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/CLDepthwiseIm2ColKernel.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/CLDepthwiseIm2ColKernel.h')
-rw-r--r-- | arm_compute/core/CL/kernels/CLDepthwiseIm2ColKernel.h | 90 |
1 files changed, 0 insertions, 90 deletions
diff --git a/arm_compute/core/CL/kernels/CLDepthwiseIm2ColKernel.h b/arm_compute/core/CL/kernels/CLDepthwiseIm2ColKernel.h deleted file mode 100644 index 15798471a8..0000000000 --- a/arm_compute/core/CL/kernels/CLDepthwiseIm2ColKernel.h +++ /dev/null @@ -1,90 +0,0 @@ -/* - * Copyright (c) 2017-2019 ARM Limited. - * - * SPDX-License-Identifier: MIT - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in all - * copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ -#ifndef __ARM_COMPUTE_CLDEPTHWISEIM2COLKERNEL_H__ -#define __ARM_COMPUTE_CLDEPTHWISEIM2COLKERNEL_H__ - -#include "arm_compute/core/CL/ICLKernel.h" -#include "arm_compute/core/Size2D.h" - -namespace arm_compute -{ -class ICLTensor; - -/** Interface for the depthwise im2col reshape kernel. - * This kernel reshape the input low 3 dimensions to a new 3D shape where the output's first dimension is - * the linear patch size (FILTER_WIDTH * FILTER_HEIGHT) and second dimension is number of patches per image and third dimension unchanged . - **/ -class CLDepthwiseIm2ColKernel : public ICLKernel -{ -public: - /** Default constructor */ - CLDepthwiseIm2ColKernel(); - /** Prevent instances of this class from being copied (As this class contains pointers) */ - CLDepthwiseIm2ColKernel(const CLDepthwiseIm2ColKernel &) = delete; - /** Prevent instances of this class from being copied (As this class contains pointers) */ - CLDepthwiseIm2ColKernel &operator=(const CLDepthwiseIm2ColKernel &) = delete; - /** Allow instances of this class to be moved */ - CLDepthwiseIm2ColKernel(CLDepthwiseIm2ColKernel &&) = default; - /** Allow instances of this class to be moved */ - CLDepthwiseIm2ColKernel &operator=(CLDepthwiseIm2ColKernel &&) = default; - /** Set the input and output of the kernel. - * - * @param[in] input The input tensor to convert. 3 lower dimensions represent a single input [width, height, IFM], - * while every optional dimension from 4 and above represent a batch of inputs. Data types supported: QASYMM8/F16/F32 - * @param[out] output The output tensor. First 3 lower dimensions represent a transform of each 3D input, - * while every dimension above 3 represents a batch. Data types supported: Same as @p input - * @param[in] kernel_dims The kernel dimensions (width and height). - * @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo. - * @param[in] has_bias Boolean that specifies if the depthwise convolution has bias. - * @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1. - * @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1). - */ - void configure(const ICLTensor *input, ICLTensor *output, const Size2D &kernel_dims, const PadStrideInfo &conv_info, bool has_bias = false, 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 CLDepthwiseIm2ColKernel - * - * @param[in] input The input tensor info to convert. 3 lower dimensions represent a single input [width, height, IFM], - * while every optional dimension from 4 and above represent a batch of inputs. Data types supported: QASYMM8/F32 - * @param[in] output The output tensor info. First 3 lower dimensions represent a transform of each 3D input, - * while every dimension above 3 represents a batch. Data types supported: Same as @p input - * @param[in] kernel_dims The kernel dimensions (width and height). - * @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo. - * @param[in] has_bias Boolean that specifies if the depthwise convolution has bias. - * @param[in] depth_multiplier Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1. - * @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1). - * - * @return a status - */ - static Status validate(const ITensorInfo *input, const ITensorInfo *output, const Size2D &kernel_dims, const PadStrideInfo &conv_info, bool has_bias, unsigned int depth_multiplier, - const Size2D &dilation = Size2D(1U, 1U)); - - // Inherited methods overridden: - void run(const Window &window, cl::CommandQueue &queue) override; - -private: - const ICLTensor *_input; - ICLTensor *_output; -}; -} // arm_compute -#endif /*__ARM_COMPUTE_CLDEPTHWISEIM2COLKERNEL_H__ */ |