natively train your own YOLOv4 neural network. You'll start off with a gentle introduction to the world of computer vision with YOLOv4, install darknet, and build libraries for YOLOv4 to implement YOLOv4 on images and videos in real-time. You'll even solve current and relevant real-world problems by building your own social distancing monitoring app and implementing vehicle tracking using the robust DeepSORT algorithm. After that, you'll learn more techniques and best practices/rules of how to take your Python implementations and develop GUIs for your YOLOv4 apps using PyQT. Then, you'll be labeling your own dataset from scratch, converting standard datasets into YOLOv4 format, amplifying your dataset 10x, and employing data augmentation to significantly increase the diversity of available data for training models, without collecting new data. Finally, you'll develop your own Mask Detection app to detect whether a person is wearing their mask and to flag an alert. By the end of this course, you'd be able to implement and train your own custom CNNs with YOLOv4. It will help you in solving real-world problems, freelancing AI projects, getting that opportunity in AI, and tackling your research work by saving time and money. The world is your oyster; just start exploring the world once you have skills in AI. All the resource files are uploaded on the GitHub repository at https://github.com/PacktPublishing/Full-YOLOv4-Pro-Course-Bundle

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

Audience

This course is for developers, researchers, and students who have at least some programming experience and want to become proficient in AI for computer vision and visual recognition. An individual with machine learning knowledge and who wants to break into neural networks or AI for visual understanding, a scientist looking to apply deep learning + computer vision algorithms, individuals looking to utilize computer vision algorithms in their own projects will highly benefit from this course.

A high-range PC/laptop, Windows 10, and CUDA Nvidia GPU graphics card are pre-requisites.

Approach

This course is a good mix of theory, complex equations, and activities that you'll learn in a fun and practical way with the help of code.

It is designed in such a way that the individual practices as he/she learns and unwinds new concepts in a step-by-step manner. This course is designed to make AI easy, through tried and tested training that saves you time.

Key Features

Social distancing app to calculate the distance between people to determine if they are at risk * Object counting app for counting cars in a parking lot and DeepSORT to track vehicles in traffic * Mask detection app to detect whether or not a person is wearing a mask; if not, flagging an alert

Github Repo

https://github.com/PacktPublishing/Full-YOLOv4-Pro-Course-Bundle

About the Author

Ritesh Kanjee

Augmented Startups have over 8 years experience in Printed Circuit Board (PCB) design as well in image processing and embedded control. Author Ritesh Kanjee has completed his Masters Degree in Electronic engineering and published two papers on the IEEE Database with one called "Vision-based adaptive Cruise Control using Pattern Matching" and the other called "A Three-Step Vehicle Detection Framework for Range Estimation Using a Single Camera" (on Google Scholar). His work was implemented in LabVIEW. He works as an embedded electronic engineer in defence research and has experience in FPGA design with programming in both VHDL and Verilog. He also has expertise in augmented reality and machine learning in which he shall be introducing new technologies through the medium of video

Course Outline

1. Introduction to the Course

1. Introduction

This video provides an introduction to the first part of the course, YOLOv4 Starters.

2. How to Excel in this Course

This video provides some pointers on how to excel in this course.

3. YOLOv4 Theory

This video demonstrates the theory of YOLOv4.

4. Installation of YOLOv4 Dependencies such as CUDA, Python, OpenCV

This video demonstrates the installation of YOLOv4 dependencies such as CUDA, Python, OpenCV, and so on.

2. Object Detection with YOLOv4

1. YOLOv4 Object Detection on Image and Video

This video talks about YOLOv4 object detection on image and video.

2. YOLOv4 Darknet Explanation with Code and Webcam Implementation

This video is about YOLOv4 darknet explanation with code and webcam implementation.

3. Social Distancing Monitoring App

This video helps you create social distancing monitoring app.

4. Social Distancing Monitoring Coaching Session

This video talks about social distancing monitoring coaching session.

5. Count Parked Cars

This video helps you create an app to count parked cars.

6. DeepSORT Intuition - How DeepSORT Object Tracking Works

This video explains DeepSORT intuition - how DeepSORT object tracking works.

