| <!-- HTML header for doxygen 1.8.15--> |
| <!-- Remember to use version doxygen 1.8.15 +--> |
| <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> |
| <html xmlns="http://www.w3.org/1999/xhtml"> |
| <head> |
| <meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/> |
| <meta http-equiv="X-UA-Compatible" content="IE=9"/> |
| <meta name="generator" content="Doxygen 1.8.15"/> |
| <meta name="robots" content="NOINDEX, NOFOLLOW" /> <!-- Prevent indexing by search engines --> |
| <title>Compute Library: arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h Source File</title> |
| <link href="tabs.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="jquery.js"></script> |
| <script type="text/javascript" src="dynsections.js"></script> |
| <link href="navtree.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="resize.js"></script> |
| <script type="text/javascript" src="navtreedata.js"></script> |
| <script type="text/javascript" src="navtree.js"></script> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ |
| $(document).ready(initResizable); |
| /* @license-end */</script> |
| <link href="search/search.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="search/searchdata.js"></script> |
| <script type="text/javascript" src="search/search.js"></script> |
| <script type="text/x-mathjax-config"> |
| MathJax.Hub.Config({ |
| extensions: ["tex2jax.js"], |
| jax: ["input/TeX","output/HTML-CSS"], |
| }); |
| </script><script type="text/javascript" async="async" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script> |
| <link href="doxygen.css" rel="stylesheet" type="text/css" /> |
| <link href="stylesheet.css" rel="stylesheet" type="text/css"/> |
| </head> |
| <body> |
| <div id="top"><!-- do not remove this div, it is closed by doxygen! --> |
| <div id="titlearea"> |
| <table cellspacing="0" cellpadding="0"> |
| <tbody> |
| <tr style="height: 56px;"> |
| <img alt="Compute Library" src="https://raw.githubusercontent.com/ARM-software/ComputeLibrary/gh-pages/ACL_logo.png" style="max-width: 100%;margin-top: 15px;margin-left: 10px"/> |
| <td style="padding-left: 0.5em;"> |
| <div id="projectname"> |
|  <span id="projectnumber">20.02.1</span> |
| </div> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <!-- end header part --> |
| <!-- Generated by Doxygen 1.8.15 --> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ |
| var searchBox = new SearchBox("searchBox", "search",false,'Search'); |
| /* @license-end */ |
| </script> |
| <script type="text/javascript" src="menudata.js"></script> |
| <script type="text/javascript" src="menu.js"></script> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ |
| $(function() { |
| initMenu('',true,false,'search.php','Search'); |
| $(document).ready(function() { init_search(); }); |
| }); |
| /* @license-end */</script> |
| <div id="main-nav"></div> |
| </div><!-- top --> |
| <div id="side-nav" class="ui-resizable side-nav-resizable"> |
| <div id="nav-tree"> |
| <div id="nav-tree-contents"> |
| <div id="nav-sync" class="sync"></div> |
| </div> |
| </div> |
| <div id="splitbar" style="-moz-user-select:none;" |
| class="ui-resizable-handle"> |
| </div> |
| </div> |
| <script type="text/javascript"> |
| /* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ |
| $(document).ready(function(){initNavTree('_c_l_depthwise_convolution_layer_native_kernel_8h_source.xhtml','');}); |
| /* @license-end */ |
| </script> |
| <div id="doc-content"> |
| <!-- window showing the filter options --> |
| <div id="MSearchSelectWindow" |
| onmouseover="return searchBox.OnSearchSelectShow()" |
| onmouseout="return searchBox.OnSearchSelectHide()" |
| onkeydown="return searchBox.OnSearchSelectKey(event)"> |
| </div> |
| |
| <!-- iframe showing the search results (closed by default) --> |
| <div id="MSearchResultsWindow"> |
| <iframe src="javascript:void(0)" frameborder="0" |
| name="MSearchResults" id="MSearchResults"> |
| </iframe> |
| </div> |
| |
| <div class="header"> |
| <div class="headertitle"> |
| <div class="title">CLDepthwiseConvolutionLayerNativeKernel.h</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| <a href="_c_l_depthwise_convolution_layer_native_kernel_8h.xhtml">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Copyright (c) 2019-2020 ARM Limited.</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> *</span></div><div class="line"><a name="l00004"></a><span class="lineno"> 4</span> <span class="comment"> * SPDX-License-Identifier: MIT</span></div><div class="line"><a name="l00005"></a><span class="lineno"> 5</span> <span class="comment"> *</span></div><div class="line"><a name="l00006"></a><span class="lineno"> 6</span> <span class="comment"> * Permission is hereby granted, free of charge, to any person obtaining a copy</span></div><div class="line"><a name="l00007"></a><span class="lineno"> 7</span> <span class="comment"> * of this software and associated documentation files (the "Software"), to</span></div><div class="line"><a name="l00008"></a><span class="lineno"> 8</span> <span class="comment"> * deal in the Software