This repository provides in-depth lecture materials on computer vision using deep learning. It is systematically structured to guide learners through the entire workflow of a computer vision developer, from fundamental theory to real-world application development.
This course goes beyond simply running pre-existing code. The core objective is to foster a deep understanding by having you implement the internal mechanisms of key deep learning models—such as CNN, ResNet, R-CNN, and YOLO—from the ground up. With hands-on exercises in PyTorch and Keras, you will gain proficiency in translating complex theories into functional code.
Moreover, you will experience the complete development lifecycle: from setting up a professional development environment (including tools like VS Code, Docker, and CUDA) and optimizing model performance through hyperparameter tuning, to ultimately building and deploying a computer vision web service using YOLO and Flask. These materials are designed to provide a solid foundation for your journey to becoming a professional in the field of deep learning and computer vision.
- Aug 2022: Started preparing lecture materials upon request for a practical course on deep learning and computer vision technology for industry professionals.
- Sep 2022: Recorded, reviewed, and supplemented lecture videos based on the prepared materials.
- Oct 2022: Developed comprehensive lecture materials for training developers in deep learning and computer vision applications.
This course provides a comprehensive guide to deep learning for computer vision, covering the following topics:
-
Core Concepts & Code:
- Provides hands-on source files (Python, Jupyter Notebook) for key computer vision models like CNN, R-CNN, ResNet, YOLOv1, YOLOv3, and YOLOv5 using Keras and PyTorch.
- Explains and implements the core mechanisms of deep learning architectures from the ground up.
-
Development Environment Setup:
- Covers how to set up a deep learning development environment using essential tools such as VS Code, Ubuntu, CUDA, Virtual Environments, Docker, and Google Colab.
-
Model Optimization:
- Demonstrates practical hyperparameter tuning techniques to improve model performance.
-
Application Development:
- Guides you through building a simple computer vision web service using YOLO, Flask, and Python.
This repository is part of my ongoing work on AI, LLMs, and Transformer-based architectures. I am open to research collaboration, academic exchange, and joint projects with universities, public institutions, company and research labs.
For collaboration inquiries, please feel free to reach out: 📧 [[email protected]] | 🌐 [LinkedIn or Personal Website]
This repository is licensed under the MIT License. You are free to use, modify, and distribute the code for personal or commercial projects.
Ph.D, Taewook Kang ([email protected])