zephyr/modules/tflite-micro/Kconfig
Stephanos Ioannidis cf211aa7af treewide: Update deprecated CONFIG_LIB_CPLUSPLUS usages
This commit updates all deprecated `CONFIG_LIB_CPLUSPLUS` usages to:

* check if the Zephyr minimal C++ library is enabled using
  `CONFIG_MINIMAL_LIBCPP` instead of relying on the
  `CONFIG_LIB_CPLUSPLUS`-based inference.

* select `CONFIG_REQUIRES_FULL_LIBCPP` when there exists a component-
  level C++ standard library dependency. This allows a component to
  declare C++ standard library dependency without designating a
  specific libray implementation.

* select the correct type of C++ standard library implementation to use
  through one of the `CONFIG_LIBCPP_IMPLEMENTATION` choices.

Signed-off-by: Stephanos Ioannidis <stephanos.ioannidis@nordicsemi.no>
2023-01-13 17:42:55 -05:00

34 lines
927 B
Plaintext

# Copyright (c) 2021 Intel Corporation
# Copyright 2022 Arm Limited and/or its affiliates <open-source-office@arm.com>
# SPDX-License-Identifier: Apache-2.0
config ZEPHYR_TFLITE-MICRO_MODULE
bool
config TENSORFLOW_LITE_MICRO
bool "TensorFlow Lite Micro Support"
select REQUIRES_FULL_LIBCPP
help
This option enables the TensorFlow Lite Micro library.
if CPU_CORTEX_M
config TENSORFLOW_LITE_MICRO_CMSIS_NN_KERNELS
bool "TensorFlow Lite Micro with optimized CMSIS-NN kernels"
depends on TENSORFLOW_LITE_MICRO
select CMSIS_NN
select CMSIS_NN_ACTIVATION
select CMSIS_NN_BASICMATH
select CMSIS_NN_CONCATENATION
select CMSIS_NN_CONVOLUTION
select CMSIS_NN_FULLYCONNECTED
select CMSIS_NN_NNSUPPORT
select CMSIS_NN_POOLING
select CMSIS_NN_RESHAPE
select CMSIS_NN_SOFTMAX
select CMSIS_NN_SVD
help
This option adds support for CMSIS-NN optimized kernels when using TensorFlow Lite Micro.
endif # CPU_CORTEX_M