PyTorch is powerful and simple to use. This course will help you leverage the power of PyTorch to perform image processing. Beginning with an introduction to image processing, the course introduces you to basic deep-learning and optimization concepts. Next, you'll learn to use PyTorch's APIs such as the dynamic graph computation tensor, which can be used for image classification. Starting off with basic 2D images, the course gradually takes you through recognizing more complex images, color, shapes, and more.
Using the Python API, you'll move on to classifying and training your model to identify more complex images—for example, recognizing plant species better than humans. Then you'll delve into AlexNet, ResNet, VGG-net, Generative Adversarial Networks(GANs), neural style transfer, and more–—all by taking advantage of PyTorch's Deep Neural Networks.
Taking this course is your one-stop, hands-on guide to applying computer vision to your projects using PyTorch. You'll create and deploy your own models, and gain the necessary intuition to work on real-world projects.
Please note that a understanding of calculus and linear algebra, along with some experience using Python, are assumed for taking this course.
About the Author
Colibri Digital is a technology consultancy company founded in 2015 by James Cross and Ingrid Funie. The company works to help its clients navigate the rapidly changing and complex world of emerging technologies, with deep expertise in areas such as big data, data science, machine learning, and cloud computing. Over the past few years, they have worked with some of the world's largest and most prestigious companies, including a tier 1 investment bank, a leading management consultancy group, and one of the World's most popular soft drinks companies, helping each of them to make better sense of its data and process it in more intelligent ways. The company lives by its motto: Data -> Intelligence -> Action.
Tom Joy is studying for a PhD at the University of Oxford in the field of Semantic SLAM, which is the process of simultaneously localizing a robot in space; producing a map/understanding of the surrounding area whilst also detecting and delineating objects in 3D space. Achieving this requires a high level of competency in computer vision, machine learning, and optimization.
Tom has extensive experience in computer vision and machine learning, having taken several internships and placements over the course of his degree and spent time in industry prior to starting his PhD. He is a big advocate of explaining concepts simply and in a clear and concise manner; he strives to obtain and provide a comprehensive understanding of all relevant methods to the task at hand.