tensorflow lite converter: porting to R status

There is a library in tensorflow ecosystem called "tf lite converter" (check the first diagram in https://www.tensorflow.org/lite/convert/index) , which converts a keras or tensorflow saved model in a format suitable for IoT (Internet of Things) devices (32 bit, 8 bit, etc). Then you can move your converted model to your embedded system and run the inference there using the tensorflow inference C/c++ API.

I think it would be great to see a porting of "tensorflow converter" python library to R. Nowadays tensorflow lite is the only open source "mature" alternative for tinyML I found, which has more support, docs, examples, etc.

I would like to know if there are ideas to port tensorflow lite / tensorflow converter library to R, maybe from the current tensorflow R package team.

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.