From 7d0adc602b3a3ff66184632fd388b25384a9bc99 Mon Sep 17 00:00:00 2001 From: Georgios Pinitas Date: Fri, 4 Sep 2020 15:25:24 +0100 Subject: COMPMID-3151: Remove NEDepthwiseConvolutionLayer3x3Kernel Prefer NEDepthwiseConvolutionLayerNativeKernel as it has a native format of NHWC avoiding extra transformation to the NCHW domain. Signed-off-by: Georgios Pinitas Change-Id: If5d8de11691b8ef7f4c3816941f87417d0c8646b Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3930 Tested-by: Arm Jenkins Reviewed-by: Michele Di Giorgio Comments-Addressed: Arm Jenkins --- arm_compute/core/NEON/NEKernels.h | 1 - .../kernels/NEDepthwiseConvolutionLayer3x3Kernel.h | 96 ---------------------- 2 files changed, 97 deletions(-) delete mode 100644 arm_compute/core/NEON/kernels/NEDepthwiseConvolutionLayer3x3Kernel.h (limited to 'arm_compute/core') diff --git a/arm_compute/core/NEON/NEKernels.h b/arm_compute/core/NEON/NEKernels.h index f5d3aec27a..4d3e6633c9 100644 --- a/arm_compute/core/NEON/NEKernels.h +++ b/arm_compute/core/NEON/NEKernels.h @@ -54,7 +54,6 @@ #include "arm_compute/core/NEON/kernels/NEDepthConcatenateLayerKernel.h" #include "arm_compute/core/NEON/kernels/NEDepthConvertLayerKernel.h" #include "arm_compute/core/NEON/kernels/NEDepthToSpaceLayerKernel.h" -#include "arm_compute/core/NEON/kernels/NEDepthwiseConvolutionLayer3x3Kernel.h" #include "arm_compute/core/NEON/kernels/NEDepthwiseConvolutionLayerNativeKernel.h" #include "arm_compute/core/NEON/kernels/NEDequantizationLayerKernel.h" #include "arm_compute/core/NEON/kernels/NEDerivativeKernel.h" diff --git a/arm_compute/core/NEON/kernels/NEDepthwiseConvolutionLayer3x3Kernel.h b/arm_compute/core/NEON/kernels/NEDepthwiseConvolutionLayer3x3Kernel.h deleted file mode 100644 index 6712e9105a..0000000000 --- a/arm_compute/core/NEON/kernels/NEDepthwiseConvolutionLayer3x3Kernel.h +++ /dev/null @@ -1,96 +0,0 @@ -/* - * Copyright (c) 2017-2020 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_NEDEPTHWISECONVOLUTIONKERNEL3x3_H -#define ARM_COMPUTE_NEDEPTHWISECONVOLUTIONKERNEL3x3_H - -#include "arm_compute/core/NEON/INEKernel.h" - -namespace arm_compute -{ -// Forward declarations -class ITensor; - -/** Interface for the kernel to run a 3x3 depthwise convolution on a tensor. */ -class NEDepthwiseConvolutionLayer3x3Kernel : public INEKernel -{ -public: - const char *name() const override - { - return "NEDepthwiseConvolutionLayer3x3Kernel"; - } - /** Default constructor */ - NEDepthwiseConvolutionLayer3x3Kernel(); - /** Prevent instances of this class from being copied (As this class contains pointers) */ - NEDepthwiseConvolutionLayer3x3Kernel(const NEDepthwiseConvolutionLayer3x3Kernel &) = delete; - /** Prevent instances of this class from being copied (As this class contains pointers) */ - NEDepthwiseConvolutionLayer3x3Kernel &operator=(const NEDepthwiseConvolutionLayer3x3Kernel &) = delete; - /** Default Move Constructor. */ - NEDepthwiseConvolutionLayer3x3Kernel(NEDepthwiseConvolutionLayer3x3Kernel &&) = default; - /** Default move assignment operator */ - NEDepthwiseConvolutionLayer3x3Kernel &operator=(NEDepthwiseConvolutionLayer3x3Kernel &&) = default; - /** Initialize the function's source, destination, conv and border_size. - * - * @note Supported data layouts: NCHW and NHWC - * - * @param[in] input Source tensor. DataType supported: QASYMM8/QASYMM8_SIGNED/F16/F32. - * @param[in] weights Weights tensor. This is a 3D tensor with dimensions [3, 3, IFM] for NCHW or [IFM, 3, 3] if NHWC data layout. Data type supported: Same as @p input. - * @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. - * @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1). - * - */ - void configure(const ITensor *input, const ITensor *weights, ITensor *output, 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 NEDepthwiseConvolutionLayer3x3Kernel - * - * @note Supported data layouts: NCHW and NHWC - * - * @param[in] input Source tensor info. DataType supported: QASYMM8/QASYMM8_SIGNED/F16/F32. - * @param[in] weights Weights tensor info. This is a 3D tensor with dimensions [3, 3, IFM] for NCHW or [IFM, 3, 3] if NHWC data layout. Data type supported: Same as @p input. - * @param[in] output Destination tensor info. 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. - * @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 *weights, const ITensorInfo *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier = 1, - const Size2D &dilation = Size2D(1U, 1U)); - - // Inherited methods overridden: - void run(const Window &window, const ThreadInfo &info) override; - BorderSize border_size() const override; - -private: - BorderSize _border_size; - const ITensor *_input; - ITensor *_output; - const ITensor *_weights; - PadStrideInfo _conv_info; - unsigned int _num_elems_written_per_iteration; - unsigned int _depth_multiplier; - Size2D _dilation; -}; -} // namespace arm_compute -#endif /* ARM_COMPUTE_NEDEPTHWISECONVOLUTIONKERNEL3x3_H */ -- cgit v1.2.1