without restriction, including without limitation the</span></div><div class="line"><a name="l00009"></a><span class="lineno"> 9</span> <span class="comment"> * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or</span></div><div class="line"><a name="l00010"></a><span class="lineno"> 10</span> <span class="comment"> * sell copies of the Software, and to permit persons to whom the Software is</span></div><div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="comment"> * furnished to do so, subject to the following conditions:</span></div><div class="line"><a name="l00012"></a><span class="lineno"> 12</span> <span class="comment"> *</span></div><div class="line"><a name="l00013"></a><span class="lineno"> 13</span> <span class="comment"> * The above copyright notice and this permission notice shall be included in all</span></div><div class="line"><a name="l00014"></a><span class="lineno"> 14</span> <span class="comment"> * copies or substantial portions of the Software.</span></div><div class="line"><a name="l00015"></a><span class="lineno"> 15</span> <span class="comment"> *</span></div><div class="line"><a name="l00016"></a><span class="lineno"> 16</span> <span class="comment"> * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR</span></div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span> <span class="comment"> * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,</span></div><div class="line"><a name="l00018"></a><span class="lineno"> 18</span> <span class="comment"> * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE</span></div><div class="line"><a name="l00019"></a><span class="lineno"> 19</span> <span class="comment"> * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER</span></div><div class="line"><a name="l00020"></a><span class="lineno"> 20</span> <span class="comment"> * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,</span></div><div class="line"><a name="l00021"></a><span class="lineno"> 21</span> <span class="comment"> * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE</span></div><div class="line"><a name="l00022"></a><span class="lineno"> 22</span> <span class="comment"> * SOFTWARE.</span></div><div class="line"><a name="l00023"></a><span class="lineno"> 23</span> <span class="comment"> */</span></div><div class="line"><a name="l00024"></a><span class="lineno"> 24</span> <span class="preprocessor">#ifndef ARM_COMPUTE_CLDEPTHWISECONVOLUTIONLAYERNATIVEKERNEL_H</span></div><div class="line"><a name="l00025"></a><span class="lineno"> 25</span> <span class="preprocessor">#define ARM_COMPUTE_CLDEPTHWISECONVOLUTIONLAYERNATIVEKERNEL_H</span></div><div class="line"><a name="l00026"></a><span class="lineno"> 26</span> </div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="preprocessor">#include "<a class="code" href="_i_c_l_kernel_8h.xhtml">arm_compute/core/CL/ICLKernel.h</a>"</span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> </div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span> <span class="preprocessor">#include "<a class="code" href="_kernel_descriptors_8h.xhtml">arm_compute/core/KernelDescriptors.h</a>"</span></div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span> </div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="keyword">namespace </span><a class="code" href="namespacearm__compute.xhtml">arm_compute</a></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> {</div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span> <span class="keyword">class </span>ICLTensor;</div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span> <span class="comment"></span></div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span> <span class="comment">/** Interface for the kernel to run a MxN depthwise convolution. M and N are respectively the rows and columns of the filter</span></div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span> <span class="comment"> This kernel assumes that tensor for the weights is NOT reshaped (Native version) */</span></div><div class="line"><a name="l00037"></a><span class="lineno"><a class="line" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml"> 37</a></span> <span class="keyword">class </span><a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml">CLDepthwiseConvolutionLayerNativeKernel</a> : <span class="keyword">public</span> <a class="code" href="classarm__compute_1_1_i_c_l_kernel.xhtml">ICLKernel</a></div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span> {</div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span> <span class="keyword">public</span>:<span class="comment"></span></div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span> <span class="comment"> /** Default Constructor */</span></div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span>  <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#a271c52eab025d7a48b4c553d9d3ca174">CLDepthwiseConvolutionLayerNativeKernel</a>();<span class="comment"></span></div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span> <span class="comment"> /** Prevent instances