In the “Introduction to NVIDIA DALI: GPU-Accelerated Data Preprocessing“ session you learned DALI basics. In this session, you'll gain practical knowledge on how to use it effectively to accelerate a real-life deep-learning application. We'll do a use case study for a particular framework and a particular model. We'll present intuitive techniques to evaluate the presence of the CPU-bottleneck in a training pipeline, and how to evaluate the potential performance improvement of incorporating GPU-accelerated preprocessing. We'll walk you through practical aspects of developing a DALI pipeline and show how to incorporate it into the training setup. Finally, you'll learn how to deploy a DALI pipeline to a Triton Inference Server.