search

Call-for-Code / DroneAid

Aerial scout for first responders. DroneAid uses machine learning to detect calls for help on the ground placed by those in need.
Apache License 2.0
122 stars 59 forks source link

Encapsulate the trained model in a Docker image #2

Open krook opened 4 years ago

krook commented 4 years ago

Is your feature request related to a problem? Please describe. The IBM Model Asset Exchange provides a way to reuse models instead of having to train them manually.

Describe the solution you'd like The trained model materials need to be packaged and shared through MAX.

Describe alternatives you've considered Training the model each time for each platform.

Additional context This could be related to any other Dockerization steps.

krook commented 4 years ago

@vabarbosa Do you know who the right person is to explore this?

vabarbosa commented 4 years ago

i've reached out to @gdequeiroz, @MLnick, and @ptitzler. hopefully they will be able to provide some guidance.

krook commented 4 years ago

Thank you @vabarbosa

krook commented 4 years ago

Looks like this is the starting point for the process: https://github.com/CODAIT/max-central-repo#contributing-to-the-model-asset-exchange

krook commented 4 years ago

I still think this could be some lower hanging fruit than encapsulating the setup code into Docker.

krook commented 3 years ago

Partially done with @upkarlidder's Code Engine contribution in #44