diff options
author | Sheri Zhang <sheri.zhang@arm.com> | 2020-03-16 14:07:51 +0000 |
---|---|---|
committer | Sheri Zhang <sheri.zhang@arm.com> | 2020-03-16 16:35:33 +0000 |
commit | 05b243aff343fd6761bbadb2fcb4d2d98b0848c9 (patch) | |
tree | f0a99e11ae4990aa68881e558b0fd86ca8a1978e /arm_compute/core/CPP/kernels | |
parent | a602f03f4c66e5ee2480f1a3fc66847968fc1076 (diff) | |
download | ComputeLibrary-05b243aff343fd6761bbadb2fcb4d2d98b0848c9.tar.gz |
COMPMID-3271: Add support for QASYMM8_SIGNED in CPPTopKVKernel/CPPTopKV
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com>
Change-Id: Ic34616fc3480ca85cc582e4e3db031d631ed5861
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2887
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/CPP/kernels')
-rw-r--r-- | arm_compute/core/CPP/kernels/CPPTopKVKernel.h | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/arm_compute/core/CPP/kernels/CPPTopKVKernel.h b/arm_compute/core/CPP/kernels/CPPTopKVKernel.h index fc62b42ab8..4b9bfdd3c9 100644 --- a/arm_compute/core/CPP/kernels/CPPTopKVKernel.h +++ b/arm_compute/core/CPP/kernels/CPPTopKVKernel.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2019 ARM Limited. + * Copyright (c) 2019-2020 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -53,7 +53,7 @@ public: /** Set the input and output of the kernel. * - * @param[in] predictions A batch_size x classes tensor. Data types supported: F16/S32/F32/QASYMM8 + * @param[in] predictions A batch_size x classes tensor. Data types supported: F16/S32/F32/QASYMM8/QASYMM8_SIGNED * @param[in] targets A batch_size 1D tensor of class ids. Data types supported: S32 * @param[out] output Computed precision at @p k as a bool 1D tensor. Data types supported: U8 * @param[in] k Number of top elements to look at for computing precision. @@ -62,7 +62,7 @@ public: /** Static function to check if given info will lead to a valid configuration of @ref CPPTopKVKernel * - * @param[in] predictions A batch_size x classes tensor info. Data types supported: F16/S32/F32/QASYMM8 + * @param[in] predictions A batch_size x classes tensor info. Data types supported: F16/S32/F32/QASYMM8/QASYMM8_SIGNED * @param[in] targets A batch_size 1D tensor info of class ids. Data types supported: S32 * @param[in] output Computed precision at @p k as a bool 1D tensor info. Data types supported: U8 * @param[in] k Number of top elements to look at for computing precision. |