of this class from being copied (As this class contains pointers) */</span></div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span>  <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#a271c52eab025d7a48b4c553d9d3ca174">CLDepthwiseConvolutionLayerNativeKernel</a>(<span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml">CLDepthwiseConvolutionLayerNativeKernel</a> &) = <span class="keyword">delete</span>;<span class="comment"></span></div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="comment"> /** Prevent instances of this class from being copied (As this class contains pointers) */</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span>  <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml">CLDepthwiseConvolutionLayerNativeKernel</a> &<a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#aedd679a6bf03b3c47be556897a6938f5">operator=</a>(<span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml">CLDepthwiseConvolutionLayerNativeKernel</a> &) = <span class="keyword">delete</span>;<span class="comment"></span></div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span> <span class="comment"> /** Allow instances of this class to be moved */</span></div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#a271c52eab025d7a48b4c553d9d3ca174">CLDepthwiseConvolutionLayerNativeKernel</a>(<a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml">CLDepthwiseConvolutionLayerNativeKernel</a> &&) = <span class="keywordflow">default</span>;<span class="comment"></span></div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span> <span class="comment"> /** Allow instances of this class to be moved */</span></div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span>  <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml">CLDepthwiseConvolutionLayerNativeKernel</a> &<a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#aedd679a6bf03b3c47be556897a6938f5">operator=</a>(<a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml">CLDepthwiseConvolutionLayerNativeKernel</a> &&) = <span class="keywordflow">default</span>;<span class="comment"></span></div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span> <span class="comment"> /** Initialize the function's source, destination and parameters</span></div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span> <span class="comment"> *</span></div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> <span class="comment"> * @param[in] input Source tensor. Data type supported: QASYMM8/QASYMM8_SIGNED/FP32/FP16. Data layout supported: NHWC</span></div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span> <span class="comment"> * @param[in] weights Weights tensor. A 3D tensor with dimensions [IFM, N, M].</span></div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span> <span class="comment"> * Data type supported: Same as @p input or QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL when @p input is QASYMM8.</span></div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span> <span class="comment"> * @param[in] biases Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.</span></div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span> <span class="comment"> * Data type supported: Same as @p input, S32 when input is QASYMM8/QASYMM8_SIGNED.</span></div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span> <span class="comment"> * @param[out] output Destination tensor. Data type supported: Same as @p input.</span></div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span> <span class="comment"> * @param[in] dwc_weights_info Depthwise convolution layer weights info to retrieve the number of output elements processed by each thread</span></div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span> <span class="comment"> * @param[in] dwc_info Depthwise convolution layer info</span></div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span> <span class="comment"> * @param[in] conv_info Padding and stride information to use for the convolution.</span></div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span> <span class="comment"> * @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1.</span></div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span> <span class="comment"> * @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).