EdgeWare
- 0 Collaborators
Explore how to optimize the deployment when multiple DNN models are inference in a distributed scenario according to the computing power requirements of the models, hardware performance, and communication costs. ...learn more
Project status: Under Development
oneAPI, Artificial Intelligence
Intel Technologies
DevCloud,
oneAPI,
Intel Python,
Intel CPU,
OpenVINO
Overview / Usage
Focus on scheduling multiple collaborative DNNs on a group of heterogeneous edge devices with the goal of reducing overall latency
Methodology / Approach
Deploying DNN models on different edge devices may impact the inference speed of each model and therefore increase the overall inference time when these models are collaboratively working to finish an intelligent service.