Complete Guide to Creating COCO Datasets

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