You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 129 Next »

ai (1).pptx Blueprint species:

Use Case Attributes

Description

Informational

Type

New Blueprint for AI on the Edge

 

Blueprint Family

Integrated Edge Cloud (IEC)

 

Use Case

Safety, security, and surveillance

 

Blueprint proposed Name

AI on the edge

 

Initial POD Cost (capex)

Leverage Unicycle POD - less than $150K

 

Scale & Type

up to 7 servers, x86/ Arm server or deep edge class

With nVIDIA Tesla K80 GPUs

 

Applications

1. Small scale IoT data aggregation and machine learning platform

2. Small scale deep learning models training for video data

3. Model training for AcumosApps

 

Power and memory restrictions

Less than 10Kw

K8s 1.12.5 or above- Container Orchestration

OS –CentOS 7.0 or above

 

Infrastructure orchestration

Docker 1.13.1 or above

 

SDN

Calico container networking, or OVS-DPDK

 

DataplaneVPP

Workload Type

Containers

 

Additional Details

There are mainly 4 pieces:

  1. a database to collect raw data streams
  2. tons of containers with various models on training
  3. a database for trained models in binary format, and predicted result in JSON format

 


Attachment: 

Akraino_Blueprint_Integrated_Edge_Cloud_AI.pptx

Committer

Affiliation

 Committer Contact Info

Committer Bio

Committer Picture

Self Nominate for PTL (Y/N)

Gang Chen

Baidu

chengang13@baidu.com




Hechun ZhangBaiduzhanghechun@baidu.com


Dechao KongBaidukongdechao@baidu.com


Arm



PSU




N
Raviraj MahatmeArmraviraj.mahatme@arm.com



Contributor

Affiliation

 Committer Contact Info

Committer Bio

Committer Picture

Self Nominate for PTL (Y/N)



















  • No labels