Google's MobileNet
Google's MobileNet was launched in 2017. It is a set of mobile-first computer vision models based on TensorFlow, very carefully optimized to run efficiently within a restrictive mobile environment. It acts as a bridge between accuracy in complex neural network structures and performance constraints on mobile runtimes. Since the models have the capability to run locally on the device itself, MobileNet has the advantages of security, privacy, and flexible accessibility. The two most important goals of MobileNet are reduced size and minimal complexity when dealing with computer vision models. The first version of MobileNet offered low-latency models capable of working smoothly with restrictive resources. They can be used for ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access