...
Use Case Attributes | Description | Informational |
Type | New |
|
Blueprint Family | Integrated Edge Cloud (IEC) |
|
Use Case | AI Ecosystem |
|
Blueprint proposed Name | IEC Type 4: AR/VR oriented Internet Edge Stack for Integrated Edge Cloud (IEC) Blueprint Family |
|
Initial POD Cost (capex) | NVIDIA Tesla K80 GPUs N/A |
|
Scale & Type |
| |
Applications | Video Processing for AutoDriving (especially training deep learning modelsAugmented reality and virtual reality for gaming, remote conferencing and interactive immersive films (especially SLAM and ray tracing) |
|
Power and memory restrictions |
| |
Infrastructure orchestration | Need Geolocation correlation with deep learning model (the trained ones in binary format) |
|
SDN | Calico and K8s, and Containers serving as client/server (a database to collect raw videos/video streams) and server/client (a database for trained models in binary format) |
|
Workload Type | Tensoflow, Keras containers |
|
Additional Details | There are mainly 4 pieces:
|
|
...