</span></div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span> <span class="comment"> * @param[in] output_multipliers (Optional) Output multipliers tensor for quantized computations. In case of per-channel quantization,</span></div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span> <span class="comment"> * the number of multipliers must be equal to the number of filters (IFM). Supported data types: S32</span></div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span> <span class="comment"> * @param[in] output_shifts (Optional) Output shifts tensor for quantized computations. In case of per-channel quantization,</span></div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span> <span class="comment"> * the number of multipliers must be equal to the number of filters (IFM). Supported data types: S32</span></div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span> <span class="comment"> */</span></div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  <span class="keywordtype">void</span> <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#af8e9479682a222c6ee73db664273b73a">configure</a>(<span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a64a08a9fec5aeee8650e7182b6d171d0">weights</a>, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *biases, <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *output, <span class="keyword">const</span> <a class="code" href="structarm__compute_1_1_d_w_c_weights_kernel_info.xhtml">DWCWeightsKernelInfo</a> &dwc_weights_info,</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span>  <span class="keyword">const</span> <a class="code" href="structarm__compute_1_1_d_w_c_kernel_info.xhtml">DWCKernelInfo</a> &dwc_info, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a> &<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a00525ff582f16038a1d3819aa44a23a3">conv_info</a>, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> depth_multiplier = 1, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_size2_d.xhtml">Size2D</a> &<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#ad3fd4136244e42ad89b01c02b904336d">dilation</a> = <a class="code" href="classarm__compute_1_1_size2_d.xhtml">Size2D</a>(1<a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa4c614360da93c0a041b22e537de151eb">U</a>, 1<a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa4c614360da93c0a041b22e537de151eb">U</a>),</div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *output_multipliers = <span class="keyword">nullptr</span>, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *output_shifts = <span class="keyword">nullptr</span>);<span class="comment"></span></div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span> <span class="comment"> /** Static function to check if given info will lead to a valid configuration of @ref CLDepthwiseConvolutionLayerNativeKernel</span></div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span> <span class="comment"> *</span></div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span> <span class="comment"> * @param[in] input Source tensor info. Data type supported: QASYMM8/QASYMM8_SIGNED/FP32/FP16. Data layout supported: NHWC</span></div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span> <span class="comment"> * @param[in] weights Weights tensor info. A 3D tensor with dimensions [IFM, N, M].</span></div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span> <span class="comment"> * Data type supported: Same as @p input or QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL when @p input is QASYMM8.</span></div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span> <span class="comment"> * @param[in] biases Biases tensor info. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.</span></div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span> <span class="comment"> * Data type supported: Same as @p input, S32 when input is QASYMM8/QASYMM8_SIGNED.</span></div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span> <span class="comment"> * @param[in] output Destination tensor info. Data type supported: Same as @p input.</span></div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span> <span class="comment"> * @param[in] dwc_weights_info Depthwise convolution layer weights info to retrieve the number of output elements processed by each thread</span></div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span> <span class="comment"> * @param[in] dwc_info Depthwise convolution layer info</span></div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span> <span class="comment"> * @param[in] conv_info Padding and stride information to use for the convolution.</span></div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span> <span class="comment"> * @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1.</span></div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span> <span class="comment"> * @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).</span></div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span> <span class="comment"> * @param[in] output_multipliers (Optional) Output multipliers tensor for quantized computations. In case of per-channel quantization,</span></div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span> <span class="comment"> * the number of multipliers must be equal to the number of filters (IFM). Supported data types: S32</span></div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span> <span class="comment"> * @param[in] output_shifts (Optional) Output shifts tensor for quantized computations. In case of per-channel quantization,</span></div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span> <span class="comment"> * the number of multipliers must be equal to the number of filters (IFM). Supported data types: