Compile with -ffp-mode=full for armclang

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

1.85k stars 805 forks source link

Compile with -ffp-mode=full for armclang #2517

Closed AdrianLundell closed 6 months ago

AdrianLundell commented 6 months ago

This is needed due to multiple uses of NaN and Infinity which is not supported with the default -ffp-mode=std.

BUG=#2518