Complete Guide to Creating COCO Datasets

Complete Guide to Creating COCO Datasets, available at $29.99, has an average rating of 4.6, with 53 lectures, 7 quizzes, based on 366 reviews, and has 946 subscribers.

You will learn about How COCO annotations work and how to parse them with Python How to go beyond the original 90 categories of the COCO dataset How to automatically generate a huge synthetic COCO dataset with instance annotations How to train a Mask R-CNN to detect your own custom object categories in real photos This course is ideal for individuals who are Developers who have completed a Deep Learning course and want to solve real-world image recognition problems or Developers looking for a deep walkthrough of creating a COCO dataset and training a Mask R-CNN It is particularly useful for Developers who have completed a Deep Learning course and want to solve real-world image recognition problems or Developers looking for a deep walkthrough of creating a COCO dataset and training a Mask R-CNN.

Enroll now: Complete Guide to Creating COCO Datasets

Summary

Title: Complete Guide to Creating COCO Datasets

Price: $29.99

Average Rating: 4.6

Number of Lectures: 53

Number of Quizzes: 7

Number of Published Lectures: 53

Number of Published Quizzes: 7

Number of Curriculum Items: 60

Number of Published Curriculum Objects: 60

Original Price: $29.99

Quality Status: approved

Status: Live

What You Will Learn

How COCO annotations work and how to parse them with Python

How to go beyond the original 90 categories of the COCO dataset

How to automatically generate a huge synthetic COCO dataset with instance annotations

How to train a Mask R-CNN to detect your own custom object categories in real photos

Who Should Attend

Developers who have completed a Deep Learning course and want to solve real-world image recognition problems

Developers looking for a deep walkthrough of creating a COCO dataset and training a Mask R-CNN

Target Audiences

Developers who have completed a Deep Learning course and want to solve real-world image recognition problems

Developers looking for a deep walkthrough of creating a COCO dataset and training a Mask R-CNN

In this course, you’ll learn how to create your own COCO dataset with images containing custom object categories. You’ll learn how to use the GIMP image editor and Python code to automatically generate thousands of realistic, synthetic images with minimal manual effort. I’ll walk you through all of the code, which is available on GitHub, so that you can understand it at a fundamental level and modify it for your own needs.

(Important:?If you only want to do manual image annotation, this course is not for you. Google “coco annotator” for a great tool you can use. This course teaches how to generate datasets automatically.)

By the end of this course, you will:

Have a full understanding of how COCO datasets work

Know how to use GIMP to create the components that go into a synthetic image dataset

Understand how to use code to generate COCO Instances Annotations in JSON format

Create your own custom training dataset with thousands of images, automatically

Train a Mask R-CNN to spot and mark the exact pixels of custom object categories

Be able to apply this knowledge to real world problems

I’ve saved weeks of my precious time using this method because I’m not doing the tedious task of manual image labeling, which can easily take a full 40 hour work week to create 1000 images. You should value your time too. After all, how are you going to solve the world’s problems if you’re busy clicking outlines on images for the next couple weeks?

Soundtrack by Silk Music
Track name: Shingo Nakamura – Hakodate

Course Curriculum

Chapter 1: Course Introduction

Lecture 1: Section Introduction

Lecture 2: Case Study: Weed Detection

Lecture 3: Initial setup and resources

Lecture 4: End to end flow of the course

Chapter 2: COCO Image Viewer

Lecture 1: Section Introduction

Lecture 2: Overview

Lecture 3: Initialization

Lecture 4: Processing COCO Instances JSON

Lecture 5: Display info, licenses, and categories

Lecture 6: Display Image: Open and calculate resize ratio

Lecture 7: Display Image: Polygon segmentations

Lecture 8: Display Image: RLE segmentation concept

Lecture 9: Display Image: RLE segmentation code

Lecture 10: Running the notebook on the COCO Dataset

Chapter 3: Dataset Creation with GIMP

Lecture 1: Section Introduction

Lecture 2: Opening, scaling, and exporting

Lecture 3: Create first mask and export

Lecture 4: Use layers to create second mask

Lecture 5: Remaining images time-lapse

Lecture 6: Mask definitions JSON

Lecture 7: Mask definitions JSON (remaining images)

Chapter 4: COCO JSON Utils

Lecture 1: Section Introduction

Lecture 2: Context for coco_json_utils.py

Lecture 3: Overview

Lecture 4: Validate and process arguments and create info

Lecture 5: Create licenses and categories

Lecture 6: Create images and annotations

Lecture 7: Split multicolored mask into isolated masks

Lecture 8: Create annotations with isolated masks

Lecture 9: Running coco_json_utils.py

Chapter 5: Foreground Cutouts with GIMP

Lecture 1: Section Introduction

Lecture 2: Context for cutting out foregrounds

Lecture 3: Foreground Select Tool (rough)

Lecture 4: Foreground Select Tool (clean) and export

Lecture 5: Free Select Tool with Feather Edges

Chapter 6: Image Composition

Lecture 1: Section Introduction

Lecture 2: MaskJsonUtils overview, adding categories, and adding masks

Lecture 3: Getting masks, getting super categories, and writing to json

Lecture 4: ImageComposition overview

Lecture 5: Validate and process arguments

Lecture 6: Validate and process foregrounds and backgrounds

Lecture 7: Choose random foregrounds and background

Lecture 8: Crop background and transform foregrounds

Lecture 9: Compose images and masks

Lecture 10: Save images and mask definitions json

Lecture 11: Create dataset info

Lecture 12: Running image_composition.py and coco_json_utils.py

Chapter 7: Training Mask R-CNN

Lecture 1: Section Introduction

Lecture 2: Getting started with Mask R-CNN

Lecture 3: Preparing to train with our synthetic dataset

Lecture 4: Training

Lecture 5: Running inference on real test images

Chapter 8: Course Wrap

Lecture 1: Overview and wrap

Instructors

Adam Kelly Immersive Limit
3D DEVELOPMENT + DEEP LEARNING

Rating Distribution

1 stars: 4 votes

2 stars: 5 votes

3 stars: 28 votes

4 stars: 119 votes

5 stars: 210 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!