S32</span></div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span> <span class="comment"> *</span></div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span> <span class="comment"> * @return a status</span></div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span> <span class="comment"> */</span></div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span>  <span class="keyword">static</span> <a class="code" href="classarm__compute_1_1_status.xhtml">Status</a> <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#a74cc304f794c459d5840fb3430b43f6c">validate</a>(<span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">input</a>, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a64a08a9fec5aeee8650e7182b6d171d0">weights</a>, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *biases, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *output, <span class="keyword">const</span> <a class="code" href="structarm__compute_1_1_d_w_c_weights_kernel_info.xhtml">DWCWeightsKernelInfo</a> &dwc_weights_info,</div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  <span class="keyword">const</span> <a class="code" href="structarm__compute_1_1_d_w_c_kernel_info.xhtml">DWCKernelInfo</a> &dwc_info, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a> &<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#a00525ff582f16038a1d3819aa44a23a3">conv_info</a>, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> depth_multiplier = 1, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_size2_d.xhtml">Size2D</a> &<a class="code" href="namespacearm__compute_1_1test_1_1validation.xhtml#ad3fd4136244e42ad89b01c02b904336d">dilation</a> = <a class="code" href="classarm__compute_1_1_size2_d.xhtml">Size2D</a>(1<a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa4c614360da93c0a041b22e537de151eb">U</a>, 1<a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa4c614360da93c0a041b22e537de151eb">U</a>),</div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *output_multipliers = <span class="keyword">nullptr</span>, <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_tensor_info.xhtml">ITensorInfo</a> *output_shifts = <span class="keyword">nullptr</span>);</div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span> </div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  <span class="comment">// Inherited methods overridden:</span></div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  <span class="keywordtype">void</span> <a class="code" href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#a493987e85723a8000eb26d1f00e2ad0e">run</a>(<span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_window.xhtml">Window</a> &<a class="code" href="classarm__compute_1_1_i_kernel.xhtml#ad34a46f53686c12a5c5e717cc9617fb6">window</a>, cl::CommandQueue &queue) <span class="keyword">override</span>;</div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span> </div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span> <span class="keyword">private</span>:</div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *_input;</div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *_weights;</div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *_biases;</div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *_output;</div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> _depth_multiplier;</div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *_output_multipliers;</div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_i_c_l_tensor.xhtml">ICLTensor</a> *_output_shifts;</div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span>  <span class="keywordtype">bool</span> _is_quantized;</div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span> };</div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span> } <span class="comment">// namespace arm_compute</span></div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span> <span class="preprocessor">#endif </span><span class="comment">/*ARM_COMPUTE_CLDEPTHWISECONVOLUTIONLAYERNATIVEKERNEL_H */</span><span class="preprocessor"></span></div><div class="ttc" id="classarm__compute_1_1_i_kernel_xhtml_ad34a46f53686c12a5c5e717cc9617fb6"><div class="ttname"><a href="classarm__compute_1_1_i_kernel.xhtml#ad34a46f53686c12a5c5e717cc9617fb6">arm_compute::IKernel::window</a></div><div class="ttdeci">const Window & window() const</div><div class="ttdoc">The maximum window the kernel can be executed on.</div><div class="ttdef"><b>Definition:</b> <a href="_i_kernel_8cpp_source.xhtml#l00028">IKernel.cpp:28</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_ad3fd4136244e42ad89b01c02b904336d"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#ad3fd4136244e42ad89b01c02b904336d">arm_compute::test::validation::dilation</a></div><div class="ttdeci">dilation</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_convolution_layer_8cpp_source.xhtml#l00182">ConvolutionLayer.cpp:182</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_a00525ff582f16038a1d3819aa44a23a3"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#a00525ff582f16038a1d3819aa44a23a3">arm_compute::test::validation::conv_info</a></div><div class="ttdeci">conv_info</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_winograd_8cpp_source.xhtml#l00597">Winograd.cpp:597</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel_xhtml_a271c52eab025d7a48b4c553d9d3ca174"><div class="ttname"><a href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#a271c52eab025d7a48b4c553d9d3ca174">arm_compute::CLDepthwiseConvolutionLayerNativeKernel::CLDepthwiseConvolutionLayerNativeKernel</a></div><div class="ttdeci">CLDepthwiseConvolutionLayerNativeKernel()</div><div class="ttdoc">Default Constructor.