...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
The AI Edge Blueprint
Project Technical Lead: To Be Elected
Blueprint species:
Use Case Attributes | Description | Informational |
Type | The AI Edge |
|
Blueprint Family | New |
|
Use Case | Safety, security, and surveillance |
|
Blueprint proposed Name | The AI Edge |
|
Initial POD Cost (capex) | Leverage Unicycle POD - less than $150K |
|
Scale & Type | up to 4 servers, x86/ Arm server or deep edge class With nVIDIA Telsa P4/T4 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 |
|
| Dataplane | VPP | |
Workload Type | Containers |
|
Additional Details | Acumos and EdgeX interfaces will be connected in this case |
|
Attachment:
| View file | ||||
|---|---|---|---|---|
|
...