If you scroll back, you can find that it took nearly half a second to generate the results on the CPU. How good is the speed and should we expect an increase?
According to the MXNet GitHub page, you should get approximately 150 images/second when running on a single K80 GPU. There is not much you can do when running it on a CPU except choose a smaller network, such as MobileNet.
Source: https://github.com/apache/incubator-mxnet/tree/master/example/image-classification
Get Hands-On Computer Vision with Julia now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
Get Mark Richards’s Software Architecture Patterns ebook to better understand how to design components—and how they should interact.
Dive in for free with a 10-day trial of the O’Reilly learning platform—then explore all the other resources our members count on to build skills and solve problems every day.
Start your free trial Become a member now