Deep Learning for Computer Vision - Lecture 9: Hardware and Software

Lecture 9 gives an overview of the hardware and software systems used in deep learning. We contrast CPUs with graphics processing units (GPUs), and see how the massively parallel architecture of GPUs allows them to accelerate deep learning workloads, and how the rapidly improving hardware performance has been a driving force in deep learning. We also discuss the special-purpose hardware (tensor cores, tensor processing units) that have recently been introduced to further accelerate deep learning. On the software side, we focus on the two most widely used deep learning frameworks: PyTorch and TensorFlow. We see how these two frameworks realize the notion of a computational graph in software, and contrast dynamic vs static computational graphs. Slides: http://myumi.ch/PlkdR _________________________________________________________________________________________________ Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification and object detection. Recent developments in neural network approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into details of neural-network based deep learning methods for computer vision. During this course, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. We will cover learning algorithms, neural network architectures, and practical engineering tricks for training and fine-tuning networks for visual recognition tasks. Course Website: http://myumi.ch/Bo9Ng Instructor: Justin Johnson http://myumi.ch/QA8Pg