Computer Vision: YOLO Custom Object Detection with Colab GPU

YOLO: Pre-Trained COCO Dataset and Custom-Trained Coronavirus Object Detection Model with Google Colab GPU Training

Created by Abhilash Nelson

Explore the fundamentals of object detection using Python and the YOLO model. Learn how to recognize objects in images and videos, work with pre-trained datasets, and build your own custom detection model using Google Colab's GPU resources.

Packt | Sep 2020 | 239 min

Start Trial

LevelIntermediate

CategoriesData Science, Advanced Computer Vision and Image Recognition, OpenCV, Python

1Course Introduction and Table of Contents
2Introduction to You Only Look Once (YOLO) Object Detection
3Environment Setup - Installing Anaconda
4Python Basics
5Installing OpenCV Library
6Introduction to Convolutional Neural Networks (CNNs)
7You Only Look Once (YOLO) Pre-Trained Object Detection from Image
8You Only Look Once (YOLO) Pre-Trained Object Detection from an Image – Non-Maximum Suppression (NMS)
9You Only Look Once (YOLO) Pre-Trained Object Detection from a Real-Time Webcam Video
10You Only Look Once (YOLO) Pre-Trained Object Detection from a Pre-Saved Video
11Introduction to the Custom-Trained You Only Look Once (YOLO) Model
12YOLOv4 Custom Training Phase 1 – Preparing Darknet
13You Only Look Once v4 (YOLOv4) Custom Training Phase 2 - Data Collection
14You Only Look Once v4 (YOLOv4) Custom Training Phase 2 - Image Labelling
15You Only Look Once v4 (YOLOv4) Custom Training Phase 2 - Train Test Split
16You Only Look Once v4 (YOLOv4) Custom Training Phase 2 - Data Preparation
17You Only Look Once v4 (YOLOv4) Custom Training Phase 3 – Data Sync
18You Only Look Once v4 (YOLOv4) Custom Training Phase 4 - Compile and Test Darknet
19You Only Look Once v4 (YOLOv4) Custom Training Phase 5 - Chart and Training Progress Analysis
20You Only Look Once v4 (YOLOv4) Custom Training Phase 5 - Finalizing Training Download Weights
21Colab GPU Usage Limit Issue
22OpenCV Upgrade for You Only Look Once v4 (YOLOv4)
23You Only Look Once v4 (YOLOv4) Pre-Trained Object Recognition from an Image and a Video
24You Only Look Once v4 (YOLOv4) Custom Coronavirus Detection from an Image
25You Only Look Once v4 (YOLOv4) Custom Coronavirus Detection from a Video
26Other Sample Real-World Case Studies

What You Will Learn

You will start by setting up Python and essential libraries, then move on to using YOLO with pre-trained data for object detection. Step by step, you will create and label your own dataset, train a custom YOLO model, and test it on real images and videos, all within Google Colab.

Key Features

Train YOLO models to detect objects in images and real-time webcam videos
Prepare and use custom datasets for specialized object recognition tasks
Leverage Google Colab's free GPU to speed up model training and testing

Target Audience

Ideal for beginners, developers, or anyone interested in computer vision who wants hands-on experience with object detection. If you have some basic Python knowledge, you'll quickly pick up the skills needed to build and train your own custom models for real-world applications.

Related courses

Cover image for Computer Vision Theory and Projects in Python for Beginners

Cover image for OpenCV Computer Vision Examples with Python: A Complete Guide for Dummies

Pro

Cover image for Modern Computer Vision with PyTorch

Cover image for Mastering Image Segmentation with PyTorch using Real-World Projects

Pro

Cover image for Computer Vision: Python OCR and Object Detection Quick Starter