Authors:
Unai Elordi
1
;
2
;
Luis Unzueta
2
;
Jon Goenetxea
2
;
Estíbaliz Loyo
2
;
Ignacio Arganda-Carreras
1
;
3
;
4
and
Oihana Otaegui
2
Affiliations:
1
Basque Country University (UPV/EHU), San Sebastian, Spain
;
2
Vicomtech, Basque Research and Technology Alliance (BRTA), San Sebastian, Spain
;
3
Donostia International Physics Center (DIPC), San Sebastian, Spain
;
4
Ikerbasque, Basque Foundation for Science, Bilbao, Spain
Keyword(s):
Video Surveillance, Serverless Computing, Deep Neural Networks Optimizations.
Abstract:
We present an approach to optimally deploy Deep Neural Networks (DNNs) in serverless cloud architectures. A serverless architecture allows running code in response to events, automatically managing the required computing resources. However, these resources have limitations in terms of execution environment (CPU only), cold starts, space, scalability, etc. These limitations hinder the deployment of DNNs, especially considering that fees are charged according to the employed resources and the computation time. Our deployment approach is comprised of multiple decoupled software layers that allow effectively managing multiple processes, such as business logic, data access, and computer vision algorithms that leverage DNN optimization techniques. Experimental results in AWS Lambda reveal its potential to build cost-effective on-demand serverless video surveillance systems.