arm_compute v17.12
diff --git a/documentation/neon__cnn_8cpp.xhtml b/documentation/neon__cnn_8cpp.xhtml
index 7fb825b..8e91928 100644
--- a/documentation/neon__cnn_8cpp.xhtml
+++ b/documentation/neon__cnn_8cpp.xhtml
@@ -4,7 +4,7 @@
<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 1.8.6"/>
+<meta name="generator" content="Doxygen 1.8.11"/>
<meta name="robots" content="NOINDEX, NOFOLLOW" /> <!-- Prevent indexing by search engines -->
<title>Compute Library: examples/neon_cnn.cpp File Reference</title>
<link href="tabs.css" rel="stylesheet" type="text/css"/>
@@ -12,22 +12,24 @@
<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">
$(document).ready(initResizable);
$(window).load(resizeHeight);
</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/javascript">
- $(document).ready(function() { searchBox.OnSelectItem(0); });
+ $(document).ready(function() { init_search(); });
</script>
<script type="text/x-mathjax-config">
MathJax.Hub.Config({
extensions: ["tex2jax.js"],
jax: ["input/TeX","output/HTML-CSS"],
});
-</script><script src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script>
+</script><script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script>
<link href="doxygen.css" rel="stylesheet" type="text/css" />
</head>
<body>
@@ -38,7 +40,7 @@
<tr style="height: 56px;">
<td style="padding-left: 0.5em;">
<div id="projectname">Compute Library
-  <span id="projectnumber">17.10</span>
+  <span id="projectnumber">17.12</span>
</div>
</td>
</tr>
@@ -46,7 +48,7 @@
</table>
</div>
<!-- end header part -->
-<!-- Generated by Doxygen 1.8.6 -->
+<!-- Generated by Doxygen 1.8.11 -->
<script type="text/javascript">
var searchBox = new SearchBox("searchBox", "search",false,'Search');
</script>
@@ -101,7 +103,7 @@
onmouseover="return searchBox.OnSearchSelectShow()"
onmouseout="return searchBox.OnSearchSelectHide()"
onkeydown="return searchBox.OnSearchSelectKey(event)">
-<a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(0)"><span class="SelectionMark"> </span>All</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(1)"><span class="SelectionMark"> </span>Data Structures</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(2)"><span class="SelectionMark"> </span>Namespaces</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(3)"><span class="SelectionMark"> </span>Files</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(4)"><span class="SelectionMark"> </span>Functions</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(5)"><span class="SelectionMark"> </span>Variables</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(6)"><span class="SelectionMark"> </span>Typedefs</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(7)"><span class="SelectionMark"> </span>Enumerations</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(8)"><span class="SelectionMark"> </span>Enumerator</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(9)"><span class="SelectionMark"> </span>Friends</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(10)"><span class="SelectionMark"> </span>Macros</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(11)"><span class="SelectionMark"> </span>Pages</a></div>
+</div>
<!-- iframe showing the search results (closed by default) -->
<div id="MSearchResultsWindow">
@@ -117,13 +119,13 @@
<div class="title">neon_cnn.cpp File Reference</div> </div>
</div><!--header-->
<div class="contents">
-<div class="textblock"><code>#include "<a class="el" href="_n_e_functions_8h_source.xhtml">arm_compute/runtime/NEON/NEFunctions.h</a>"</code><br/>
-<code>#include "<a class="el" href="arm__compute_2core_2_types_8h_source.xhtml">arm_compute/core/Types.h</a>"</code><br/>
-<code>#include "<a class="el" href="_allocator_8h_source.xhtml">arm_compute/runtime/Allocator.h</a>"</code><br/>
-<code>#include "<a class="el" href="_blob_lifetime_manager_8h_source.xhtml">arm_compute/runtime/BlobLifetimeManager.h</a>"</code><br/>
-<code>#include "<a class="el" href="_memory_manager_on_demand_8h_source.xhtml">arm_compute/runtime/MemoryManagerOnDemand.h</a>"</code><br/>
-<code>#include "<a class="el" href="_pool_manager_8h_source.xhtml">arm_compute/runtime/PoolManager.h</a>"</code><br/>
-<code>#include "<a class="el" href="utils_2_utils_8h_source.xhtml">utils/Utils.h</a>"</code><br/>
+<div class="textblock"><code>#include "<a class="el" href="_n_e_functions_8h_source.xhtml">arm_compute/runtime/NEON/NEFunctions.h</a>"</code><br />
+<code>#include "<a class="el" href="arm__compute_2core_2_types_8h_source.xhtml">arm_compute/core/Types.h</a>"</code><br />
+<code>#include "<a class="el" href="_allocator_8h_source.xhtml">arm_compute/runtime/Allocator.h</a>"</code><br />
+<code>#include "<a class="el" href="_blob_lifetime_manager_8h_source.xhtml">arm_compute/runtime/BlobLifetimeManager.h</a>"</code><br />
+<code>#include "<a class="el" href="_memory_manager_on_demand_8h_source.xhtml">arm_compute/runtime/MemoryManagerOnDemand.h</a>"</code><br />
+<code>#include "<a class="el" href="_pool_manager_8h_source.xhtml">arm_compute/runtime/PoolManager.h</a>"</code><br />
+<code>#include "<a class="el" href="utils_2_utils_8h_source.xhtml">utils/Utils.h</a>"</code><br />
</div>
<p><a href="neon__cnn_8cpp_source.xhtml">Go to the source code of this file.</a></p>
<table class="memberdecls">
@@ -132,7 +134,7 @@
<tr class="memitem:a7616847a3120a787be556c0bb30f43b4"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="neon__cnn_8cpp.xhtml#a7616847a3120a787be556c0bb30f43b4">main_cnn</a> (int argc, const char **argv)</td></tr>
<tr class="separator:a7616847a3120a787be556c0bb30f43b4"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a217dbf8b442f20279ea00b898af96f52"><td class="memItemLeft" align="right" valign="top">int </td><td class="memItemRight" valign="bottom"><a class="el" href="neon__cnn_8cpp.xhtml#a217dbf8b442f20279ea00b898af96f52">main</a> (int argc, const char **argv)</td></tr>
-<tr class="memdesc:a217dbf8b442f20279ea00b898af96f52"><td class="mdescLeft"> </td><td class="mdescRight">Main program for cnn test. <a href="#a217dbf8b442f20279ea00b898af96f52">More...</a><br/></td></tr>
+<tr class="memdesc:a217dbf8b442f20279ea00b898af96f52"><td class="mdescLeft"> </td><td class="mdescRight">Main program for cnn test. <a href="#a217dbf8b442f20279ea00b898af96f52">More...</a><br /></td></tr>
<tr class="separator:a217dbf8b442f20279ea00b898af96f52"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<h2 class="groupheader">Function Documentation</h2>
@@ -174,9 +176,7 @@
<p>Definition at line <a class="el" href="neon__cnn_8cpp_source.xhtml#l00294">294</a> of file <a class="el" href="neon__cnn_8cpp_source.xhtml">neon_cnn.cpp</a>.</p>
<p>References <a class="el" href="neon__cnn_8cpp_source.xhtml#l00036">main_cnn()</a>, and <a class="el" href="utils_2_utils_8cpp_source.xhtml#l00069">arm_compute::utils::run_example()</a>.</p>
-<div class="fragment"><div class="line"><a name="l00295"></a><span class="lineno"> 295</span> {</div>
-<div class="line"><a name="l00296"></a><span class="lineno"> 296</span>  <span class="keywordflow">return</span> <a class="code" href="namespacearm__compute_1_1utils.xhtml#a4c9395db2c8b8d0c336656a7b58fca3e">utils::run_example</a>(argc, argv, <a class="code" href="neon__cnn_8cpp.xhtml#a7616847a3120a787be556c0bb30f43b4">main_cnn</a>);</div>
-<div class="line"><a name="l00297"></a><span class="lineno"> 297</span> }<div class="ttc" id="namespacearm__compute_1_1utils_xhtml_a4c9395db2c8b8d0c336656a7b58fca3e"><div class="ttname"><a href="namespacearm__compute_1_1utils.xhtml#a4c9395db2c8b8d0c336656a7b58fca3e">arm_compute::utils::run_example</a></div><div class="ttdeci">int run_example(int argc, const char **argv, example &func)</div><div class="ttdoc">Run an example and handle the potential exceptions it throws. </div><div class="ttdef"><b>Definition:</b> <a href="utils_2_utils_8cpp_source.xhtml#l00069">Utils.cpp:69</a></div></div>
+<div class="fragment"><div class="line"><a name="l00295"></a><span class="lineno"> 295</span> {</div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span>  <span class="keywordflow">return</span> <a class="code" href="namespacearm__compute_1_1utils.xhtml#a4c9395db2c8b8d0c336656a7b58fca3e">utils::run_example</a>(argc, argv, <a class="code" href="neon__cnn_8cpp.xhtml#a7616847a3120a787be556c0bb30f43b4">main_cnn</a>);</div><div class="line"><a name="l00297"></a><span class="lineno"> 297</span> }<div class="ttc" id="namespacearm__compute_1_1utils_xhtml_a4c9395db2c8b8d0c336656a7b58fca3e"><div class="ttname"><a href="namespacearm__compute_1_1utils.xhtml#a4c9395db2c8b8d0c336656a7b58fca3e">arm_compute::utils::run_example</a></div><div class="ttdeci">int run_example(int argc, const char **argv, example &func)</div><div class="ttdoc">Run an example and handle the potential exceptions it throws. </div><div class="ttdef"><b>Definition:</b> <a href="utils_2_utils_8cpp_source.xhtml#l00069">Utils.cpp:69</a></div></div>
<div class="ttc" id="neon__cnn_8cpp_xhtml_a7616847a3120a787be556c0bb30f43b4"><div class="ttname"><a href="neon__cnn_8cpp.xhtml#a7616847a3120a787be556c0bb30f43b4">main_cnn</a></div><div class="ttdeci">void main_cnn(int argc, const char **argv)</div><div class="ttdef"><b>Definition:</b> <a href="neon__cnn_8cpp_source.xhtml#l00036">neon_cnn.cpp:36</a></div></div>
</div><!-- fragment -->
</div>
@@ -207,268 +207,21 @@
<p>Definition at line <a class="el" href="neon__cnn_8cpp_source.xhtml#l00036">36</a> of file <a class="el" href="neon__cnn_8cpp_source.xhtml">neon_cnn.cpp</a>.</p>
-<p>References <a class="el" href="_memory_group_base_8h_source.xhtml#l00124">MemoryGroupBase< typename >::acquire()</a>, <a class="el" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">TensorAllocator::allocate()</a>, <a class="el" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">Tensor::allocator()</a>, <a class="el" href="_error_8h_source.xhtml#l00049">ARM_COMPUTE_UNUSED</a>, <a class="el" href="namespacearm__compute.xhtml#a9172da722f0a434e5cc07c0a3c115d93afcefd647d6a866603c627b11347c707a">arm_compute::AVG</a>, <a class="el" href="classarm__compute_1_1_n_e_activation_layer.xhtml#adfb5ef37594fc9371c4a2b95e3d5e31b">NEActivationLayer::configure()</a>, <a class="el" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#a6fa6e4b65796fd0bf43da9b4d617d568">NEPoolingLayer::configure()</a>, <a class="el" href="classarm__compute_1_1_n_e_softmax_layer.xhtml#a9daf8026e68559806afe7d0aa12693d6">NESoftmaxLayer::configure()</a>, <a class="el" href="classarm__compute_1_1_n_e_fully_connected_layer.xhtml#ae184041d029cd0dded821875db8a0929">NEFullyConnectedLayer::configure()</a>, <a class="el" href="classarm__compute_1_1_n_e_convolution_layer.xhtml#aee13eaa771696a8257ededf5bf921cbb">NEConvolutionLayer::configure()</a>, <a class="el" href="namespacearm__compute.xhtml#ab4e88c89b3b7ea1735996cc4def22d58a44ad4ef5a76e6aa6fb3e3fa079a54fda">arm_compute::F32</a>, <a class="el" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">TensorAllocator::init()</a>, <a class="el" href="_memory_group_base_8h_source.xhtml#l00096">MemoryGroupBase< typename >::manage()</a>, <a class="el" href="namespacearm__compute.xhtml#adf2ced65e536375a1c96425d9fced858a26a4b44a837bf97b972628509912b4a5">arm_compute::MAX</a>, <a class="el" href="_memory_group_base_8h_source.xhtml#l00135">MemoryGroupBase< typename >::release()</a>, <a class="el" href="classarm__compute_1_1_activation_layer_info.xhtml#a56297e0f7b215eea46c818cb7528d9eaad346bb4679d29be241279f15d7795c1c">ActivationLayerInfo::RELU</a>, <a class="el" href="classarm__compute_1_1_i_n_e_simple_function.xhtml#ab5fd6e96c07aaaed2747c7e16ed5951e">INESimpleFunction::run()</a>, <a class="el" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">NEPoolingLayer::run()</a>, <a class="el" href="classarm__compute_1_1_n_e_softmax_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">NESoftmaxLayer::run()</a>, <a class="el" href="classarm__compute_1_1_n_e_fully_connected_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">NEFullyConnectedLayer::run()</a>, <a class="el" href="classarm__compute_1_1_n_e_convolution_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">NEConvolutionLayer::run()</a>, <a class="el" href="_tensor_shape_8h_source.xhtml#l00074">TensorShape::set()</a>, <a class="el" href="_dimensions_8h_source.xhtml#l00081">Dimensions< T >::x()</a>, <a class="el" href="_dimensions_8h_source.xhtml#l00086">Dimensions< T >::y()</a>, and <a class="el" href="_dimensions_8h_source.xhtml#l00091">Dimensions< T >::z()</a>.</p>
