Udemy

Platform

English

Language

Software Engineering

Category

Train YOLO for Object Detection with Custom Data

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

4.44 (711 reviews)

Students

7 hours

Content

Jun 2021

Last Update
Regular Price


What you will 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


Description

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

  1. 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.

  2. After that, you’ll label individual dataset as well as create custom one by extracting needed images from huge existing dataset.

  3. 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.

  4. When datasets are ready, you’ll train and test YOLO v3-v4 detectors in Darknet framework.

  5. 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)


Screenshots

Train YOLO for Object Detection with Custom Data
Train YOLO for Object Detection with Custom Data
Train YOLO for Object Detection with Custom Data
Train YOLO for Object Detection with Custom Data

Content

Welcome

Introduction to the course

Quick Win - Step 1: Simple Object Detection by thresholding with mask

Quick Win - Step 2: Simple Object Detection by thresholding with mask

Activity: Let's get acquainted

Installing Miniconda, Python, PyCharm, OpenCV

Objects Detection with YOLO v3-v4

Introduction: What are the differences between approaches?

Objects Detection on Image with YOLO v3 and OpenCV

Activity: Detect Objects on this image

Objects Detection on Video with YOLO v3 and OpenCV

Activity: Detect Objects on this video

Objects Detection in Real Time with YOLO v3 and OpenCV

Quiz: What are the best practices for

Conclusion: key takeaways for Objects Detection with dnn library in OpenCV

YOLO v4: instructions

Labelling new dataset in YOLO format

Introduction: Data Annotation

How does labelled image in YOLO format looks like?

Useful resources for labelling

Labelling image in YOLO format

Activity: Label Objects on this image

Labelling video in YOLO format

Activity: Label Objects on this video

Preparing files for training

Quiz: What are the best practices for

Conclusion: key takeaways for labelling data in YOLO format

YOLO v4: instructions

Creating custom dataset in YOLO format

Introduction: How to create custom dataset?

Toolkit for downloading images

Downloading images from huge dataset

Activity: Download Images for these classes

Converting downloaded files to YOLO format

Preparing files for training

Joining datasets for training

Quiz: What are the best practices for

Conclusion: key takeaways for creating custom dataset and converting it to YOLO

YOLO v4: instructions

Converting Traffic Signs dataset in YOLO format

Introduction: One more custom dataset to be converted

Downloading Traffic Signs dataset

Converting downloaded Traffic Signs dataset to YOLO format

Preparing files for training

Quiz: What are the best practices for

Conclusion: key takeaways for converting Traffic Signs dataset in YOLO format

YOLO v4: instructions

Training YOLO v3-v4 in Darknet framework

Introduction: What is Darknet framework?

Installing Darknet

Checking installation

Preparing files for training

Setting up configuration files

Running training process

When do we stop training?

Activity: Test trained custom models on these images

Activity: Test trained custom models on these videos

Quiz: What are the best practices for

Conclusion: key takeaways for training YOLO v3 in Darknet framework

YOLO v4: instructions

Building PyQt user interface for Objects Detection with YOLO v3-v4

Congratulation word and recap of learned skills

What is next?

Installing PyQt for building user interface

Creating PyQt interface

Integrating YOLO v3 into PyQt interface

Running experiments with PyQt interface for Objects Detection

YOLO v4: instructions

How does it work?

How does YOLO v3 work?

Quiz: YOLO v3

YOLO v4

How to train YOLO v4: Instructions


Reviews

C
Carlos9 February 2021

The learning material is easy to follow and the instructor is very practical in his explanations. I hope to find this course always updated!. The course is worth it.

R
Rupendra26 January 2021

"No words to say", The course went on very well organized as well as the motive and goal of learning to train our custom object detection was perfectly fulfilled (100%) though I would recommend the author to tune the things towards the yolov4 which is is the latest(I do agree that most of the things to do with yolov4 are similar to yolov3) but may be then the course will show up to date

H
Harnish11 January 2021

Amazing, there are some content here that is not available on YouTube also, thanks @Valentyn for teaching me.

H
Hani28 December 2020

Missing a lot of lessons that force me to proceed in free youtube lessons. In addition, bad language but this is not issue to me ,but it is annoying sometimes.

T
Tamas30 November 2020

A very detailed and useful training, which absolute deliver its promises, to implement and train you own YOLO object detector.

E
Eder25 November 2020

Estou gostando muito e bem explicado é o que estou precisando para minha formação acadêmica, muito bom. O único ponto negativo é que só tem em ingles.

P
Plamen20 November 2020

The course is very detailed and very well organized! It offers solutions for real life scenarios (labeling datasets, joining datasets, etc.).

E
Ertug16 November 2020

The best course I have ever taken. Instructions very clear and code templates work good. Also instructor try to help us as best he can.

E
Enes5 November 2020

Fantastic course! Definitely exceded my all expectations, such complex topic is designed very well, structured to teach perfectly without missing any point. I think that, this is not just course, also very good guide for anyone who have interest on deep learning and object detection. Instructor also answered my all questions immediately, pointed me to right direction. I will follow him for upcoming courses. Finally i would like to thank him for all efforts.

A
Aditya19 October 2020

Excellent course for students and professionals who want to start with object detection. It helped me in completing a small project in the Deep Learning course in my master's.

S
Steven6 October 2020

Great course, at first i was unsure but as i went through it the explanations are simple enough to practically use YOLO. I would highly recommend this course. All the tools and methods worked

L
Léo1 October 2020

Probably the best most well organized course I have ever followed ! Everything works perfectly, we have all the documentation to do everything ourselves and the instructor is very clear ! EXCELLENT COURSE !

T
Thiago30 September 2020

Sim!! Era exatamente o que eu precisava para conseguir criar e treinar um detector de objetos com dataset personalizado usando YOLO

A
Andres22 August 2020

This was one of the best purchases I made and the truth is that I was very impressed on the level of Mr Valentyn's guide trough the course. You will get a lot of base code that one can improve for future complex projects I can hardly imagine all the dedication and time that he spent in making this piece of art for those making their first steps on Computer Vision using CNNs. If you are thinking of buying this course, you will not regret. And not only that, Mr Sichkar is very attentive to questions made by his students. Thank you for such complete course

S
Syeda22 August 2020

The course was amazing, Very new for me. But i think the lecturer as able to explain in the easiest way. Thanks


2448144

Udemy ID

7/7/2019

Course created date

3/5/2021

Course Indexed date
Bot
Course Submitted by