Deep learning on embedded devices is currently enjoying considerable success in a wide variety of applications – particularly smartphones, where increasingly prevalent AI cameras are able to enhance every captured moment. But the great number of deep learning network architectures proposed every year presents a challenge for developers looking to implement these algorithms efficiently.
During this webinar, you will learn how to:
• Identify a structured approach to performance analysis
• Evaluate methodologies, and explore examples using the Arm Compute Library and Arm NN
• Observe performance analysis in action, and detect and fix performance bottlenecks