I’m seeking information about the layer-by-layer details of Metropolis microservices and the advantages of running models through Metropolis. Could someone provide a concise breakdown of the microservices architecture and highlight the benefits of using Metropolis for model execution?
Hi, Thanks for your reply.
I have already gone through this documentation but couldn’t exactly find any details on the layer wise implementation as in which microservices run on CPU, GPU and DLA.
Also, when PeopleNet model is implemented in Deepstream microservice it executes on which accelerator and is there any fallback?
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks