[Feature] Extend more examples based on Multi-edge tracking ReID #302
Description
Why is this needed:
Sedna is a general collaborative framework for AI training and inference across cloud and edge, it now supports joint inference, incremental learning, federated learning, lifelong learning. It is not designed for special area, so it can be used in most edge AI scenarios to reduce the cost, improve the performance and protect the privacy.
Currently, Sedna has already provided some examples, you can find them here. But it falls far short of covering most of the edge AI scenarios, such as industrial quality inspection, campus energy consumption management, even for AI applications on satellites.
It is needed to extend more examples based on Sedna collaborative features, so that Sedna can be used more widely.
What would you like to be added/modified:
Extend end-to-end example
| Target | Datasets | Reference Feature |
|---|---|---|
| Multi-edge tracking ReID example | Pedestrian/Vechile/Container | Multi-edge tracking ReID |
the feature
Multi-edge tracking ReIDwill be released before 30th. May, but now you can refer to here.
As every
| review dimension | These could get High Marks |
|---|---|
| datasets | 1. support more dataset format for Sedna Lib. |
| algorithm | 1. using proper algorithms and models. |
| architecture | 1. Clear architecture description 2. Take advantage of cloud and edge, and it can bring benefit through collobrative between cloud and edge |
| feature engneering | 1. Proper feature engineering makes the final result good. |
| test case | 1. Include feature-level test cases 2. Include sample-level test cases |