</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_depthwise_convolution_layer_native_kernel_8cpp_source.xhtml#l00182">CLDepthwiseConvolutionLayerNativeKernel.cpp:182</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_tensor_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_i_tensor_info.xhtml">arm_compute::ITensorInfo</a></div><div class="ttdoc">Store the tensor's metadata.</div><div class="ttdef"><b>Definition:</b> <a href="_i_tensor_info_8h_source.xhtml#l00040">ITensorInfo.h:40</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_status_xhtml"><div class="ttname"><a href="classarm__compute_1_1_status.xhtml">arm_compute::Status</a></div><div class="ttdoc">Status class.</div><div class="ttdef"><b>Definition:</b> <a href="_error_8h_source.xhtml#l00052">Error.h:52</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_c_l_kernel_xhtml"><div class="ttname"><a href="classarm__compute_1_1_i_c_l_kernel.xhtml">arm_compute::ICLKernel</a></div><div class="ttdoc">Common interface for all the OpenCL kernels.</div><div class="ttdef"><b>Definition:</b> <a href="_i_c_l_kernel_8h_source.xhtml#l00043">ICLKernel.h:43</a></div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml"><div class="ttname"><a href="namespacearm__compute.xhtml">arm_compute</a></div><div class="ttdoc">Copyright (c) 2017-2020 ARM Limited.</div><div class="ttdef"><b>Definition:</b> <a href="00__introduction_8dox_source.xhtml#l00024">00_introduction.dox:24</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_a8fcf2ddd9a1d58b1b280f5c0aed71845"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#a8fcf2ddd9a1d58b1b280f5c0aed71845">arm_compute::test::validation::input</a></div><div class="ttdeci">auto input</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_l_s_t_m_layer_quantized_8cpp_source.xhtml#l00487">LSTMLayerQuantized.cpp:487</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel_xhtml_a493987e85723a8000eb26d1f00e2ad0e"><div class="ttname"><a href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#a493987e85723a8000eb26d1f00e2ad0e">arm_compute::CLDepthwiseConvolutionLayerNativeKernel::run</a></div><div class="ttdeci">void run(const Window &window, cl::CommandQueue &queue) override</div><div class="ttdoc">Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_depthwise_convolution_layer_native_kernel_8cpp_source.xhtml#l00321">CLDepthwiseConvolutionLayerNativeKernel.cpp:321</a></div></div> |
| <div class="ttc" id="namespacearm__compute_xhtml_a1ce9b523fd4f3b5bbcadcd796183455aa4c614360da93c0a041b22e537de151eb"><div class="ttname"><a href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa4c614360da93c0a041b22e537de151eb">arm_compute::Channel::U</a></div><div class="ttdoc">Cb/U channel.</div></div> |
| <div class="ttc" id="structarm__compute_1_1_d_w_c_kernel_info_xhtml"><div class="ttname"><a href="structarm__compute_1_1_d_w_c_kernel_info.xhtml">arm_compute::DWCKernelInfo</a></div><div class="ttdoc">Descriptor used by the depthwise convolution kernels.</div><div class="ttdef"><b>Definition:</b> <a href="_kernel_descriptors_8h_source.xhtml#l00068">KernelDescriptors.h:68</a></div></div> |
| <div class="ttc" id="_i_c_l_kernel_8h_xhtml"><div class="ttname"><a href="_i_c_l_kernel_8h.xhtml">ICLKernel.h</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_pad_stride_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_pad_stride_info.xhtml">arm_compute::PadStrideInfo</a></div><div class="ttdoc">Padding and stride information class.</div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l00686">Types.h:686</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel_xhtml_af8e9479682a222c6ee73db664273b73a"><div class="ttname"><a href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#af8e9479682a222c6ee73db664273b73a">arm_compute::CLDepthwiseConvolutionLayerNativeKernel::configure</a></div><div class="ttdeci">void configure(const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const DWCWeightsKernelInfo &dwc_weights_info, const DWCKernelInfo &dwc_info, const PadStrideInfo &conv_info, unsigned int depth_multiplier=1, const Size2D &dilation=Size2D(1U, 1U), const ICLTensor *output_multipliers=nullptr, const ICLTensor *output_shifts=nullptr)</div><div class="ttdoc">Initialize the function's source, destination and parameters.</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_depthwise_convolution_layer_native_kernel_8cpp_source.xhtml#l00194">CLDepthwiseConvolutionLayerNativeKernel.cpp:194</a></div></div> |
