Add int16 support to MINIMUM and MAXIMUM

tensorflow / tflite-micro

Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).

Apache License 2.0

1.9k stars 818 forks source link

Add int16 support to MINIMUM and MAXIMUM #2679

Closed andresovela closed 1 month ago

andresovela commented 1 month ago

This is needed for running this ops when using int16x8 quantization for audio models

ctwillson commented 1 month ago

Hi Andresovela:

Does TFLM support mfcc ops? This is also needed for audio models

andresovela commented 1 month ago

Sorry, I don't know the answer to that