+<p>References <a class="el" href="_memory_group_base_8h_source.xhtml#l00125">MemoryGroupBase< TensorType >::acquire()</a>, <a class="el" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">TensorAllocator::allocate()</a>, <a class="el" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">Tensor::allocator()</a>, <a class="el" href="core_2_error_8h_source.xhtml#l00147">ARM_COMPUTE_UNUSED</a>, <a class="el" href="namespacearm__compute.xhtml#a9172da722f0a434e5cc07c0a3c115d93afcefd647d6a866603c627b11347c707a">arm_compute::AVG</a>, <a class="el" href="classarm__compute_1_1_n_e_activation_layer.xhtml#adfb5ef37594fc9371c4a2b95e3d5e31b">NEActivationLayer::configure()</a>, <a class="el" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#a6fa6e4b65796fd0bf43da9b4d617d568">NEPoolingLayer::configure()</a>, <a class="el" href="classarm__compute_1_1_n_e_softmax_layer.xhtml#a062268dfb7b8a63b7331d1cafcb7a081">NESoftmaxLayer::configure()</a>, <a class="el" href="classarm__compute_1_1_n_e_fully_connected_layer.xhtml#ae184041d029cd0dded821875db8a0929">NEFullyConnectedLayer::configure()</a>, <a class="el" href="classarm__compute_1_1_n_e_convolution_layer.xhtml#aee13eaa771696a8257ededf5bf921cbb">NEConvolutionLayer::configure()</a>, <a class="el" href="namespacearm__compute.xhtml#ab4e88c89b3b7ea1735996cc4def22d58a44ad4ef5a76e6aa6fb3e3fa079a54fda">arm_compute::F32</a>, <a class="el" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">TensorAllocator::init()</a>, <a class="el" href="_memory_group_base_8h_source.xhtml#l00097">MemoryGroupBase< TensorType >::manage()</a>, <a class="el" href="namespacearm__compute.xhtml#adf2ced65e536375a1c96425d9fced858a26a4b44a837bf97b972628509912b4a5">arm_compute::MAX</a>, <a class="el" href="_memory_group_base_8h_source.xhtml#l00136">MemoryGroupBase< TensorType >::release()</a>, <a class="el" href="classarm__compute_1_1_activation_layer_info.xhtml#a56297e0f7b215eea46c818cb7528d9eaad346bb4679d29be241279f15d7795c1c">ActivationLayerInfo::RELU</a>, <a class="el" href="classarm__compute_1_1_i_n_e_simple_function.xhtml#ab5fd6e96c07aaaed2747c7e16ed5951e">INESimpleFunction::run()</a>, <a class="el" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">NEPoolingLayer::run()</a>, <a class="el" href="classarm__compute_1_1_n_e_softmax_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">NESoftmaxLayer::run()</a>, <a class="el" href="classarm__compute_1_1_n_e_fully_connected_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">NEFullyConnectedLayer::run()</a>, <a class="el" href="classarm__compute_1_1_n_e_convolution_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">NEConvolutionLayer::run()</a>, <a class="el" href="_tensor_shape_8h_source.xhtml#l00074">TensorShape::set()</a>, <a class="el" href="_dimensions_8h_source.xhtml#l00081">Dimensions< T >::x()</a>, <a class="el" href="_dimensions_8h_source.xhtml#l00086">Dimensions< T >::y()</a>, and <a class="el" href="_dimensions_8h_source.xhtml#l00091">Dimensions< T >::z()</a>.</p>
<p>Referenced by <a class="el" href="neon__cnn_8cpp_source.xhtml#l00294">main()</a>.</p>
-<div class="fragment"><div class="line"><a name="l00037"></a><span class="lineno"> 37</span> {</div>
-<div class="line"><a name="l00038"></a><span class="lineno"> 38</span>  <a class="code" href="_error_8h.xhtml#a4103adbb45806b2f2002d44b91d0d206">ARM_COMPUTE_UNUSED</a>(argc);</div>
-<div class="line"><a name="l00039"></a><span class="lineno"> 39</span>  <a class="code" href="_error_8h.xhtml#a4103adbb45806b2f2002d44b91d0d206">ARM_COMPUTE_UNUSED</a>(argv);</div>
-<div class="line"><a name="l00040"></a><span class="lineno"> 40</span> </div>
-<div class="line"><a name="l00041"></a><span class="lineno"> 41</span>  <span class="comment">// Create NEON allocator</span></div>
-<div class="line"><a name="l00042"></a><span class="lineno"> 42</span>  <a class="code" href="classarm__compute_1_1_allocator.xhtml">Allocator</a> allocator;</div>
-<div class="line"><a name="l00043"></a><span class="lineno"> 43</span> </div>
-<div class="line"><a name="l00044"></a><span class="lineno"> 44</span>  <span class="comment">// Create memory manager components</span></div>
-<div class="line"><a name="l00045"></a><span class="lineno"> 45</span>  <span class="comment">// We need 2 memory managers: 1 for handling the tensors within the functions (mm_layers) and 1 for handling the input and output tensors of the functions (mm_transitions))</span></div>
-<div class="line"><a name="l00046"></a><span class="lineno"> 46</span>  <span class="keyword">auto</span> lifetime_mgr0 = std::make_shared<BlobLifetimeManager>(); <span class="comment">// Create lifetime manager</span></div>
-<div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  <span class="keyword">auto</span> lifetime_mgr1 = std::make_shared<BlobLifetimeManager>(); <span class="comment">// Create lifetime manager</span></div>
-<div class="line"><a name="l00048"></a><span class="lineno"> 48</span>  <span class="keyword">auto</span> pool_mgr0 = std::make_shared<PoolManager>(); <span class="comment">// Create pool manager</span></div>
-<div class="line"><a name="l00049"></a><span class="lineno"> 49</span>  <span class="keyword">auto</span> pool_mgr1 = std::make_shared<PoolManager>(); <span class="comment">// Create pool manager</span></div>
-<div class="line"><a name="l00050"></a><span class="lineno"> 50</span>  <span class="keyword">auto</span> mm_layers = std::make_shared<MemoryManagerOnDemand>(lifetime_mgr0, pool_mgr0); <span class="comment">// Create the memory manager</span></div>
-<div class="line"><a name="l00051"></a><span class="lineno"> 51</span>  <span class="keyword">auto</span> mm_transitions = std::make_shared<MemoryManagerOnDemand>(lifetime_mgr1, pool_mgr1); <span class="comment">// Create the memory manager</span></div>
-<div class="line"><a name="l00052"></a><span class="lineno"> 52</span> </div>
-<div class="line"><a name="l00053"></a><span class="lineno"> 53</span>  <span class="comment">// The src tensor should contain the input image</span></div>
-<div class="line"><a name="l00054"></a><span class="lineno"> 54</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> src;</div>
-<div class="line"><a name="l00055"></a><span class="lineno"> 55</span> </div>
-<div class="line"><a name="l00056"></a><span class="lineno"> 56</span>  <span class="comment">// The weights and biases tensors should be initialized with the values inferred with the training</span></div>
-<div class="line"><a name="l00057"></a><span class="lineno"> 57</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> weights0;</div>
-<div class="line"><a name="l00058"></a><span class="lineno"> 58</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> weights1;</div>
-<div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> weights2;</div>
-<div class="line"><a name="l00060"></a><span class="lineno"> 60</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> biases0;</div>
-<div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> biases1;</div>
-<div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> biases2;</div>
-<div class="line"><a name="l00063"></a><span class="lineno"> 63</span> </div>
-<div class="line"><a name="l00064"></a><span class="lineno"> 64</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_conv0;</div>
-<div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_conv1;</div>
-<div class="line"><a name="l00066"></a><span class="lineno"> 66</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_act0;</div>
-<div class="line"><a name="l00067"></a><span class="lineno"> 67</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_act1;</div>
-<div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_act2;</div>
-<div class="line"><a name="l00069"></a><span class="lineno"> 69</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_pool0;</div>
-<div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_pool1;</div>
-<div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_fc0;</div>
-<div class="line"><a name="l00072"></a><span class="lineno"> 72</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_softmax;</div>
-<div class="line"><a name="l00073"></a><span class="lineno"> 73</span> </div>
-<div class="line"><a name="l00074"></a><span class="lineno"> 74</span>  <span class="comment">// Create layers and set memory manager where allowed to manage internal memory requirements</span></div>
-<div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  <a class="code" href="classarm__compute_1_1_n_e_convolution_layer.xhtml">NEConvolutionLayer</a> conv0(mm_layers);</div>
-<div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  <a class="code" href="classarm__compute_1_1_n_e_convolution_layer.xhtml">NEConvolutionLayer</a> conv1(mm_layers);</div>
-<div class="line"><a name="l00077"></a><span class="lineno"> 77</span>  <a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml">NEPoolingLayer</a> pool0;</div>
-<div class="line"><a name="l00078"></a><span class="lineno"> 78</span>  <a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml">NEPoolingLayer</a> pool1;</div>
-<div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <a class="code" href="classarm__compute_1_1_n_e_fully_connected_layer.xhtml">NEFullyConnectedLayer</a> fc0(mm_layers);</div>
-<div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  <a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml">NEActivationLayer</a> act0;</div>
-<div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  <a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml">NEActivationLayer</a> act1;</div>
-<div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  <a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml">NEActivationLayer</a> act2;</div>
-<div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  <a class="code" href="classarm__compute_1_1_n_e_softmax_layer.xhtml">NESoftmaxLayer</a> softmax(mm_layers);</div>
-<div class="line"><a name="l00084"></a><span class="lineno"> 84</span> </div>
-<div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  <span class="comment">/* [Initialize tensors] */</span></div>
-<div class="line"><a name="l00086"></a><span class="lineno"> 86</span> </div>
