...
This document should function as a glossary of APIs with its functionality, interfaces, inputs, and expected outcomes as the following example:
API1:
...
Kubernetes native APIs
API2: KubeEdge APIs (Kubernetes API extensions)
API3: ML inference framework APIs
API4: ML management APIs
This is the link of ML management API specification.
API5: ML inference offloading APIs
ML Offloading APIs provides provide synchronization of ML inference service with UE side. It serves application developers and enable enables machine learning apps to offload computation intensive jobs from UE device to close by edge nodes. ML offloading services satisfy the requirement the ML computing resource requirement, meanwhile its responses faster than cloud ML services.
The ML offloading APIs offer ML inference services (support different ML tensorflow serving frameworks) from KubeEdge sites through ML APIs, which contains a set of commonly used model pool. Pre-trained Machine Learning models in the pool have detail features published and performance has been tested. It has different categories can be deployed to the pool from cloud environment. In the future, the pool can open different categories of models to cover a wide variety of use cases in ML domain. The ML API if an app developers don't have a in-house trained model, they can also chose from the existing models, and it enables traditional app developer developers to leverage the fast response time of edge computing, and lower entry barriers of machine learning knowledge. Just use those ML offloading API in app, and stable new ML feature can be delivered to user devices from the nearest edge node. quickly adopt the KubeEdge ML offloading solution without concerns of model management by themselves.
The KubeEdge ML offloading service has a Facial recognition demo api. Developer’s application can input The demo mobile application passes a face image to it via https request, and the edge ML offloading service identify identifies the expression and return corresponding facial expression code. It is a sample component of KubeEdge to address users' data security or latency concerns. With high scalability of model acceleration on demand. Mobile app developers don't need to worry about the device resource limitation and , or latency issues to from the public cloud.
The ML offloading APIs is a set of intelligence services on edge cloud which offers various of AI services, and it can be triggered by mobile applications. For example, it can be used to determine if an image contains faces or translate text into different languages. Those APIs are available only if developers deploy it through KubeEdge. The ML offloading APIs can support different ML categories, including Vision, ASR, dialog engine and more in the future, ans serves as REST web service.
Here is an example of Facial expression API
...
Request URL: https://{endpoint}/ficialExpressionfacialExpression
Parameters
Image type: PNG image
...