python - How to transfer pre trained machine learning model to App Engine -


i have few machine learning models have trained (size in 300mb - 4 gb). want query them using rest api. build apis in flask require these models in memory. google app engine suitable it? or should use compute engine instead?

it's unsuited appengine because of reasons like:

  1. appengine not have instances ram (unless use flexible same gce option).

  2. even if did, instance can go away requires reload data memory (thou on memcached)

  3. time restrictions on frontend instances make unlikely can time load data memory, less being able analyze data. backend type of instance it, harder doing regular vm.

  4. good luck loading libraries need, none should write file storage, temp file.

thus compute engine correct place.


Comments

Popular posts from this blog

PySide and Qt Properties: Connecting signals from Python to QML -

c# - DevExpress.Wpf.Grid.InfiniteGridSizeException was unhandled -

scala - 'wrong top statement declaration' when using slick in IntelliJ -