-<div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  <span class="comment">// Initialize src tensor</span></div>
-<div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> width_src_image = 32;</div>
-<div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> height_src_image = 32;</div>
-<div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> ifm_src_img = 1;</div>
-<div class="line"><a name="l00091"></a><span class="lineno"> 91</span> </div>
-<div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> src_shape(width_src_image, height_src_image, ifm_src_img);</div>
-<div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  src.allocator()->init(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(src_shape, 1, DataType::F32));</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">// Initialize tensors of conv0</span></div>
-<div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kernel_x_conv0 = 5;</div>
-<div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kernel_y_conv0 = 5;</div>
-<div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> ofm_conv0 = 8;</div>
-<div class="line"><a name="l00099"></a><span class="lineno"> 99</span> </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_tensor_shape.xhtml">TensorShape</a> weights_shape_conv0(kernel_x_conv0, kernel_y_conv0, src_shape.z(), ofm_conv0);</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_tensor_shape.xhtml">TensorShape</a> biases_shape_conv0(weights_shape_conv0[3]);</div>
-<div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_conv0(src_shape.x(), src_shape.y(), weights_shape_conv0[3]);</div>
-<div class="line"><a name="l00103"></a><span class="lineno"> 103</span> </div>
-<div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  weights0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(weights_shape_conv0, 1, DataType::F32));</div>
-<div class="line"><a name="l00105"></a><span class="lineno"> 105</span>  biases0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(biases_shape_conv0, 1, DataType::F32));</div>
-<div class="line"><a name="l00106"></a><span class="lineno"> 106</span>  out_conv0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_conv0, 1, DataType::F32));</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">// Initialize tensor of act0</span></div>
-<div class="line"><a name="l00109"></a><span class="lineno"> 109</span>  out_act0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_conv0, 1, DataType::F32));</div>
-<div class="line"><a name="l00110"></a><span class="lineno"> 110</span> </div>
-<div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  <span class="comment">// Initialize tensor of pool0</span></div>
-<div class="line"><a name="l00112"></a><span class="lineno"> 112</span>  <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_pool0 = out_shape_conv0;</div>
-<div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  out_shape_pool0.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a0cb0e1f5da2e1cc2e0ea5690450f53e8">set</a>(0, out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#afb5cd37bb08f1029691590372e6330f0">x</a>() / 2);</div>
-<div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  out_shape_pool0.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a0cb0e1f5da2e1cc2e0ea5690450f53e8">set</a>(1, out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a691c9cb93365c2e33f3429de43244098">y</a>() / 2);</div>
-<div class="line"><a name="l00115"></a><span class="lineno"> 115</span>  out_pool0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_pool0, 1, DataType::F32));</div>
-<div class="line"><a name="l00116"></a><span class="lineno"> 116</span> </div>
-<div class="line"><a name="l00117"></a><span class="lineno"> 117</span>  <span class="comment">// Initialize tensors of conv1</span></div>
-<div class="line"><a name="l00118"></a><span class="lineno"> 118</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kernel_x_conv1 = 3;</div>
-<div class="line"><a name="l00119"></a><span class="lineno"> 119</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kernel_y_conv1 = 3;</div>
-<div class="line"><a name="l00120"></a><span class="lineno"> 120</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> ofm_conv1 = 16;</div>
-<div class="line"><a name="l00121"></a><span class="lineno"> 121</span> </div>
-<div class="line"><a name="l00122"></a><span class="lineno"> 122</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> weights_shape_conv1(kernel_x_conv1, kernel_y_conv1, out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a336121cb63ed79fa0a072eed03d694ac">z</a>(), ofm_conv1);</div>
-<div class="line"><a name="l00123"></a><span class="lineno"> 123</span> </div>
-<div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> biases_shape_conv1(weights_shape_conv1[3]);</div>
-<div class="line"><a name="l00125"></a><span class="lineno"> 125</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_conv1(out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#afb5cd37bb08f1029691590372e6330f0">x</a>(), out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a691c9cb93365c2e33f3429de43244098">y</a>(), weights_shape_conv1[3]);</div>
-<div class="line"><a name="l00126"></a><span class="lineno"> 126</span> </div>
-<div class="line"><a name="l00127"></a><span class="lineno"> 127</span>  weights1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(weights_shape_conv1, 1, DataType::F32));</div>
-<div class="line"><a name="l00128"></a><span class="lineno"> 128</span>  biases1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(biases_shape_conv1, 1, DataType::F32));</div>
-<div class="line"><a name="l00129"></a><span class="lineno"> 129</span>  out_conv1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_conv1, 1, DataType::F32));</div>
-<div class="line"><a name="l00130"></a><span class="lineno"> 130</span> </div>
-<div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  <span class="comment">// Initialize tensor of act1</span></div>
-<div class="line"><a name="l00132"></a><span class="lineno"> 132</span>  out_act1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_conv1, 1, DataType::F32));</div>
-<div class="line"><a name="l00133"></a><span class="lineno"> 133</span> </div>
-<div class="line"><a name="l00134"></a><span class="lineno"> 134</span>  <span class="comment">// Initialize tensor of pool1</span></div>
-<div class="line"><a name="l00135"></a><span class="lineno"> 135</span>  <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_pool1 = out_shape_conv1;</div>
-<div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  out_shape_pool1.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a0cb0e1f5da2e1cc2e0ea5690450f53e8">set</a>(0, out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#afb5cd37bb08f1029691590372e6330f0">x</a>() / 2);</div>
-<div class="line"><a name="l00137"></a><span class="lineno"> 137</span>  out_shape_pool1.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a0cb0e1f5da2e1cc2e0ea5690450f53e8">set</a>(1, out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a691c9cb93365c2e33f3429de43244098">y</a>() / 2);</div>
-<div class="line"><a name="l00138"></a><span class="lineno"> 138</span>  out_pool1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_pool1, 1, DataType::F32));</div>
-<div class="line"><a name="l00139"></a><span class="lineno"> 139</span> </div>
-<div class="line"><a name="l00140"></a><span class="lineno"> 140</span>  <span class="comment">// Initialize tensor of fc0</span></div>
-<div class="line"><a name="l00141"></a><span class="lineno"> 141</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> num_labels = 128;</div>
-<div class="line"><a name="l00142"></a><span class="lineno"> 142</span> </div>
-<div class="line"><a name="l00143"></a><span class="lineno"> 143</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> weights_shape_fc0(out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#afb5cd37bb08f1029691590372e6330f0">x</a>() * out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a691c9cb93365c2e33f3429de43244098">y</a>() * out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a336121cb63ed79fa0a072eed03d694ac">z</a>(), num_labels);</div>
-<div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> biases_shape_fc0(num_labels);</div>
-<div class="line"><a name="l00145"></a><span class="lineno"> 145</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_fc0(num_labels);</div>
-<div class="line"><a name="l00146"></a><span class="lineno"> 146</span> </div>
-<div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  weights2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(weights_shape_fc0, 1, DataType::F32));</div>
-<div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  biases2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(biases_shape_fc0, 1, DataType::F32));</div>
-<div class="line"><a name="l00149"></a><span class="lineno"> 149</span>  out_fc0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_fc0, 1, DataType::F32));</div>
-<div class="line"><a name="l00150"></a><span class="lineno"> 150</span> </div>
-<div class="line"><a name="l00151"></a><span class="lineno"> 151</span>  <span class="comment">// Initialize tensor of act2</span></div>
-<div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  out_act2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_fc0, 1, DataType::F32));</div>
-<div class="line"><a name="l00153"></a><span class="lineno"> 153</span> </div>
-<div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  <span class="comment">// Initialize tensor of softmax</span></div>
-<div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_softmax(out_shape_fc0.x());</div>
-<div class="line"><a name="l00156"></a><span class="lineno"> 156</span>  out_softmax.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_softmax, 1, DataType::F32));</div>
-<div class="line"><a name="l00157"></a><span class="lineno"> 157</span> </div>
-<div class="line"><a name="l00158"></a><span class="lineno"> 158</span>  <span class="comment">/* -----------------------End: [Initialize tensors] */</span></div>
-<div class="line"><a name="l00159"></a><span class="lineno"> 159</span> </div>
-<div class="line"><a name="l00160"></a><span class="lineno"> 160</span>  <span class="comment">/* [Configure functions] */</span></div>
-<div class="line"><a name="l00161"></a><span class="lineno"> 161</span> </div>
-<div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  <span class="comment">// in:32x32x1: 5x5 convolution, 8 output features maps (OFM)</span></div>
-<div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  conv0.configure(&src, &weights0, &biases0, &out_conv0, <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a>(1 <span class="comment">/* stride_x */</span>, 1 <span class="comment">/* stride_y */</span>, 2 <span class="comment">/* pad_x */</span>, 2 <span class="comment">/* pad_y */</span>));</div>
-<div class="line"><a name="l00164"></a><span class="lineno"> 164</span> </div>
-<div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  <span class="comment">// in:32x32x8, out:32x32x8, Activation function: relu</span></div>
-<div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  act0.<a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml#adfb5ef37594fc9371c4a2b95e3d5e31b">configure</a>(&out_conv0, &out_act0, <a class="code" href="classarm__compute_1_1_activation_layer_info.xhtml">ActivationLayerInfo</a>(ActivationLayerInfo::ActivationFunction::RELU));</div>
