diff options
author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2020-01-06 14:07:44 +0000 |
---|---|---|
committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2020-01-06 17:40:39 +0000 |
commit | 4cd4cdeedd8431556806bb6f3b6ff559b757e792 (patch) | |
tree | 607a0cb5c688c59ba5e85577a38b8a87f5715fb0 /arm_compute/runtime/CL | |
parent | ec0c412ec044b1fbc83b3172f2765823850ed50d (diff) | |
download | ComputeLibrary-4cd4cdeedd8431556806bb6f3b6ff559b757e792.tar.gz |
COMPMID-2757: Add support for QASYMM8_SIGNED in CLDepthwiseConvolutionLayer
Change-Id: I1f292f98bc3a213ba5b26ac88aa78160c809cb87
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2540
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL')
-rw-r--r-- | arm_compute/runtime/CL/functions/CLDepthwiseConvolutionLayer.h | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/arm_compute/runtime/CL/functions/CLDepthwiseConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLDepthwiseConvolutionLayer.h index 7ce7cce064..4668e82bab 100644 --- a/arm_compute/runtime/CL/functions/CLDepthwiseConvolutionLayer.h +++ b/arm_compute/runtime/CL/functions/CLDepthwiseConvolutionLayer.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017-2019 ARM Limited. + * Copyright (c) 2017-2020 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -221,11 +221,11 @@ private: CLDepthwiseConvolutionLayerGeneric &operator=(CLDepthwiseConvolutionLayerGeneric &&) = default; /** Initialize the function's source, destination, weights and convolution information. * - * @param[in, out] input Source tensor. Data type supported: QASYMM8/F32. (Written to only for border filling). + * @param[in, out] input Source tensor. Data type supported: QASYMM8/QASYMM8_SIGNED/F32. (Written to only for border filling). * @param[in] weights Weights tensor. These are 3D tensors with shape [kernel_x, kernel_y, IFM]. - * Data type supported: Same as @p input or QASYMM8/QSYMM8_PER_CHANNEL when @p input is QASYMM8. + * Data type supported: Same as @p input or QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL when @p input is QASYMM8. * @param[in] biases Biases tensor. A 1D tensor with shape [IFM]. Must be nullptr if not needed. - * Data type supported: Same as @p input, S32 when input is QASYMM8. + * Data type supported: Same as @p input, S32 when input is QASYMM8/QASYMM8_SIGNED. * @param[out] output Destination tensor. Data type supported: same as @p input. * @param[in] conv_info Padding and stride information to use for the convolution. * @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1. @@ -237,11 +237,11 @@ private: /** Static function to check if given info will lead to a valid configuration of @ref CLDepthwiseConvolutionLayerGeneric * - * @param[in] input Source tensor info. Data type supported: QASYMM8/F32. + * @param[in] input Source tensor info. Data type supported: QASYMM8/QASYMM8_SIGNED/F32. * @param[in] weights Weights tensor info. These are 3D tensors with shape [kernel_x, kernel_y, IFM]. - * Data type supported: Same as @p input or QASYMM8/QSYMM8_PER_CHANNEL when @p input is QASYMM8. + * Data type supported: Same as @p input or QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL when @p input is QASYMM8. * @param[in] biases Biases tensor info. A 1D tensor with shape [IFM]. Must be nullptr if not needed. - * Data type supported: Same as @p input, S32 when input is QASYMM8. + * Data type supported: Same as @p input, S32 when input is QASYMM8/QASYMM8_SIGNED. * @param[in] output Destination tensor. Data type supported: same as @p input. * @param[in] conv_info Padding and stride information to use for the convolution. * @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1. |