Welcome to my repository where I've compiled all my learnings and studies from the Master's course on Computer Vision at UTP (Universidad Tecnológica de Pereira). This repository serves as a comprehensive guide and reference to the various concepts, methodologies, and implementations covered throughout the course.
Please install python and the IDE of your choice. The next step is to install the enviroment for this project if you are on windows please follow this guide first (If you are on linux ignore this). Now execute the following comand line:
make setupHere, you'll find notes, code snippets, and practical examples illustrating the concepts of ( P^2 ) and ( P^3 ). From the foundational theories to the advanced applications, this section is designed to provide a robust understanding of projective geometry as it pertains to computer vision.
Modern computer vision heavily relies on the power of neural networks. In this section, we explore the core principles of computer vision as realized through the lens of neural networks. Whether you are just starting out or are looking to refine your knowledge, this section provides a mix of theoretical insights and hands-on implementations.
To ensure a holistic learning experience, we've used both TensorFlow and PyTorch – two of the leading deep learning frameworks in the industry. This allows for a comparative study, understanding the strengths, and nuances of each framework in the context of computer vision tasks. You'll find a plethora of examples, best practices, and experiments showcasing the capabilities of both frameworks in this domain.