aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/NEON/kernels/NEIm2ColKernel.h
diff options
context:
space:
mode:
authorAnthony Barbier <anthony.barbier@arm.com>2017-09-04 18:44:23 +0100
committerAnthony Barbier <anthony.barbier@arm.com>2018-09-17 13:03:09 +0100
commit6ff3b19ee6120edf015fad8caab2991faa3070af (patch)
treea7a6dcd16dfd56d79fa1b56a313caeebcc939b68 /arm_compute/core/NEON/kernels/NEIm2ColKernel.h
downloadComputeLibrary-6ff3b19ee6120edf015fad8caab2991faa3070af.tar.gz
COMPMID-344 Updated doxygen
Change-Id: I32f7b84daa560e460b77216add529c8fa8b327ae
Diffstat (limited to 'arm_compute/core/NEON/kernels/NEIm2ColKernel.h')
-rw-r--r--arm_compute/core/NEON/kernels/NEIm2ColKernel.h114
1 files changed, 114 insertions, 0 deletions
diff --git a/arm_compute/core/NEON/kernels/NEIm2ColKernel.h b/arm_compute/core/NEON/kernels/NEIm2ColKernel.h
new file mode 100644
index 0000000000..ebaafb467f
--- /dev/null
+++ b/arm_compute/core/NEON/kernels/NEIm2ColKernel.h
@@ -0,0 +1,114 @@
+/*
+ * Copyright (c) 2017 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_NEIM2COLKERNEL_H__
+#define __ARM_COMPUTE_NEIM2COLKERNEL_H__
+
+#include "arm_compute/core/NEON/INEKernel.h"
+
+namespace arm_compute
+{
+class ITensor;
+
+/** Interface for the im2col reshape kernel.
+ *
+ * Rearranges image blocks into columns. It is used to strip out each convolution block to a single column.
+ * It is used to transform a convolution to a plain matrix multiplication.
+ *
+ * For example taking into account the image below and assuming 3x3 image blocks with stride of 1 we have:
+ *
+ * @f[
+ * \left( \begin{array}{cccc}
+ * a00 & a01 & a02 & a03 \\
+ * a10 & a11 & a12 & a13 \\
+ * a20 & a21 & a22 & a23 \\
+ * a30 & a31 & a32 & a33 \\
+ * \end{array} \right)
+ * \rightarrow
+ * \left( \begin{array}{ccccccccc}
+ * a00 & a01 & a02 & a10 & a11 & a12 & a20 & a21 & a22 \\
+ * a01 & a02 & a03 & a11 & a12 & a13 & a21 & a22 & a23 \\
+ * a10 & a11 & a12 & a20 & a21 & a22 & a30 & a31 & a32 \\
+ * a11 & a12 & a13 & a21 & a22 & a23 & a31 & a32 & a33 \\
+ * \end{array} \right)
+ * @f]
+ */
+class NEIm2ColKernel : public INEKernel
+{
+public:
+ /** Default constructor */
+ NEIm2ColKernel();
+ /** Prevent instances of this class from being copied (As this class contains pointers) */
+ NEIm2ColKernel(const NEIm2ColKernel &) = delete;
+ /** Prevent instances of this class from being copied (As this class contains pointers) */
+ NEIm2ColKernel &operator=(const NEIm2ColKernel &) = delete;
+ /** Allow instances of this class to be moved */
+ NEIm2ColKernel(NEIm2ColKernel &&) = default;
+ /** Allow instances of this class to be moved */
+ NEIm2ColKernel &operator=(NEIm2ColKernel &&) = default;
+ /** Default destructor */
+ ~NEIm2ColKernel() = 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: QS8/F32
+ * @param[out] output The output tensor. Data types supported: Same as @p input
+ * @param[in] convolved_dims The convolved output dimensions.
+ * @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo.
+ * @param[in] has_bias In case biases are provided expands the matrix with 1.
+ */
+ void configure(const ITensor *input, ITensor *output, std::pair<unsigned int, unsigned int> convolved_dims, const PadStrideInfo &conv_info, bool has_bias);
+
+ // Inherited methods overridden:
+ void run(const Window &window) override;
+
+private:
+ /** Template function to run the im2col optimised for the fully connected layer case
+ *
+ * @param[in] window Region on which to execute the kernel. (Must be a valid region of the window returned by window()).
+ */
+ template <typename T>
+ void run_reduced(const Window &window);
+ /** Template function to run the im2col used for the convolution layer case
+ *
+ * @param[in] window Region on which to execute the kernel. (Must be a valid region of the window returned by window()).
+ */
+ template <typename T, bool has_pads>
+ void run_generic(const Window &window);
+ /** Common signature for all the specialised im2col functions
+ *
+ * @param[in] window Region on which to execute the kernel.
+ */
+ using Im2ColFunctionPtr = void (NEIm2ColKernel::*)(const Window &window);
+
+ Im2ColFunctionPtr _func;
+ const ITensor *_input;
+ ITensor *_output;
+ std::pair<unsigned int, unsigned int> _convolved_dims;
+ PadStrideInfo _conv_info;
+ unsigned int _kernel_size;
+ bool _has_bias;
+};
+}
+#endif /*__ARM_COMPUTE_NEIM2COLKERNEL_H__ */