st0nedB / rooms

With "Rooms" mobile devices can perform indoor self-localization using an app and low-cost BLE beacons.
MIT License
64 stars 7 forks source link

cloud web Service to train data #8

Open jaburges opened 3 years ago

jaburges commented 3 years ago

Is your feature request related to a problem? Please describe. everyone has to spin up a pipenv to train their data (when its essentially the same process) Add Json files, crunch model, spit out result - import to phone.

Describe the solution you'd like could we spin up a cloud service where the user uploads their models and it provides the results back? I have a dev Azure subscription I could leverage? not sure how to make a web front end for it though?

Describe alternatives you've considered not sure if its of value, but thought i'd suggest it

st0nedB commented 3 years ago

Sounds like an interesting idea, but not a priority at the moment. It would also be nice to store models under some cryptic URL, so users can download the same model on multiple devices. I have no experience with Azure, so I don't know how time intensive it is to spin something up there. Have also toyed with the idea to provide the service myself, by hosting it on a Pi or some other device. But I don't have free hardware available at the moment. The required processing power should be fairly low, as these models are not very demanding to train.

st0nedB commented 3 years ago

After some brief research, it seems that Flask might be a good choice to do this.