Closed psyhtest closed 5 years ago
As Arm prefer using the TFLite frontend to ArmNN, we should support it as a matter of priority.
This is the manual protocol users are expected to follow:
https://developer.arm.com/technologies/machine-learning-on-arm/developer-material/how-to-guides/configuring-the-arm-nn-sdk-build-environment-for-tensorflow-lite
We can now configure ArmNN to support TFlite frontend. See the main README ( https://github.com/dividiti/ck-armnn/ ) for details.
As Arm prefer using the TFLite frontend to ArmNN, we should support it as a matter of priority.