diff options
author | Giorgio Arena <giorgio.arena@arm.com> | 2019-10-15 11:09:33 +0100 |
---|---|---|
committer | Giorgio Arena <giorgio.arena@arm.com> | 2019-10-21 10:14:20 +0000 |
commit | d93e263e70e3101422402c95946e520fef34c4c7 (patch) | |
tree | f79d3b325ed6881fb9252cb7ee0b7573739e00be /src/core/NEON/kernels/NEPermuteKernel.cpp | |
parent | ab5b1a279284bed350d3bb75f3d9d3aec6edca0e (diff) | |
download | ComputeLibrary-d93e263e70e3101422402c95946e520fef34c4c7.tar.gz |
COMPMID-2708 NEDepthwiseConvolution Generic: support for QUANT8_PER_CHANNEL_SYMM
COMPMID-2470 Implement a new and generic depthwise convolution for NEON QASYMM8 NHWC
COMPMID-2477 Enable FP16 data type for the new generic convolution on NEON for NHWC
COMPMID-2625 Remove old implementation files for the generic NEDepthwiseConvolution
Change-Id: I8f6deda4fc69dd7e472fba3228b1ed5dad172f3e
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2094
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/NEPermuteKernel.cpp')
-rw-r--r-- | src/core/NEON/kernels/NEPermuteKernel.cpp | 6 |
1 files changed, 0 insertions, 6 deletions
diff --git a/src/core/NEON/kernels/NEPermuteKernel.cpp b/src/core/NEON/kernels/NEPermuteKernel.cpp index 1df94aef06..897b764b45 100644 --- a/src/core/NEON/kernels/NEPermuteKernel.cpp +++ b/src/core/NEON/kernels/NEPermuteKernel.cpp @@ -91,12 +91,6 @@ inline bool is_permutation_supported(const PermutationVector &v) Status validate_arguments(const ITensorInfo *input, const ITensorInfo *output, const PermutationVector &perm) { - //Note: ARM_COMPUTE_RETURN_ERROR_ON_CPU_F16_UNSUPPORTED(input) is not needed here as this kernel doesn't use NEON FP16 instructions. - ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(input, 1, DataType::U8, DataType::S8, DataType::QASYMM8, - DataType::U16, DataType::S16, - DataType::U32, DataType::S32, - DataType::F16, DataType::F32); - ARM_COMPUTE_RETURN_ERROR_ON_MSG(!is_permutation_supported(perm), "PermutationVector not supported."); const TensorShape output_shape = misc::shape_calculator::compute_permutation_output_shape(*input, perm); |