[elithrar]

I’m not sure why the other post was marked dead, but AutoML models can be exported - you can export them to TFLite format[0] and then run them on edge devices, such as a SparkFun Edge[1] or a Coral SoC / board.

[0]: https://cloud.google.com/vision/automl/docs/export-edge#expo... [1]: https://www.sparkfun.com/categories/tags/tensorflow

[ckvamme]

You can also export your model as a server within a Docker container:

https://cloud.google.com/automl-tables/docs/model-export