-<div class="line"><a name="l00167"></a><span class="lineno"> 167</span> </div>
-<div class="line"><a name="l00168"></a><span class="lineno"> 168</span>  <span class="comment">// in:32x32x8, out:16x16x8 (2x2 pooling), Pool type function: Max</span></div>
-<div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  pool0.<a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#a6fa6e4b65796fd0bf43da9b4d617d568">configure</a>(&out_act0, &out_pool0, <a class="code" href="classarm__compute_1_1_pooling_layer_info.xhtml">PoolingLayerInfo</a>(PoolingType::MAX, 2, <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a>(2 <span class="comment">/* stride_x */</span>, 2 <span class="comment">/* stride_y */</span>)));</div>
-<div class="line"><a name="l00170"></a><span class="lineno"> 170</span> </div>
-<div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  <span class="comment">// in:16x16x8: 3x3 convolution, 16 output features maps (OFM)</span></div>
-<div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  conv1.configure(&out_pool0, &weights1, &biases1, &out_conv1, <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a>(1 <span class="comment">/* stride_x */</span>, 1 <span class="comment">/* stride_y */</span>, 1 <span class="comment">/* pad_x */</span>, 1 <span class="comment">/* pad_y */</span>));</div>
-<div class="line"><a name="l00173"></a><span class="lineno"> 173</span> </div>
-<div class="line"><a name="l00174"></a><span class="lineno"> 174</span>  <span class="comment">// in:16x16x16, out:16x16x16, Activation function: relu</span></div>
-<div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  act1.<a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml#adfb5ef37594fc9371c4a2b95e3d5e31b">configure</a>(&out_conv1, &out_act1, <a class="code" href="classarm__compute_1_1_activation_layer_info.xhtml">ActivationLayerInfo</a>(ActivationLayerInfo::ActivationFunction::RELU));</div>
-<div class="line"><a name="l00176"></a><span class="lineno"> 176</span> </div>
-<div class="line"><a name="l00177"></a><span class="lineno"> 177</span>  <span class="comment">// in:16x16x16, out:8x8x16 (2x2 pooling), Pool type function: Average</span></div>
-<div class="line"><a name="l00178"></a><span class="lineno"> 178</span>  pool1.<a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#a6fa6e4b65796fd0bf43da9b4d617d568">configure</a>(&out_act1, &out_pool1, <a class="code" href="classarm__compute_1_1_pooling_layer_info.xhtml">PoolingLayerInfo</a>(PoolingType::AVG, 2, <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a>(2 <span class="comment">/* stride_x */</span>, 2 <span class="comment">/* stride_y */</span>)));</div>
-<div class="line"><a name="l00179"></a><span class="lineno"> 179</span> </div>
-<div class="line"><a name="l00180"></a><span class="lineno"> 180</span>  <span class="comment">// in:8x8x16, out:128</span></div>
-<div class="line"><a name="l00181"></a><span class="lineno"> 181</span>  fc0.configure(&out_pool1, &weights2, &biases2, &out_fc0);</div>
-<div class="line"><a name="l00182"></a><span class="lineno"> 182</span> </div>
-<div class="line"><a name="l00183"></a><span class="lineno"> 183</span>  <span class="comment">// in:128, out:128, Activation function: relu</span></div>
-<div class="line"><a name="l00184"></a><span class="lineno"> 184</span>  act2.<a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml#adfb5ef37594fc9371c4a2b95e3d5e31b">configure</a>(&out_fc0, &out_act2, <a class="code" href="classarm__compute_1_1_activation_layer_info.xhtml">ActivationLayerInfo</a>(ActivationLayerInfo::ActivationFunction::RELU));</div>
-<div class="line"><a name="l00185"></a><span class="lineno"> 185</span> </div>
-<div class="line"><a name="l00186"></a><span class="lineno"> 186</span>  <span class="comment">// in:128, out:128</span></div>
-<div class="line"><a name="l00187"></a><span class="lineno"> 187</span>  softmax.configure(&out_act2, &out_softmax);</div>
-<div class="line"><a name="l00188"></a><span class="lineno"> 188</span> </div>
-<div class="line"><a name="l00189"></a><span class="lineno"> 189</span>  <span class="comment">/* -----------------------End: [Configure functions] */</span></div>
-<div class="line"><a name="l00190"></a><span class="lineno"> 190</span> </div>
-<div class="line"><a name="l00191"></a><span class="lineno"> 191</span>  <span class="comment">/*[ Add tensors to memory manager ]*/</span></div>
-<div class="line"><a name="l00192"></a><span class="lineno"> 192</span> </div>
-<div class="line"><a name="l00193"></a><span class="lineno"> 193</span>  <span class="comment">// We need 2 memory groups for handling the input and output</span></div>
-<div class="line"><a name="l00194"></a><span class="lineno"> 194</span>  <span class="comment">// We call explicitly allocate after manage() in order to avoid overlapping lifetimes</span></div>
-<div class="line"><a name="l00195"></a><span class="lineno"> 195</span>  <a class="code" href="classarm__compute_1_1_memory_group_base.xhtml">MemoryGroup</a> memory_group0(mm_transitions);</div>
-<div class="line"><a name="l00196"></a><span class="lineno"> 196</span>  <a class="code" href="classarm__compute_1_1_memory_group_base.xhtml">MemoryGroup</a> memory_group1(mm_transitions);</div>
-<div class="line"><a name="l00197"></a><span class="lineno"> 197</span> </div>
-<div class="line"><a name="l00198"></a><span class="lineno"> 198</span>  memory_group0.manage(&out_conv0);</div>
-<div class="line"><a name="l00199"></a><span class="lineno"> 199</span>  out_conv0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00200"></a><span class="lineno"> 200</span>  memory_group1.manage(&out_act0);</div>
-<div class="line"><a name="l00201"></a><span class="lineno"> 201</span>  out_act0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00202"></a><span class="lineno"> 202</span>  memory_group0.manage(&out_pool0);</div>
-<div class="line"><a name="l00203"></a><span class="lineno"> 203</span>  out_pool0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00204"></a><span class="lineno"> 204</span>  memory_group1.manage(&out_conv1);</div>
-<div class="line"><a name="l00205"></a><span class="lineno"> 205</span>  out_conv1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00206"></a><span class="lineno"> 206</span>  memory_group0.manage(&out_act1);</div>
-<div class="line"><a name="l00207"></a><span class="lineno"> 207</span>  out_act1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00208"></a><span class="lineno"> 208</span>  memory_group1.manage(&out_pool1);</div>
-<div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  out_pool1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00210"></a><span class="lineno"> 210</span>  memory_group0.manage(&out_fc0);</div>
-<div class="line"><a name="l00211"></a><span class="lineno"> 211</span>  out_fc0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00212"></a><span class="lineno"> 212</span>  memory_group1.manage(&out_act2);</div>
-<div class="line"><a name="l00213"></a><span class="lineno"> 213</span>  out_act2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  memory_group0.manage(&out_softmax);</div>
-<div class="line"><a name="l00215"></a><span class="lineno"> 215</span>  out_softmax.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00216"></a><span class="lineno"> 216</span> </div>
-<div class="line"><a name="l00217"></a><span class="lineno"> 217</span>  <span class="comment">/* -----------------------End: [ Add tensors to memory manager ] */</span></div>
-<div class="line"><a name="l00218"></a><span class="lineno"> 218</span> </div>
-<div class="line"><a name="l00219"></a><span class="lineno"> 219</span>  <span class="comment">/* [Allocate tensors] */</span></div>
-<div class="line"><a name="l00220"></a><span class="lineno"> 220</span> </div>
-<div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  <span class="comment">// Now that the padding requirements are known we can allocate all tensors</span></div>
-<div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  src.allocator()->allocate();</div>
-<div class="line"><a name="l00223"></a><span class="lineno"> 223</span>  weights0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  weights1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  weights2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  biases0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00227"></a><span class="lineno"> 227</span>  biases1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  biases2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div>
-<div class="line"><a name="l00229"></a><span class="lineno"> 229</span> </div>
-<div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  <span class="comment">/* -----------------------End: [Allocate tensors] */</span></div>
-<div class="line"><a name="l00231"></a><span class="lineno"> 231</span> </div>
-<div class="line"><a name="l00232"></a><span class="lineno"> 232</span>  <span class="comment">// Finalize layers memory manager</span></div>
-<div class="line"><a name="l00233"></a><span class="lineno"> 233</span> </div>
-<div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  <span class="comment">// Set allocator that the memory manager will use</span></div>
-<div class="line"><a name="l00235"></a><span class="lineno"> 235</span>  mm_layers->set_allocator(&allocator);</div>
-<div class="line"><a name="l00236"></a><span class="lineno"> 236</span> </div>
-<div class="line"><a name="l00237"></a><span class="lineno"> 237</span>  <span class="comment">// Number of pools that the manager will create. This specifies how many layers you want to run in parallel</span></div>
-<div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  mm_layers->set_num_pools(1);</div>
-<div class="line"><a name="l00239"></a><span class="lineno"> 239</span> </div>
-<div class="line"><a name="l00240"></a><span class="lineno"> 240</span>  <span class="comment">// Finalize the manager. (Validity checks, memory allocations etc)</span></div>
-<div class="line"><a name="l00241"></a><span class="lineno"> 241</span>  mm_layers->finalize();</div>
-<div class="line"><a name="l00242"></a><span class="lineno"> 242</span> </div>
-<div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  <span class="comment">// Finalize transitions memory manager</span></div>
-<div class="line"><a name="l00244"></a><span class="lineno"> 244</span> </div>
-<div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  <span class="comment">// Set allocator that the memory manager will use</span></div>
-<div class="line"><a name="l00246"></a><span class="lineno"> 246</span>  mm_transitions->set_allocator(&allocator);</div>
-<div class="line"><a name="l00247"></a><span class="lineno"> 247</span> </div>
-<div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  <span class="comment">// Number of pools that the manager will create. This specifies how many models we can run in parallel.</span></div>
-<div class="line"><a name="l00249"></a><span class="lineno"> 249</span>  <span class="comment">// Setting to 2 as we need one for the input and one for the output at any given time</span></div>
-<div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  mm_transitions->set_num_pools(2);</div>
