Approach

[Lkruitwagen]

• ML test-bench style
• streaming data? or fixed corpus? (transfer costs excessive on Azure - probably want a fixed corpus)
• two corpuses: [DL S2 DLSR, S1] and [L2A, EES1]
• pytorch
• pytorch parallel generator: https://stanford.edu/~shervine/blog/pytorch-how-to-generate-data-parallel
• run self-supervised experiments, with supervised finishing on a joint header
• "cross validate on the same distribution as test"

[Lkruitwagen]

https://wiki.openstreetmap.org/wiki/Setting_up_a_local_copy_of_the_OpenStreetMap_database,_kept_up_to_date_with_minutely_diffs

[Lkruitwagen]

https://switch2osm.org/serving-tiles/using-a-docker-container/

https://hub.docker.com/r/overv/openstreetmap-tile-server/

[Lkruitwagen]

https://ircama.github.io/osm-carto-tutorials/tile-server-ubuntu/

https://switch2osm.org/serving-tiles/manually-building-a-tile-server-20-04-lts/

[Lkruitwagen]

https://medium.com/@rajitha.mail48/create-a-docker-image-of-an-offline-open-street-map-server-9fdedd433cc8