7. Robust Tracking with YOLOv4 and DeepSORT

This video explains robust tracking with YOLOv4 and DeepSORT.

3. YOLOv4 Starter Summary

1. Evolution of YOLOv1 to YOLOv3

This video provides an evolution of YOLOv1 to YOLOv3.

2. YOLOv5 Chess Piece Detection

This video demonstrates the YOLOv5 chess piece detection.

3. Bernie Sanders Detector

This video explains how to detect the image of Bernie Sanders.

4. Labelling a New Dataset in YOLOv4 Format

1. Introduction to Data Annotation

This video provides an introduction to data annotation.

2. YOLOv4 Format for Image Labelling

This video demonstrates YOLOv4 format for image labelling.

3. YOLOv4 Labelling Tools

This video talks about YOLOv4 labelling tools.

4. Web-Scaping Data

This video explains web-scaping data.

5. Annotating Images with LabelImg

This video explains annotating images with LabelImg.

6. Labelling on Video Using LabelImg

This video demonstrates labelling on video using LabelImg.

7. Labelling on Video Using Darklabel

This video explains the labelling on video using Darklabel.

8. Label Objects on this Video

This video explains how to label objects on this video.

9. Annotation Summary

This video provides a summary on annotation.

10. Data Annotation Key Takeaway

This video talks about the key takeaway from the data annotation part.

5. Creating Custom Dataset in YOLOv4 Format

1. Introduction: How to Create Custom Dataset

This video provides an introduction to create custom dataset.

2. Toolkit for Downloading Image Datasets

This video talks about toolkit for downloading image datasets.

3. Downloading Images from Specific Classes

This video explains downloading images from specific classes.

4. Converting Downloaded Files to YOLOv4 format

This video explains how to convert downloaded files to YOLOv4 format.

5. Data Augmentation Using Rotational Transform

This video talks about data augmentation using rotational transform.

6. Summary - Key Takeaways for Custom Datasets

This video demonstrates the key takeaways for custom datasets.

6. Training YOLOv4 Using Darknet Framework

1. Introduction to Training YOLOV4 with Darknet Framework

This video provides an introduction to training YOLOV4 with darknet framework.

2. Step 1 - Configuring the Files for Training

This video focusses on the first step that =is configuring the files for training.

3. Step 2 - Creating the obj.names File

This video explains the second step for creating the obj.names file.

4. Step 3 - Dataset Placement for Training

This video explains the third step that covers dataset placement for training.

5. Step 4 - Train Test Metafiles

This video explains the fourth step that focuses on train test metafiles.

6. Step 5 - Training YOLOv4

This video explains the fifth step that focuses on training YOLOv4.

7. Trained YOLOv4 Execution on Image and Video for Mask Detection

This video explains trained YOLOv4 execution on image and video for mask detection.

8. Activity: Train on Your Own Dataset

This video demonstrates an activity on training the dataset.

9. When to Stop Training

This video explains when to stop training.

10. Summary - Key Takeaways

This video focuses on the key takeaways of this section.

7. PyQT User Interface for Object Detection with YOLOv4

1. Introduction to Object Detection with PyQt

This video provides an introduction to object detection with PyQt.

2. Installing PyQt

This video explains the installation of PyQT.

3. GUI Layout Using PyQt Designer

This video explains the GUI layout using PyQt designer.

4. Integrating PyQt with YOLOv4

This video explains integrating PyQt with YOLOv4.

5. Code Explanation

This video explains the code in detail.

6. Adding GUI Widgets - Counting Objects

This video explains adding GUI widgets - counting objects.

7. Adding Widgets - Slider Threshold

This video talks about adding widgets - slider threshold.

8. Adding Widgets - Class Filter Using Checkbox Widget

This video explains adding widgets - class filter using the checkbox widget.

9. Adding Widgets - Real-Time Live Plot Graph Widget

This video explains adding widgets - real-time live plot graph widget.

10. Social Distancing in PyQt Activity

This video is an activity on social distancing in PyQt.

11. Conclusion

This video provides a summary to this section.

Course Images

Full YOLOv4 Pro Course Bundle

By Packt

Booking options

Highlights