-<div class="line"><a name="l00251"></a><span class="lineno"> 251</span> </div>
-<div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  <span class="comment">// Finalize the manager. (Validity checks, memory allocations etc)</span></div>
-<div class="line"><a name="l00253"></a><span class="lineno"> 253</span>  mm_transitions->finalize();</div>
-<div class="line"><a name="l00254"></a><span class="lineno"> 254</span> </div>
-<div class="line"><a name="l00255"></a><span class="lineno"> 255</span>  <span class="comment">/* [Initialize weights and biases tensors] */</span></div>
-<div class="line"><a name="l00256"></a><span class="lineno"> 256</span> </div>
-<div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  <span class="comment">// Once the tensors have been allocated, the src, weights and biases tensors can be initialized</span></div>
-<div class="line"><a name="l00258"></a><span class="lineno"> 258</span>  <span class="comment">// ...</span></div>
-<div class="line"><a name="l00259"></a><span class="lineno"> 259</span> </div>
-<div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  <span class="comment">/* -----------------------[Initialize weights and biases tensors] */</span></div>
-<div class="line"><a name="l00261"></a><span class="lineno"> 261</span> </div>
-<div class="line"><a name="l00262"></a><span class="lineno"> 262</span>  <span class="comment">/* [Execute the functions] */</span></div>
-<div class="line"><a name="l00263"></a><span class="lineno"> 263</span> </div>
-<div class="line"><a name="l00264"></a><span class="lineno"> 264</span>  <span class="comment">// Acquire memory for the memory groups</span></div>
-<div class="line"><a name="l00265"></a><span class="lineno"> 265</span>  memory_group0.acquire();</div>
-<div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  memory_group1.acquire();</div>
-<div class="line"><a name="l00267"></a><span class="lineno"> 267</span> </div>
-<div class="line"><a name="l00268"></a><span class="lineno"> 268</span>  conv0.run();</div>
-<div class="line"><a name="l00269"></a><span class="lineno"> 269</span>  act0.<a class="code" href="classarm__compute_1_1_i_n_e_simple_function.xhtml#ab5fd6e96c07aaaed2747c7e16ed5951e">run</a>();</div>
-<div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  pool0.<a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">run</a>();</div>
-<div class="line"><a name="l00271"></a><span class="lineno"> 271</span>  conv1.run();</div>
-<div class="line"><a name="l00272"></a><span class="lineno"> 272</span>  act1.<a class="code" href="classarm__compute_1_1_i_n_e_simple_function.xhtml#ab5fd6e96c07aaaed2747c7e16ed5951e">run</a>();</div>
-<div class="line"><a name="l00273"></a><span class="lineno"> 273</span>  pool1.<a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">run</a>();</div>
-<div class="line"><a name="l00274"></a><span class="lineno"> 274</span>  fc0.run();</div>
-<div class="line"><a name="l00275"></a><span class="lineno"> 275</span>  act2.<a class="code" href="classarm__compute_1_1_i_n_e_simple_function.xhtml#ab5fd6e96c07aaaed2747c7e16ed5951e">run</a>();</div>
-<div class="line"><a name="l00276"></a><span class="lineno"> 276</span>  softmax.run();</div>
-<div class="line"><a name="l00277"></a><span class="lineno"> 277</span> </div>
-<div class="line"><a name="l00278"></a><span class="lineno"> 278</span>  <span class="comment">// Release memory</span></div>
-<div class="line"><a name="l00279"></a><span class="lineno"> 279</span>  memory_group0.release();</div>
-<div class="line"><a name="l00280"></a><span class="lineno"> 280</span>  memory_group1.release();</div>
-<div class="line"><a name="l00281"></a><span class="lineno"> 281</span> </div>
-<div class="line"><a name="l00282"></a><span class="lineno"> 282</span>  <span class="comment">/* -----------------------End: [Execute the functions] */</span></div>
-<div class="line"><a name="l00283"></a><span class="lineno"> 283</span> }</div>
-<div class="ttc" id="classarm__compute_1_1_dimensions_xhtml_a336121cb63ed79fa0a072eed03d694ac"><div class="ttname"><a href="classarm__compute_1_1_dimensions.xhtml#a336121cb63ed79fa0a072eed03d694ac">arm_compute::Dimensions::z</a></div><div class="ttdeci">T z() const </div><div class="ttdoc">Alias to access the size of the third dimension. </div><div class="ttdef"><b>Definition:</b> <a href="_dimensions_8h_source.xhtml#l00091">Dimensions.h:91</a></div></div>
+<div class="fragment"><div class="line"><a name="l00037"></a><span class="lineno"> 37</span> {</div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span>  <a class="code" href="core_2_error_8h.xhtml#a4103adbb45806b2f2002d44b91d0d206">ARM_COMPUTE_UNUSED</a>(argc);</div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span>  <a class="code" href="core_2_error_8h.xhtml#a4103adbb45806b2f2002d44b91d0d206">ARM_COMPUTE_UNUSED</a>(argv);</div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span> </div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span>  <span class="comment">// Create NEON allocator</span></div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span>  <a class="code" href="classarm__compute_1_1_allocator.xhtml">Allocator</a> allocator;</div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> </div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span>  <span class="comment">// Create memory manager components</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span>  <span class="comment">// We need 2 memory managers: 1 for handling the tensors within the functions (mm_layers) and 1 for handling the input and output tensors of the functions (mm_transitions))</span></div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span>  <span class="keyword">auto</span> lifetime_mgr0 = std::make_shared<BlobLifetimeManager>(); <span class="comment">// Create lifetime manager</span></div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  <span class="keyword">auto</span> lifetime_mgr1 = std::make_shared<BlobLifetimeManager>(); <span class="comment">// Create lifetime manager</span></div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span>  <span class="keyword">auto</span> pool_mgr0 = std::make_shared<PoolManager>(); <span class="comment">// Create pool manager</span></div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span>  <span class="keyword">auto</span> pool_mgr1 = std::make_shared<PoolManager>(); <span class="comment">// Create pool manager</span></div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span>  <span class="keyword">auto</span> mm_layers = std::make_shared<MemoryManagerOnDemand>(lifetime_mgr0, pool_mgr0); <span class="comment">// Create the memory manager</span></div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span>  <span class="keyword">auto</span> mm_transitions = std::make_shared<MemoryManagerOnDemand>(lifetime_mgr1, pool_mgr1); <span class="comment">// Create the memory manager</span></div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> </div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span>  <span class="comment">// The src tensor should contain the input image</span></div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> src;</div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span> </div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span>  <span class="comment">// The weights and biases tensors should be initialized with the values inferred with the training</span></div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> weights0;</div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> weights1;</div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> weights2;</div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> biases0;</div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> biases1;</div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> biases2;</div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span> </div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_conv0;</div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_conv1;</div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_act0;</div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_act1;</div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_act2;</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_pool0;</div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_pool1;</div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_fc0;</div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span>  <a class="code" href="classarm__compute_1_1_tensor.xhtml">Tensor</a> out_softmax;</div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span> </div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span>  <span class="comment">// Create layers and set memory manager where allowed to manage internal memory requirements</span></div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  <a class="code" href="classarm__compute_1_1_n_e_convolution_layer.xhtml">NEConvolutionLayer</a> conv0(mm_layers);</div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  <a class="code" href="classarm__compute_1_1_n_e_convolution_layer.xhtml">NEConvolutionLayer</a> conv1(mm_layers);</div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span>  <a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml">NEPoolingLayer</a> pool0;</div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span>  <a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml">NEPoolingLayer</a> pool1;</div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <a class="code" href="classarm__compute_1_1_n_e_fully_connected_layer.xhtml">NEFullyConnectedLayer</a> fc0(mm_layers);</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  <a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml">NEActivationLayer</a> act0;</div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  <a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml">NEActivationLayer</a> act1;</div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  <a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml">NEActivationLayer</a> act2;</div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  <a class="code" href="classarm__compute_1_1_n_e_softmax_layer.xhtml">NESoftmaxLayer</a> softmax(mm_layers);</div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span> </div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  <span class="comment">/* [Initialize tensors] */</span></div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span> </div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  <span class="comment">// Initialize src tensor</span></div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> width_src_image = 32;</div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> height_src_image = 32;</div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> ifm_src_img = 1;</div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span> </div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> src_shape(width_src_image, height_src_image, ifm_src_img);</div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  src.allocator()->init(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(src_shape, 1, DataType::F32));</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">// Initialize tensors of conv0</span></div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kernel_x_conv0 = 5;</div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kernel_y_conv0 = 5;</div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> ofm_conv0 = 8;</div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span> </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_tensor_shape.xhtml">TensorShape</a> weights_shape_conv0(kernel_x_conv0, kernel_y_conv0, src_shape.z(), ofm_conv0);</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_tensor_shape.xhtml">TensorShape</a> biases_shape_conv0(weights_shape_conv0[3]);</div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_conv0(src_shape.x(), src_shape.y(), weights_shape_conv0[3]);</div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span> </div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  weights0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(weights_shape_conv0, 1, DataType::F32));</div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span>  biases0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(biases_shape_conv0, 1, DataType::F32));</div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span>  out_conv0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_conv0, 1, DataType::F32));</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">// Initialize tensor of act0</span></div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span>  out_act0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_conv0, 1, DataType::F32));</div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span> </div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  <span class="comment">// Initialize tensor of pool0</span></div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span>  <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_pool0 = out_shape_conv0;</div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  out_shape_pool0.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a0cb0e1f5da2e1cc2e0ea5690450f53e8">set</a>(0, out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#afb5cd37bb08f1029691590372e6330f0">x</a>() / 2);</div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  out_shape_pool0.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a0cb0e1f5da2e1cc2e0ea5690450f53e8">set</a>(1, out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a691c9cb93365c2e33f3429de43244098">y</a>() / 2);</div><div class="line"><a name="l00115"></a><span class="lineno"> 115</span>  out_pool0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_pool0, 1, DataType::F32));</div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span> </div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span>  <span class="comment">// Initialize tensors of conv1</span></div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kernel_x_conv1 = 3;</div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kernel_y_conv1 = 3;</div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> ofm_conv1 = 16;</div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span> </div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> weights_shape_conv1(kernel_x_conv1, kernel_y_conv1, out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a336121cb63ed79fa0a072eed03d694ac">z</a>(), ofm_conv1);</div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span> </div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> biases_shape_conv1(weights_shape_conv1[3]);</div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_conv1(out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#afb5cd37bb08f1029691590372e6330f0">x</a>(), out_shape_pool0.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a691c9cb93365c2e33f3429de43244098">y</a>(), weights_shape_conv1[3]);</div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span> </div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span>  weights1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(weights_shape_conv1, 1, DataType::F32));</div><div class="line"><a name="l00128"></a><span class="lineno"> 128</span>  biases1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(biases_shape_conv1, 1, DataType::F32));</div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span>  out_conv1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_conv1, 1, DataType::F32));</div><div class="line"><a name="l00130"></a><span class="lineno"> 130</span> </div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  <span class="comment">// Initialize tensor of act1</span></div><div class="line"><a name="l00132"></a><span class="lineno"> 132</span>  out_act1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_conv1, 1, DataType::F32));</div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span> </div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span>  <span class="comment">// Initialize tensor of pool1</span></div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span>  <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_pool1 = out_shape_conv1;</div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  out_shape_pool1.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a0cb0e1f5da2e1cc2e0ea5690450f53e8">set</a>(0, out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#afb5cd37bb08f1029691590372e6330f0">x</a>() / 2);</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span>  out_shape_pool1.<a class="code" href="classarm__compute_1_1_tensor_shape.xhtml#a0cb0e1f5da2e1cc2e0ea5690450f53e8">set</a>(1, out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a691c9cb93365c2e33f3429de43244098">y</a>() / 2);</div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span>  out_pool1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_pool1, 1, DataType::F32));</div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span> </div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span>  <span class="comment">// Initialize tensor of fc0</span></div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span>  constexpr <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> num_labels = 128;</div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span> </div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> weights_shape_fc0(out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#afb5cd37bb08f1029691590372e6330f0">x</a>() * out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a691c9cb93365c2e33f3429de43244098">y</a>() * out_shape_pool1.<a class="code" href="classarm__compute_1_1_dimensions.xhtml#a336121cb63ed79fa0a072eed03d694ac">z</a>(), num_labels);</div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> biases_shape_fc0(num_labels);</div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_fc0(num_labels);</div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span> </div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  weights2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(weights_shape_fc0, 1, DataType::F32));</div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  biases2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(biases_shape_fc0, 1, DataType::F32));</div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span>  out_fc0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_fc0, 1, DataType::F32));</div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span> </div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span>  <span class="comment">// Initialize tensor of act2</span></div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  out_act2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_fc0, 1, DataType::F32));</div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span> </div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  <span class="comment">// Initialize tensor of softmax</span></div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  <span class="keyword">const</span> <a class="code" href="classarm__compute_1_1_tensor_shape.xhtml">TensorShape</a> out_shape_softmax(out_shape_fc0.x());</div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span>  out_softmax.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">init</a>(<a class="code" href="classarm__compute_1_1_tensor_info.xhtml">TensorInfo</a>(out_shape_softmax, 1, DataType::F32));</div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span> </div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span>  <span class="comment">/* -----------------------End: [Initialize tensors] */</span></div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span> </div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span>  <span class="comment">/* [Configure functions] */</span></div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span> </div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  <span class="comment">// in:32x32x1: 5x5 convolution, 8 output features maps (OFM)</span></div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  conv0.configure(&src, &weights0, &biases0, &out_conv0, <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a>(1 <span class="comment">/* stride_x */</span>, 1 <span class="comment">/* stride_y */</span>, 2 <span class="comment">/* pad_x */</span>, 2 <span class="comment">/* pad_y */</span>));</div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span> </div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  <span class="comment">// in:32x32x8, out:32x32x8, Activation function: relu</span></div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  act0.<a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml#adfb5ef37594fc9371c4a2b95e3d5e31b">configure</a>(&out_conv0, &out_act0, <a class="code" href="classarm__compute_1_1_activation_layer_info.xhtml">ActivationLayerInfo</a>(ActivationLayerInfo::ActivationFunction::RELU));</div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span> </div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span>  <span class="comment">// in:32x32x8, out:16x16x8 (2x2 pooling), Pool type function: Max</span></div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  pool0.<a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#a6fa6e4b65796fd0bf43da9b4d617d568">configure</a>(&out_act0, &out_pool0, <a class="code" href="classarm__compute_1_1_pooling_layer_info.xhtml">PoolingLayerInfo</a>(PoolingType::MAX, 2, <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a>(2 <span class="comment">/* stride_x */</span>, 2 <span class="comment">/* stride_y */</span>)));</div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span> </div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  <span class="comment">// in:16x16x8: 3x3 convolution, 16 output features maps (OFM)</span></div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  conv1.configure(&out_pool0, &weights1, &biases1, &out_conv1, <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a>(1 <span class="comment">/* stride_x */</span>, 1 <span class="comment">/* stride_y */</span>, 1 <span class="comment">/* pad_x */</span>, 1 <span class="comment">/* pad_y */</span>));</div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span> </div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span>  <span class="comment">// in:16x16x16, out:16x16x16, Activation function: relu</span></div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  act1.