| <div class="ttc" id="structarm__compute_1_1_d_w_c_weights_kernel_info_xhtml"><div class="ttname"><a href="structarm__compute_1_1_d_w_c_weights_kernel_info.xhtml">arm_compute::DWCWeightsKernelInfo</a></div><div class="ttdoc">Descriptor used by the depthwise convolution kernels to retrieve the number of output elements proces...</div><div class="ttdef"><b>Definition:</b> <a href="_kernel_descriptors_8h_source.xhtml#l00074">KernelDescriptors.h:74</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel_xhtml_aedd679a6bf03b3c47be556897a6938f5"><div class="ttname"><a href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#aedd679a6bf03b3c47be556897a6938f5">arm_compute::CLDepthwiseConvolutionLayerNativeKernel::operator=</a></div><div class="ttdeci">CLDepthwiseConvolutionLayerNativeKernel & operator=(const CLDepthwiseConvolutionLayerNativeKernel &)=delete</div><div class="ttdoc">Prevent instances of this class from being copied (As this class contains pointers)</div></div> |
| <div class="ttc" id="classarm__compute_1_1_i_c_l_tensor_xhtml"><div class="ttname"><a href="classarm__compute_1_1_i_c_l_tensor.xhtml">arm_compute::ICLTensor</a></div><div class="ttdoc">Interface for OpenCL tensor.</div><div class="ttdef"><b>Definition:</b> <a href="_i_c_l_tensor_8h_source.xhtml#l00042">ICLTensor.h:42</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_size2_d_xhtml"><div class="ttname"><a href="classarm__compute_1_1_size2_d.xhtml">arm_compute::Size2D</a></div><div class="ttdoc">Class for specifying the size of an image or rectangle.</div><div class="ttdef"><b>Definition:</b> <a href="_size2_d_8h_source.xhtml#l00034">Size2D.h:34</a></div></div> |
| <div class="ttc" id="namespacearm__compute_1_1test_1_1validation_xhtml_a64a08a9fec5aeee8650e7182b6d171d0"><div class="ttname"><a href="namespacearm__compute_1_1test_1_1validation.xhtml#a64a08a9fec5aeee8650e7182b6d171d0">arm_compute::test::validation::weights</a></div><div class="ttdeci">CLTensor weights</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_2_convolution_layer_8cpp_source.xhtml#l00188">ConvolutionLayer.cpp:188</a></div></div> |
| <div class="ttc" id="_kernel_descriptors_8h_xhtml"><div class="ttname"><a href="_kernel_descriptors_8h.xhtml">KernelDescriptors.h</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_window_xhtml"><div class="ttname"><a href="classarm__compute_1_1_window.xhtml">arm_compute::Window</a></div><div class="ttdoc">Describe a multidimensional execution window.</div><div class="ttdef"><b>Definition:</b> <a href="_window_8h_source.xhtml#l00039">Window.h:39</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel_xhtml_a74cc304f794c459d5840fb3430b43f6c"><div class="ttname"><a href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml#a74cc304f794c459d5840fb3430b43f6c">arm_compute::CLDepthwiseConvolutionLayerNativeKernel::validate</a></div><div class="ttdeci">static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const DWCWeightsKernelInfo &dwc_weights_info, const DWCKernelInfo &dwc_info, const PadStrideInfo &conv_info, unsigned int depth_multiplier=1, const Size2D &dilation=Size2D(1U, 1U), const ITensorInfo *output_multipliers=nullptr, const ITensorInfo *output_shifts=nullptr)</div><div class="ttdoc">Static function to check if given info will lead to a valid configuration of CLDepthwiseConvolutionLa...</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_depthwise_convolution_layer_native_kernel_8cpp_source.xhtml#l00306">CLDepthwiseConvolutionLayerNativeKernel.cpp:306</a></div></div> |
| <div class="ttc" id="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel_xhtml"><div class="ttname"><a href="classarm__compute_1_1_c_l_depthwise_convolution_layer_native_kernel.xhtml">arm_compute::CLDepthwiseConvolutionLayerNativeKernel</a></div><div class="ttdoc">Interface for the kernel to run a MxN depthwise convolution.</div><div class="ttdef"><b>Definition:</b> <a href="_c_l_depthwise_convolution_layer_native_kernel_8h_source.xhtml#l00037">CLDepthwiseConvolutionLayerNativeKernel.h:37</a></div></div> |
| </div><!-- fragment --></div><!-- contents --> |
| </div><!-- doc-content --> |
| <!-- start footer part --> |
| <div id="nav-path" class="navpath"><!-- id is needed for treeview function! --> |
| <ul> |
| <li class="navelem"><a class="el" href="dir_214608ef36d61442cb2b0c1c4e9a7def.xhtml">arm_compute</a></li><li class="navelem"><a class="el" href="dir_1fb090f0c6070330bfaccc4236d3ca0d.xhtml">core</a></li><li class="navelem"><a class="el" href="dir_1633709b037eda5b8477677909f78129.xhtml">CL</a></li><li class="navelem"><a class="el" href="dir_f906bbebc596bc606d589ccb705e6595.xhtml">kernels</a></li><li class="navelem"><a class="el" href="_c_l_depthwise_convolution_layer_native_kernel_8h.xhtml">CLDepthwiseConvolutionLayerNativeKernel.h</a></li> |
| <li class="footer">Generated on Thu Mar 5 2020 16:06:54 for Compute Library by |
| <a href="http://www.doxygen.org/index.html"> |
| <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.15 </li> |
| </ul> |
| </div> |
| </body> |
| </html> |
