Udemy Business

Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Train YOLO for Object Detection with Custom Data

Name: Train YOLO for Object Detection with Custom Data
Rating: 4.4 (1229 reviews)

Build your own detector by labelling, training and testing on image, video and in real time with camera: YOLO v3 and v4

Created byValentyn Sichkar

Last updated 11/2023

English

What you'll learn

Apply already trained YOLO v3-v4 for Object Detection on image, video and in real time with camera
Label own dataset and structure files in YOLO format
Train YOLO v3-v4 detector in Darknet framework
Assemble custom dataset in YOLO format
Convert existing dataset of Traffic Signs in YOLO format
Build individual PyQt graphical user interface for Object Detection based on YOLO v3-v4 algorithm

Course content

10 sections • 59 lectures • 7h 6m total length

Introduction to the course3:24
What am I going to learn in this course?
What will I be able to do by the end of the course?
Will this course be fun and engaging?
Quick Win - Step 1: Simple Object Detection by thresholding with mask10:48
Reading image with Blue Object and finding the needed mask.
Quick Win - Step 2: Simple Object Detection by thresholding with mask8:29
Detecting Object in Real Time according to the founded mask. Drawing rectangle with OpenCV around the Object and labeling it.
Activity: Let's get acquainted1:22
Quickly share who you are, where you’re from and why you chose to do this course.
Installing Miniconda, Python, PyCharm, OpenCV3:39
Needed prerequisites to be installed.

Introduction: What are the differences between approaches?2:35
Differences of Objects Detection on image, video and in real time with camera.
Objects Detection on Image with YOLO v3 and OpenCV23:34
Writing code for Objects Detection on Image. Testing results.
Activity: Detect Objects on this image1:10
Download image and implement Objects Detection on it.
Objects Detection on Video with YOLO v3 and OpenCV14:02
Writing code for Objects Detection on Video. Testing results.
Activity: Detect Objects on this video1:09
Download video and implement Objects Detection on it.
Objects Detection in Real Time with YOLO v3 and OpenCV5:56
Writing code for Objects Detection in Real Time with Camera. Testing results.
Quiz: What are the best practices for
Conclusion: key takeaways for Objects Detection with dnn library in OpenCV1:12
Recap, summarize, sense of progress, transition to the next step.
YOLO v4: instructions0:16
Instructions on how to test YOLO v4.

Introduction: Data Annotation1:29
Why do we need data annotation techniques?
How does labelled image in YOLO format looks like?2:11
Representation of image in YOLO format.
Useful resources for labelling3:04
Overview of different useful and free resources for labelling.
Labelling image in YOLO format12:23
Step-by-step instructions on how to use labelling tool and save results.
Activity: Label Objects on this image0:56
Download image and implement labelling of the Objects on it.
Labelling video in YOLO format9:50
Step-by-step instructions on how to get set of images from video and label them.
Activity: Label Objects on this video1:03
Download video and implement labelling of the Objects on it.
Preparing files for training17:38
Writing code for preparing needed files to train in Darknet framework for Labelled data.
Quiz: What are the best practices for
Conclusion: key takeaways for labelling data in YOLO format1:10
Recap, summarize, sense of progress, transition to the next step.
YOLO v4: instructions0:04
Instructions for YOLO v4.

Introduction: How to create custom dataset?1:25
How to use huge existing dataset to create custom one.
Toolkit for downloading images1:21
Setting up toolkit for further downloading needed images from huge dataset.
Downloading images from huge dataset9:45
By using toolkit, downloading needed images from huge dataset.
Activity: Download Images for these classes1:34
Download 10 images for every of the given classes.
Converting downloaded files to YOLO format35:27
Writing code for converting annotations for downloaded images into YOLO format.
Preparing files for training14:29
Preparing needed files to train in Darknet framework for Custom data.
Joining datasets for training30:27
Joining needed files of datasets to train in Darknet framework.
Quiz: What are the best practices for
Conclusion: key takeaways for creating custom dataset and converting it to YOLO1:35
Recap, summarize, sense of progress, transition to the next step.
YOLO v4: instructions0:05
Instructions for YOLO v4.

Introduction: One more custom dataset to be converted1:34
How to use existing Traffic Signs dataset and prepare it for training by YOLO v3.
Downloading Traffic Signs dataset4:02
Step-by-step instructions on how to download Traffic Signs dataset.
Converting downloaded Traffic Signs dataset to YOLO format26:09
Writing code for converting original annotations for downloaded dataset into YOLO format.
Preparing files for training12:24
Preparing needed files to train in Darknet framework for Traffic Signs dataset.
Quiz: What are the best practices for
Conclusion: key takeaways for converting Traffic Signs dataset in YOLO format1:04
Recap, summarize, sense of progress, transition to the next step.
YOLO v4: instructions0:05
Instructions for YOLO v4.