<a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml#adfb5ef37594fc9371c4a2b95e3d5e31b">configure</a>(&out_conv1, &out_act1, <a class="code" href="classarm__compute_1_1_activation_layer_info.xhtml">ActivationLayerInfo</a>(ActivationLayerInfo::ActivationFunction::RELU));</div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span> </div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span>  <span class="comment">// in:16x16x16, out:8x8x16 (2x2 pooling), Pool type function: Average</span></div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span>  pool1.<a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#a6fa6e4b65796fd0bf43da9b4d617d568">configure</a>(&out_act1, &out_pool1, <a class="code" href="classarm__compute_1_1_pooling_layer_info.xhtml">PoolingLayerInfo</a>(PoolingType::AVG, 2, <a class="code" href="classarm__compute_1_1_pad_stride_info.xhtml">PadStrideInfo</a>(2 <span class="comment">/* stride_x */</span>, 2 <span class="comment">/* stride_y */</span>)));</div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span> </div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span>  <span class="comment">// in:8x8x16, out:128</span></div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span>  fc0.configure(&out_pool1, &weights2, &biases2, &out_fc0);</div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span> </div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span>  <span class="comment">// in:128, out:128, Activation function: relu</span></div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span>  act2.<a class="code" href="classarm__compute_1_1_n_e_activation_layer.xhtml#adfb5ef37594fc9371c4a2b95e3d5e31b">configure</a>(&out_fc0, &out_act2, <a class="code" href="classarm__compute_1_1_activation_layer_info.xhtml">ActivationLayerInfo</a>(ActivationLayerInfo::ActivationFunction::RELU));</div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span> </div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span>  <span class="comment">// in:128, out:128</span></div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span>  softmax.configure(&out_act2, &out_softmax);</div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span> </div><div class="line"><a name="l00189"></a><span class="lineno"> 189</span>  <span class="comment">/* -----------------------End: [Configure functions] */</span></div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span> </div><div class="line"><a name="l00191"></a><span class="lineno"> 191</span>  <span class="comment">/*[ Add tensors to memory manager ]*/</span></div><div class="line"><a name="l00192"></a><span class="lineno"> 192</span> </div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span>  <span class="comment">// We need 2 memory groups for handling the input and output</span></div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span>  <span class="comment">// We call explicitly allocate after manage() in order to avoid overlapping lifetimes</span></div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span>  <a class="code" href="classarm__compute_1_1_memory_group_base.xhtml">MemoryGroup</a> memory_group0(mm_transitions);</div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span>  <a class="code" href="classarm__compute_1_1_memory_group_base.xhtml">MemoryGroup</a> memory_group1(mm_transitions);</div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span> </div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span>  memory_group0.manage(&out_conv0);</div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span>  out_conv0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span>  memory_group1.manage(&out_act0);</div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span>  out_act0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span>  memory_group0.manage(&out_pool0);</div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span>  out_pool0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span>  memory_group1.manage(&out_conv1);</div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span>  out_conv1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span>  memory_group0.manage(&out_act1);</div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span>  out_act1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span>  memory_group1.manage(&out_pool1);</div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  out_pool1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span>  memory_group0.manage(&out_fc0);</div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span>  out_fc0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span>  memory_group1.manage(&out_act2);</div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span>  out_act2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  memory_group0.manage(&out_softmax);</div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span>  out_softmax.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span> </div><div class="line"><a name="l00217"></a><span class="lineno"> 217</span>  <span class="comment">/* -----------------------End: [ Add tensors to memory manager ] */</span></div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span> </div><div class="line"><a name="l00219"></a><span class="lineno"> 219</span>  <span class="comment">/* [Allocate tensors] */</span></div><div class="line"><a name="l00220"></a><span class="lineno"> 220</span> </div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  <span class="comment">// Now that the padding requirements are known we can allocate all tensors</span></div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  src.allocator()->allocate();</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span>  weights0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  weights1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  weights2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  biases0.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span>  biases1.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  biases2.<a class="code" href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">allocator</a>()-><a class="code" href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">allocate</a>();</div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span> </div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  <span class="comment">/* -----------------------End: [Allocate tensors] */</span></div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span> </div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span>  <span class="comment">// Finalize layers memory manager</span></div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span> </div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  <span class="comment">// Set allocator that the memory manager will use</span></div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span>  mm_layers->set_allocator(&allocator);</div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span> </div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span>  <span class="comment">// Number of pools that the manager will create. This specifies how many layers you want to run in parallel</span></div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  mm_layers->set_num_pools(1);</div><div class="line"><a name="l00239"></a><span class="lineno"> 239</span> </div><div class="line"><a name="l00240"></a><span class="lineno"> 240</span>  <span class="comment">// Finalize the manager. (Validity checks, memory allocations etc)</span></div><div class="line"><a name="l00241"></a><span class="lineno"> 241</span>  mm_layers->finalize();</div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span> </div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  <span class="comment">// Finalize transitions memory manager</span></div><div class="line"><a name="l00244"></a><span class="lineno"> 244</span> </div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  <span class="comment">// Set allocator that the memory manager will use</span></div><div class="line"><a name="l00246"></a><span class="lineno"> 246</span>  mm_transitions->set_allocator(&allocator);</div><div class="line"><a name="l00247"></a><span class="lineno"> 247</span> </div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  <span class="comment">// Number of pools that the manager will create. This specifies how many models we can run in parallel.</span></div><div class="line"><a name="l00249"></a><span class="lineno"> 249</span>  <span class="comment">// Setting to 2 as we need one for the input and one for the output at any given time</span></div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  mm_transitions->set_num_pools(2);</div><div class="line"><a name="l00251"></a><span class="lineno"> 251</span> </div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  <span class="comment">// Finalize the manager. (Validity checks, memory allocations etc)</span></div><div class="line"><a name="l00253"></a><span class="lineno"> 253</span>  mm_transitions->finalize();</div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span> </div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span>  <span class="comment">/* [Initialize weights and biases tensors] */</span></div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span> </div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  <span class="comment">// Once the tensors have been allocated, the src, weights and biases tensors can be initialized</span></div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span>  <span class="comment">// ...</span></div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span> </div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  <span class="comment">/* -----------------------[Initialize weights and biases tensors] */</span></div><div class="line"><a name="l00261"></a><span class="lineno"> 261</span> </div><div class="line"><a name="l00262"></a><span class="lineno"> 262</span>  <span class="comment">/* [Execute the functions] */</span></div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span> </div><div class="line"><a name="l00264"></a><span class="lineno"> 264</span>  <span class="comment">// Acquire memory for the memory groups</span></div><div class="line"><a name="l00265"></a><span class="lineno"> 265</span>  memory_group0.acquire();</div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  memory_group1.acquire();</div><div class="line"><a name="l00267"></a><span class="lineno"> 267</span> </div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span>  conv0.run();</div><div class="line"><a name="l00269"></a><span class="lineno"> 269</span>  act0.<a class="code" href="classarm__compute_1_1_i_n_e_simple_function.xhtml#ab5fd6e96c07aaaed2747c7e16ed5951e">run</a>();</div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  pool0.<a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">run</a>();</div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span>  conv1.run();</div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span>  act1.<a class="code" href="classarm__compute_1_1_i_n_e_simple_function.xhtml#ab5fd6e96c07aaaed2747c7e16ed5951e">run</a>();</div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span>  pool1.<a class="code" href="classarm__compute_1_1_n_e_pooling_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">run</a>();</div><div class="line"><a name="l00274"></a><span class="lineno"> 274</span>  fc0.run();</div><div class="line"><a name="l00275"></a><span class="lineno"> 275</span>  act2.<a class="code" href="classarm__compute_1_1_i_n_e_simple_function.xhtml#ab5fd6e96c07aaaed2747c7e16ed5951e">run</a>();</div><div class="line"><a name="l00276"></a><span class="lineno"> 276</span>  softmax.run();</div><div class="line"><a name="l00277"></a><span class="lineno"> 277</span> </div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span>  <span class="comment">// Release memory</span></div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span>  memory_group0.release();</div><div class="line"><a name="l00280"></a><span class="lineno"> 280</span>  memory_group1.release();</div><div class="line"><a name="l00281"></a><span class="lineno"> 281</span> </div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span>  <span class="comment">/* -----------------------End: [Execute the functions] */</span></div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span> }</div><div class="ttc" id="classarm__compute_1_1_dimensions_xhtml_a336121cb63ed79fa0a072eed03d694ac"><div class="ttname"><a href="classarm__compute_1_1_dimensions.xhtml#a336121cb63ed79fa0a072eed03d694ac">arm_compute::Dimensions::z</a></div><div class="ttdeci">T z() const </div><div class="ttdoc">Alias to access the size of the third dimension. </div><div class="ttdef"><b>Definition:</b> <a href="_dimensions_8h_source.xhtml#l00091">Dimensions.h:91</a></div></div>
