Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature] Extend more examples based on Multi-edge tracking ReID #302

Open
jaypume opened this issue Apr 11, 2022 · 0 comments · May be fixed by #344
Open

[Feature] Extend more examples based on Multi-edge tracking ReID #302

jaypume opened this issue Apr 11, 2022 · 0 comments · May be fixed by #344
Labels
kind/feature Categorizes issue or PR as related to a new feature.

Comments

@jaypume
Copy link
Member

jaypume commented Apr 11, 2022

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 ReID will 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
@jaypume jaypume added the kind/feature Categorizes issue or PR as related to a new feature. label Apr 11, 2022
@jaypume jaypume changed the title [Feature] Extend more examples based on Multi-edge Joint Inference [Feature] Extend more examples based on Multi-edge tracking ReID May 10, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
kind/feature Categorizes issue or PR as related to a new feature.
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant