The Embedded Vision Summit is the event for innovators who want to incorporate visual intelligence into products. We encourage you to attend to be able to;
- Find new ways to create innovative products using visual intelligence.
- Gain new insights and know-how about computer vision enabling technologies, applications and markets.
- Learn proven techniques for practical computer vision and how these enable vision-based products.
- Meet leading technologists and industry luminaries.
We are pleased to offer you a special 15% discount on your Summit Two-Day Package registration. So register now, using discount code Imgtec16. We look forward to seeing you in Santa Clara, California in May.
Be sure to visit our Showcase G5 in the Technology Showcase for demos of our latest vision technologies.
Don’t miss our session on Tuesday, May 3, 12.30-1pm.
Efficient Convolutional Neural Network Inference on Mobile GPUs
GPUs have become established as a key tool for training of deep learning algorithms. Deploying those algorithms on end devices is a key enabler to their commercial success and mobile GPUs are proving to be an efficient target processor that is readily available in end devices today. This talk will look at how to approach the task of deploying convolutional neural networks (CNNs) on mobile GPUs today. We’ll explore the key primitives for CNN inference and what strategies there are for implementation. We’ll work through alternative options, trade-offs and provide reference performance analysis on mobile GPUs, using the PowerVR architecture as a case study.
Speaker: Paul Brasnett, Principal Research Engineer, Imagination Technologies
If you would like to arrange a meeting, please email email@example.com