<div class="ttc" id="classarm__compute_1_1_tensor_shape_xhtml"><div class="ttname"><a href="classarm__compute_1_1_tensor_shape.xhtml">arm_compute::TensorShape</a></div><div class="ttdoc">Shape of a tensor. </div><div class="ttdef"><b>Definition:</b> <a href="_tensor_shape_8h_source.xhtml#l00038">TensorShape.h:38</a></div></div>
-<div class="ttc" id="_error_8h_xhtml_a4103adbb45806b2f2002d44b91d0d206"><div class="ttname"><a href="_error_8h.xhtml#a4103adbb45806b2f2002d44b91d0d206">ARM_COMPUTE_UNUSED</a></div><div class="ttdeci">#define ARM_COMPUTE_UNUSED(var)</div><div class="ttdoc">To avoid unused variables warnings. </div><div class="ttdef"><b>Definition:</b> <a href="_error_8h_source.xhtml#l00049">Error.h:49</a></div></div>
-<div class="ttc" id="classarm__compute_1_1_activation_layer_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_activation_layer_info.xhtml">arm_compute::ActivationLayerInfo</a></div><div class="ttdoc">Activation Layer Information class. </div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l00511">Types.h:511</a></div></div>
+<div class="ttc" id="classarm__compute_1_1_activation_layer_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_activation_layer_info.xhtml">arm_compute::ActivationLayerInfo</a></div><div class="ttdoc">Activation Layer Information class. </div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l00650">Types.h:650</a></div></div>
+<div class="ttc" id="core_2_error_8h_xhtml_a4103adbb45806b2f2002d44b91d0d206"><div class="ttname"><a href="core_2_error_8h.xhtml#a4103adbb45806b2f2002d44b91d0d206">ARM_COMPUTE_UNUSED</a></div><div class="ttdeci">#define ARM_COMPUTE_UNUSED(var)</div><div class="ttdoc">To avoid unused variables warnings. </div><div class="ttdef"><b>Definition:</b> <a href="core_2_error_8h_source.xhtml#l00147">Error.h:147</a></div></div>
<div class="ttc" id="classarm__compute_1_1_n_e_softmax_layer_xhtml"><div class="ttname"><a href="classarm__compute_1_1_n_e_softmax_layer.xhtml">arm_compute::NESoftmaxLayer</a></div><div class="ttdoc">Basic function to compute a SoftmaxLayer. </div><div class="ttdef"><b>Definition:</b> <a href="_n_e_softmax_layer_8h_source.xhtml#l00047">NESoftmaxLayer.h:47</a></div></div>
-<div class="ttc" id="classarm__compute_1_1_tensor_xhtml_a531ec877bfc923dea3ab6f1be5e6e1ac"><div class="ttname"><a href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">arm_compute::Tensor::allocator</a></div><div class="ttdeci">TensorAllocator * allocator()</div><div class="ttdoc">Return a pointer to the tensor's allocator. </div></div>
+<div class="ttc" id="classarm__compute_1_1_tensor_xhtml_a531ec877bfc923dea3ab6f1be5e6e1ac"><div class="ttname"><a href="classarm__compute_1_1_tensor.xhtml#a531ec877bfc923dea3ab6f1be5e6e1ac">arm_compute::Tensor::allocator</a></div><div class="ttdeci">TensorAllocator * allocator()</div><div class="ttdoc">Return a pointer to the tensor&#39;s allocator. </div></div>
<div class="ttc" id="classarm__compute_1_1_dimensions_xhtml_afb5cd37bb08f1029691590372e6330f0"><div class="ttname"><a href="classarm__compute_1_1_dimensions.xhtml#afb5cd37bb08f1029691590372e6330f0">arm_compute::Dimensions::x</a></div><div class="ttdeci">T x() const </div><div class="ttdoc">Alias to access the size of the first dimension. </div><div class="ttdef"><b>Definition:</b> <a href="_dimensions_8h_source.xhtml#l00081">Dimensions.h:81</a></div></div>
<div class="ttc" id="classarm__compute_1_1_n_e_pooling_layer_xhtml_ad1717410afd0be936c6213a63c8005fb"><div class="ttname"><a href="classarm__compute_1_1_n_e_pooling_layer.xhtml#ad1717410afd0be936c6213a63c8005fb">arm_compute::NEPoolingLayer::run</a></div><div class="ttdeci">void run() override</div><div class="ttdoc">Run the kernels contained in the function. </div></div>
<div class="ttc" id="classarm__compute_1_1_n_e_convolution_layer_xhtml"><div class="ttname"><a href="classarm__compute_1_1_n_e_convolution_layer.xhtml">arm_compute::NEConvolutionLayer</a></div><div class="ttdoc">Basic function to simulate a convolution layer. </div><div class="ttdef"><b>Definition:</b> <a href="_n_e_convolution_layer_8h_source.xhtml#l00084">NEConvolutionLayer.h:84</a></div></div>
<div class="ttc" id="classarm__compute_1_1_tensor_allocator_xhtml_a6e509c2a177b0b29e9e2369535094dee"><div class="ttname"><a href="classarm__compute_1_1_tensor_allocator.xhtml#a6e509c2a177b0b29e9e2369535094dee">arm_compute::TensorAllocator::allocate</a></div><div class="ttdeci">void allocate() override</div><div class="ttdoc">Allocate size specified by TensorInfo of CPU memory. </div></div>
<div class="ttc" id="classarm__compute_1_1_tensor_xhtml"><div class="ttname"><a href="classarm__compute_1_1_tensor.xhtml">arm_compute::Tensor</a></div><div class="ttdoc">Basic implementation of the tensor interface. </div><div class="ttdef"><b>Definition:</b> <a href="runtime_2_tensor_8h_source.xhtml#l00037">Tensor.h:37</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#l00406">Types.h:406</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#l00460">Types.h:460</a></div></div>
<div class="ttc" id="classarm__compute_1_1_tensor_shape_xhtml_a0cb0e1f5da2e1cc2e0ea5690450f53e8"><div class="ttname"><a href="classarm__compute_1_1_tensor_shape.xhtml#a0cb0e1f5da2e1cc2e0ea5690450f53e8">arm_compute::TensorShape::set</a></div><div class="ttdeci">void set(size_t dimension, size_t value)</div><div class="ttdoc">Accessor to set the value of one of the dimensions. </div><div class="ttdef"><b>Definition:</b> <a href="_tensor_shape_8h_source.xhtml#l00074">TensorShape.h:74</a></div></div>
<div class="ttc" id="classarm__compute_1_1_n_e_activation_layer_xhtml"><div class="ttname"><a href="classarm__compute_1_1_n_e_activation_layer.xhtml">arm_compute::NEActivationLayer</a></div><div class="ttdoc">Basic function to run NEActivationLayerKernel. </div><div class="ttdef"><b>Definition:</b> <a href="_n_e_activation_layer_8h_source.xhtml#l00039">NEActivationLayer.h:39</a></div></div>
<div class="ttc" id="classarm__compute_1_1_n_e_fully_connected_layer_xhtml"><div class="ttname"><a href="classarm__compute_1_1_n_e_fully_connected_layer.xhtml">arm_compute::NEFullyConnectedLayer</a></div><div class="ttdoc">Basic function to compute a Fully Connected layer on NEON. </div><div class="ttdef"><b>Definition:</b> <a href="_n_e_fully_connected_layer_8h_source.xhtml#l00082">NEFullyConnectedLayer.h:82</a></div></div>
@@ -480,8 +233,8 @@
<div class="ttc" id="classarm__compute_1_1_n_e_pooling_layer_xhtml"><div class="ttname"><a href="classarm__compute_1_1_n_e_pooling_layer.xhtml">arm_compute::NEPoolingLayer</a></div><div class="ttdoc">Basic function to simulate a pooling layer with the specified pooling operation. </div><div class="ttdef"><b>Definition:</b> <a href="_n_e_pooling_layer_8h_source.xhtml#l00042">NEPoolingLayer.h:42</a></div></div>
<div class="ttc" id="classarm__compute_1_1_allocator_xhtml"><div class="ttname"><a href="classarm__compute_1_1_allocator.xhtml">arm_compute::Allocator</a></div><div class="ttdoc">Default malloc allocator implementation. </div><div class="ttdef"><b>Definition:</b> <a href="_allocator_8h_source.xhtml#l00034">Allocator.h:34</a></div></div>
<div class="ttc" id="classarm__compute_1_1_tensor_allocator_xhtml_a3014ce2f4215e8a44331aa5daf3ba0d4"><div class="ttname"><a href="classarm__compute_1_1_tensor_allocator.xhtml#a3014ce2f4215e8a44331aa5daf3ba0d4">arm_compute::TensorAllocator::init</a></div><div class="ttdeci">void init(const TensorAllocator &allocator, const Coordinates &coords, TensorInfo sub_info)</div><div class="ttdoc">Shares the same backing memory with another tensor allocator, while the tensor info might be differen...</div></div>
-<div class="ttc" id="classarm__compute_1_1_tensor_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_tensor_info.xhtml">arm_compute::TensorInfo</a></div><div class="ttdoc">Store the tensor's metadata. </div><div class="ttdef"><b>Definition:</b> <a href="_tensor_info_8h_source.xhtml#l00042">TensorInfo.h:42</a></div></div>
-<div class="ttc" id="classarm__compute_1_1_pooling_layer_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_pooling_layer_info.xhtml">arm_compute::PoolingLayerInfo</a></div><div class="ttdoc">Pooling Layer Information class. </div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l00445">Types.h:445</a></div></div>
+<div class="ttc" id="classarm__compute_1_1_tensor_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_tensor_info.xhtml">arm_compute::TensorInfo</a></div><div class="ttdoc">Store the tensor&#39;s metadata. </div><div class="ttdef"><b>Definition:</b> <a href="_tensor_info_8h_source.xhtml#l00044">TensorInfo.h:44</a></div></div>
+<div class="ttc" id="classarm__compute_1_1_pooling_layer_info_xhtml"><div class="ttname"><a href="classarm__compute_1_1_pooling_layer_info.xhtml">arm_compute::PoolingLayerInfo</a></div><div class="ttdoc">Pooling Layer Information class. </div><div class="ttdef"><b>Definition:</b> <a href="arm__compute_2core_2_types_8h_source.xhtml#l00553">Types.h:553</a></div></div>
</div><!-- fragment -->
</div>
</div>
@@ -490,10 +243,10 @@
<!-- start footer part -->
<div id="nav-path" class="navpath"><!-- id is needed for treeview function! -->
<ul>
- <li class="navelem"><a class="el" href="dir_1253bad92dedae5edd993ead924afb7b.xhtml">examples</a></li><li class="navelem"><a class="el" href="neon__cnn_8cpp.xhtml">neon_cnn.cpp</a></li>
- <li class="footer">Generated on Thu Oct 12 2017 14:26:35 for Compute Library by
+ <li class="navelem"><a class="el" href="dir_d28a4824dc47e487b107a5db32ef43c4.xhtml">examples</a></li><li class="navelem"><a class="el" href="neon__cnn_8cpp.xhtml">neon_cnn.cpp</a></li>
+ <li class="footer">Generated on Thu Dec 14 2017 23:48:33 for Compute Library by
<a href="http://www.doxygen.org/index.html">
- <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.6 </li>
+ <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.11 </li>
</ul>
</div>
</body>