diff options
| author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2019-10-08 09:36:26 +0100 |
|---|---|---|
| committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2019-10-15 10:27:18 +0000 |
| commit | a046e164b96a8441b2fa14ef578f7db46a0e97da (patch) | |
| tree | 9fa2b7e003342b608acd3ed627f47f9d027ef72c /arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h | |
| parent | 76c996f3b240eb1f60a566e5b0a5e61fe363685a (diff) | |
| download | ComputeLibrary-a046e164b96a8441b2fa14ef578f7db46a0e97da.tar.gz | |
COMPMID-2600: Implement a new and generic depthwise convolution for CL QASYMM8 NHWC
The NCHW case is supported at function level by permuting the
inputs/outputs to NHWC.
This patch also removes CLDirectConvolutionLayerOutputStageKernel which
is deprecated and some kernels which were only used in the generic case
of depthwise convolution.
Change-Id: I91e0f02d0a2f4a4a352e08c248e648944137fe68
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2056
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Diffstat (limited to 'arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h')
| -rw-r--r-- | arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h index f8c841ab6a..31ec871123 100644 --- a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h +++ b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h @@ -49,7 +49,7 @@ public: CLDepthwiseConvolutionLayerNativeKernel &operator=(CLDepthwiseConvolutionLayerNativeKernel &&) = default; /** Initialize the function's source, destination and parameters * - * @param[in] input Source tensor. Data type supported: FP32/FP16. Data layout supported: NHWC + * @param[in] input Source tensor. Data type supported: QASYMM8/FP32/FP16. Data layout supported: NHWC * @param[in] weights Weights tensor. A 3D tensor with dimensions [IFM, N, M]. Data type supported: Same as @p input. * @param[in] biases Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed. * Data type supported: Same as @p input. @@ -64,7 +64,7 @@ public: const PadStrideInfo &conv_info, unsigned int depth_multiplier = 1, const Size2D &dilation = Size2D(1U, 1U)); /** Static function to check if given info will lead to a valid configuration of @ref CLDepthwiseConvolutionLayerNativeKernel * - * @param[in] input Source tensor info. Data type supported: FP32/FP16. Data layout supported: NHWC + * @param[in] input Source tensor info. Data type supported: QASYMM8/FP32/FP16. Data layout supported: NHWC * @param[in] weights Weights tensor info. A 3D tensor with dimensions [IFM, N, M]. Data type supported: Same as @p input. * @param[in] biases Biases tensor info. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed. * Data type supported: Same as @p input. |