Introduction: What is Darknet framework?1:40
Darknet framework for training YOLO v3 Object Detector.
Installing Darknet7:08
Step-by-step instructions on how to install Darknet framework.
Checking installation16:18
Playing with different built-in tools for Objects Detection in Darknet framework.
Preparing files for training4:00
Preparing needed files to train in Darknet framework for custom datasets.
Setting up configuration files24:48
Adjusting configuration files for training and testing with custom datasets in Darknet framework.
Running training process7:04
Step-by-step instructions on how to run training process in Darknet framework.
When do we stop training?5:23
Tips on how to define optimal number of iterations for training in Darknet framework.
Activity: Test trained custom models on these images2:35
Download images, weights and implement Objects Detection by using trained weights and cfg file for testing YOLO v3.
Activity: Test trained custom models on these videos2:26
Download videos and implement Objects Detection by using trained weights and cfg file for testing YOLO v3.
Quiz: What are the best practices for
Conclusion: key takeaways for training YOLO v3 in Darknet framework1:06
Recap, summarize, sense of progress, transition to the next step.
YOLO v4: instructions0:49
Instructions for YOLO v4.

Congratulation word and recap of learned skills1:54
Thank you and congratulation words. Recap what has been learned.
What is next?4:38
Where to go from here. Tips on how to experiment with training Custom Models.
Installing PyQt for building user interface8:10
Step-by-step instructions on how to install PyQt for building GUI.
Creating PyQt interface25:35
Step-by-step instructions on how to create PyQt GUI.
Integrating YOLO v3 into PyQt interface11:15
Step-by-step instructions on how to integrate YOLO v3 into created PyQt GUI.
Running experiments with PyQt interface for Objects Detection0:54
Testing PyQt GUI for Objects Detection with YOLO v3.
YOLO v4: instructions0:06
Instructions for YOLO v4.

Requirements

Basic knowledge of Object Detection algorithms
Basics on how YOLO works
Intermediate knowledge of Python v3
Basic knowledge of OpenCV
Basics on how to work with Anaconda Environments
Basics on how to work with PyCharm IDE or any other Python IDE
Basics on how to work with Terminal Window or Anaconda Prompt
To have Linux Ubuntu installed is optional, but recommended

Description

In this hands-on course, you'll train your own Object Detector using YOLO v3-v4 algorithms.

As for beginning, you’ll implement already trained YOLO v3-v4 on COCO dataset. You’ll detect objects on image, video and in real time by OpenCV deep learning library. The code templates you can integrate later in your own future projects and use them for your own trained YOLO detectors.
After that, you’ll label individual dataset as well as create custom one by extracting needed images from huge existing dataset.
Next, you’ll convert Traffic Signs dataset into YOLO format. Code templates for converting you can modify and apply for other datasets in your future work.
When datasets are ready, you’ll train and test YOLO v3-v4 detectors in Darknet framework.
As for Bonus part, you’ll build graphical user interface for Object Detection by YOLO and by the help of PyQt. This project you can represent as your results to your supervisor or to make a presentation in front of classmates or even mention it in your resume.

Content Organization. Each Section of the course contains:

Video Lectures
Coding Activities
Code Templates
Quizzes
Downloadable Instructions
Discussion Opportunities

Video Lectures of the course have SMART objectives:

S - specific (the lecture has specific objectives)

M - measurable (results are reasonable and can be quantified)

A - attainable (the lecture has clear steps to achieve the objectives)

R - result-oriented (results can be obtained by the end of the lecture)

T - time-oriented (results can be obtained within the visible time frame)

Who this course is for:

Students who study Computer Vision and want to know how to use YOLO for Object Detection
Students who know basics of Object Detection but want to know how to Train YOLO with New Data
Students who study YOLO and want to Label Own Data in YOLO format
Students who use already existing datasets for Object Detection but want to Convert them in YOLO format
Young Researchers who study different Object Detection Algorithms and want to Train YOLO with Custom Data and Compare results with different approaches

Train YOLO for Object Detection with Custom Data

What you'll learn

Explore related topics

Course content

Welcome5 lectures • 28min

Objects Detection with YOLO v3-v48 lectures • 50min

Labelling new dataset in YOLO format10 lectures • 50min

Creating custom dataset in YOLO format9 lectures • 1hr 36min

Converting Traffic Signs dataset in YOLO format6 lectures • 45min

Training YOLO v3-v4 in Darknet framework11 lectures • 1hr 13min

Building PyQt user interface for Objects Detection with YOLO v3-v47 lectures • 53min

How does it work?1 lecture • 26min

YOLO v41 lecture • 5min

YOLO v51 lecture • 1min

Requirements

Description

Who this course is for: