| <a href="_const_tensor_layer_visitor_8cpp.xhtml">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">//</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment">// Copyright © 2017 Arm Ltd. All rights reserved.</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment">// SPDX-License-Identifier: MIT</span></div><div class="line"><a name="l00004"></a><span class="lineno"> 4</span> <span class="comment">//</span></div><div class="line"><a name="l00005"></a><span class="lineno"> 5</span> </div><div class="line"><a name="l00006"></a><span class="lineno"> 6</span> <span class="preprocessor">#include "<a class="code" href="_const_tensor_layer_visitor_8hpp.xhtml">ConstTensorLayerVisitor.hpp</a>"</span></div><div class="line"><a name="l00007"></a><span class="lineno"> 7</span> <span class="preprocessor">#include "<a class="code" href="_network_8hpp.xhtml">Network.hpp</a>"</span></div><div class="line"><a name="l00008"></a><span class="lineno"> 8</span> </div><div class="line"><a name="l00009"></a><span class="lineno"> 9</span> <span class="preprocessor">#include <boost/test/unit_test.hpp></span></div><div class="line"><a name="l00010"></a><span class="lineno"> 10</span> </div><div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="keyword">namespace </span><a class="code" href="namespacearmnn.xhtml">armnn</a></div><div class="line"><a name="l00012"></a><span class="lineno"> 12</span> {</div><div class="line"><a name="l00013"></a><span class="lineno"> 13</span> </div><div class="line"><a name="l00014"></a><span class="lineno"><a class="line" href="classarmnn_1_1_test_convolution2d_layer_visitor.xhtml#ac8b078bb166c52b45f04cae3e74557ad"> 14</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_test_convolution2d_layer_visitor.xhtml#ac8b078bb166c52b45f04cae3e74557ad">TestConvolution2dLayerVisitor::CheckDescriptor</a>(<span class="keyword">const</span> <a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml">Convolution2dDescriptor</a> &convolution2dDescriptor)</div><div class="line"><a name="l00015"></a><span class="lineno"> 15</span> {</div><div class="line"><a name="l00016"></a><span class="lineno"> 16</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a>);</div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a>);</div><div class="line"><a name="l00018"></a><span class="lineno"> 18</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a>);</div><div class="line"><a name="l00019"></a><span class="lineno"> 19</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a>);</div><div class="line"><a name="l00020"></a><span class="lineno"> 20</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a>);</div><div class="line"><a name="l00021"></a><span class="lineno"> 21</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a>);</div><div class="line"><a name="l00022"></a><span class="lineno"> 22</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a>);</div><div class="line"><a name="l00023"></a><span class="lineno"> 23</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a>);</div><div class="line"><a name="l00024"></a><span class="lineno"> 24</span> }</div><div class="line"><a name="l00025"></a><span class="lineno"> 25</span> </div><div class="line"><a name="l00026"></a><span class="lineno"><a class="line" href="classarmnn_1_1_test_depthwise_convolution2d_layer_visitor.xhtml#a8498083056c114343a16c556beea6057"> 26</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_test_depthwise_convolution2d_layer_visitor.xhtml#a8498083056c114343a16c556beea6057">TestDepthwiseConvolution2dLayerVisitor::CheckDescriptor</a>(</div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span>  <span class="keyword">const</span> <a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml">DepthwiseConvolution2dDescriptor</a>& convolution2dDescriptor)</div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> {</div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a>);</div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a>);</div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a>);</div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a>);</div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a>);</div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a>);</div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a>);</div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> == convolution2dDescriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a>);</div><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> </div><div class="line"><a name="l00039"></a><span class="lineno"><a class="line" href="classarmnn_1_1_test_fully_connected_layer_vistor.xhtml#ae48eafaa6a4bc4b7bde0a8824797c350"> 39</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_test_fully_connected_layer_vistor.xhtml#ae48eafaa6a4bc4b7bde0a8824797c350">TestFullyConnectedLayerVistor::CheckDescriptor</a>(<span class="keyword">const</span> <a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml">FullyConnectedDescriptor</a>& descriptor)</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>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a> == descriptor.<a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a>);</div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.m_TransposeWeightMatrix == descriptor.<a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml#a281fcaec86e17c97f7b8402633f6b55a">m_TransposeWeightMatrix</a>);</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> </div><div class="line"><a name="l00045"></a><span class="lineno"><a class="line" href="classarmnn_1_1_test_batch_normalization_layer_visitor.xhtml#abb0d5c2c24fc8c43d01e0fe503df2e93"> 45</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_test_batch_normalization_layer_visitor.xhtml#abb0d5c2c24fc8c43d01e0fe503df2e93">TestBatchNormalizationLayerVisitor::CheckDescriptor</a>(<span class="keyword">const</span> <a class="code" href="structarmnn_1_1_batch_normalization_descriptor.xhtml">BatchNormalizationDescriptor</a>& descriptor)</div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span> {</div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.m_Eps == descriptor.<a class="code" href="structarmnn_1_1_batch_normalization_descriptor.xhtml#a11c821c7524251004a72ed13c510853c">m_Eps</a>);</div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> == descriptor.<a class="code" href="structarmnn_1_1_batch_normalization_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a>);</div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span> }</div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span> </div><div class="line"><a name="l00051"></a><span class="lineno"><a class="line" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml#a7f36acbe9f04ed87e4bc8529f7ec0391"> 51</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml#a7f36acbe9f04ed87e4bc8529f7ec0391">TestLstmLayerVisitor::CheckDescriptor</a>(<span class="keyword">const</span> <a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml">LstmDescriptor</a>& descriptor)</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>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.m_ActivationFunc == descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ae1b07ed928036004bd257169e5aeeef4">m_ActivationFunc</a>);</div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.m_ClippingThresCell == descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a531a3907ec13d3772370da88030191a5">m_ClippingThresCell</a>);</div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.m_ClippingThresProj == descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a86e88bef0df4df96df752b4b8955a3af">m_ClippingThresProj</a>);</div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.m_CifgEnabled == descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ad474e5c51a0b194ef32e812b86c0cbdb">m_CifgEnabled</a>);</div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.m_PeepholeEnabled == descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a2837b4396f20c956952d1a7286cab5f8">m_PeepholeEnabled</a>);</div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span>  <a class="code" href="_file_only_profiling_decorator_tests_8cpp.xhtml#a0c262ba6f6c189a2d092d127c1b7627b">BOOST_CHECK</a>(m_Descriptor.m_ProjectionEnabled == descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a6c9de81fc65b3c4924cab11907075a17">m_ProjectionEnabled</a>);</div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span> }</div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span> </div><div class="line"><a name="l00061"></a><span class="lineno"><a class="line" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml#ac45b7720c3156ab1004a904da7d42b44"> 61</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml#ac45b7720c3156ab1004a904da7d42b44">TestLstmLayerVisitor::CheckConstTensorPtrs</a>(<span class="keyword">const</span> std::string& name,</div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a>* expected,</div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a>* actual)</div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span> {</div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span>  <span class="keywordflow">if</span> (expected == <span class="keyword">nullptr</span>)</div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span>  {</div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span>  BOOST_CHECK_MESSAGE(actual == <span class="keyword">nullptr</span>, name + <span class="stringliteral">" actual should have been a nullptr"</span>);</div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  }</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span>  <span class="keywordflow">else</span></div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  {</div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  BOOST_CHECK_MESSAGE(actual != <span class="keyword">nullptr</span>, name + <span class="stringliteral">" actual should have been set"</span>);</div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span>  <span class="keywordflow">if</span> (actual != <span class="keyword">nullptr</span>)</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>  <a class="code" href="classarmnn_1_1_test_layer_visitor.xhtml#ab49c9a185af94e39ae9cd81aa8ec926c">CheckConstTensors</a>(*expected, *actual);</div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  }</div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  }</div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span> }</div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span> </div><div class="line"><a name="l00079"></a><span class="lineno"><a class="line" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml#a7607350d75bcb2ac402bba7494585f33"> 79</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml#a7607350d75bcb2ac402bba7494585f33">TestLstmLayerVisitor::CheckInputParameters</a>(<span class="keyword">const</span> <a class="code" href="structarmnn_1_1_lstm_input_params.xhtml">LstmInputParams</a>& inputParams)</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span> {</div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  CheckConstTensorPtrs(<span class="stringliteral">"ProjectionBias"</span>, m_InputParams.m_ProjectionBias, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a44b0e6b16708df7f0d2bbab141688aaa">m_ProjectionBias</a>);</div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  CheckConstTensorPtrs(<span class="stringliteral">"ProjectionWeights"</span>, m_InputParams.m_ProjectionWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ab03e6e1514f74427916c892f473fe04c">m_ProjectionWeights</a>);</div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  CheckConstTensorPtrs(<span class="stringliteral">"OutputGateBias"</span>, m_InputParams.m_OutputGateBias, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a>);</div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  CheckConstTensorPtrs(<span class="stringliteral">"InputToInputWeights"</span>,</div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  m_InputParams.m_InputToInputWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#affcee5f4ab5994a21bee3b78b4e43de3">m_InputToInputWeights</a>);</div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span>  CheckConstTensorPtrs(<span class="stringliteral">"InputToForgetWeights"</span>,</div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  m_InputParams.m_InputToForgetWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a>);</div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  CheckConstTensorPtrs(<span class="stringliteral">"InputToCellWeights"</span>, m_InputParams.m_InputToCellWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a>);</div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  CheckConstTensorPtrs(</div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  <span class="stringliteral">"InputToOutputWeights"</span>, m_InputParams.m_InputToOutputWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a>);</div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span>  CheckConstTensorPtrs(</div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  <span class="stringliteral">"RecurrentToInputWeights"</span>, m_InputParams.m_RecurrentToInputWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a435d3651482bbfcc11263b4e4e0c900f">m_RecurrentToInputWeights</a>);</div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  CheckConstTensorPtrs(</div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span>  <span class="stringliteral">"RecurrentToForgetWeights"</span>, m_InputParams.m_RecurrentToForgetWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a>);</div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  CheckConstTensorPtrs(</div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  <span class="stringliteral">"RecurrentToCellWeights"</span>, m_InputParams.m_RecurrentToCellWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a>);</div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  CheckConstTensorPtrs(</div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  <span class="stringliteral">"RecurrentToOutputWeights"</span>, m_InputParams.m_RecurrentToOutputWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a>);</div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span>  CheckConstTensorPtrs(</div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span>  <span class="stringliteral">"CellToInputWeights"</span>, m_InputParams.m_CellToInputWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a484bafa2f8453a7c5a4a00b92a61b006">m_CellToInputWeights</a>);</div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span>  CheckConstTensorPtrs(</div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  <span class="stringliteral">"CellToForgetWeights"</span>, m_InputParams.m_CellToForgetWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a35b112e30c3eb153806a2a8c16d178e3">m_CellToForgetWeights</a>);</div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span>  CheckConstTensorPtrs(</div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  <span class="stringliteral">"CellToOutputWeights"</span>, m_InputParams.m_CellToOutputWeights, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#afe204ca375b74e9a72640c9227918d0a">m_CellToOutputWeights</a>);</div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span>  CheckConstTensorPtrs(<span class="stringliteral">"InputGateBias"</span>, m_InputParams.m_InputGateBias, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a9e081a9b94defb30d1558dc912507e0e">m_InputGateBias</a>);</div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span>  CheckConstTensorPtrs(<span class="stringliteral">"ForgetGateBias"</span>, m_InputParams.m_ForgetGateBias, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a>);</div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span>  CheckConstTensorPtrs(<span class="stringliteral">"CellBias"</span>, m_InputParams.m_CellBias, inputParams.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a>);</div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span> }</div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span> </div><div class="line"><a name="l00110"></a><span class="lineno"><a class="line" href="classarmnn_1_1_test_quantized_lstm_layer_visitor.xhtml#ac45b7720c3156ab1004a904da7d42b44"> 110</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_test_quantized_lstm_layer_visitor.xhtml#ac45b7720c3156ab1004a904da7d42b44">TestQuantizedLstmLayerVisitor::CheckConstTensorPtrs</a>(<span class="keyword">const</span> std::string& name,</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a>* expected,</div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span>  <span class="keyword">const</span> <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a>* actual)</div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span> {</div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  <span class="keywordflow">if</span> (expected == <span class="keyword">nullptr</span>)</div><div class="line"><a name="l00115"></a><span class="lineno"> 115</span>  {</div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span>  BOOST_CHECK_MESSAGE(actual == <span class="keyword">nullptr</span>, name + <span class="stringliteral">" actual should have been a nullptr"</span>);</div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span>  }</div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span>  <span class="keywordflow">else</span></div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span>  {</div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span>  BOOST_CHECK_MESSAGE(actual != <span class="keyword">nullptr</span>, name + <span class="stringliteral">" actual should have been set"</span>);</div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span>  <span class="keywordflow">if</span> (actual != <span class="keyword">nullptr</span>)</div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span>  {</div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  <a class="code" href="classarmnn_1_1_test_layer_visitor.xhtml#ab49c9a185af94e39ae9cd81aa8ec926c">CheckConstTensors</a>(*expected, *actual);</div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  }</div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span>  }</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> </div><div class="line"><a name="l00128"></a><span class="lineno"><a class="line" href="classarmnn_1_1_test_quantized_lstm_layer_visitor.xhtml#ac6627007bd7a0b3a00cc690307840039"> 128</a></span> <span class="keywordtype">void</span> <a class="code" href="classarmnn_1_1_test_quantized_lstm_layer_visitor.xhtml#ac6627007bd7a0b3a00cc690307840039">TestQuantizedLstmLayerVisitor::CheckInputParameters</a>(<span class="keyword">const</span> <a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml">QuantizedLstmInputParams</a>& inputParams)</div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span> {</div><div class="line"><a name="l00130"></a><span class="lineno"> 130</span>  CheckConstTensorPtrs(<span class="stringliteral">"InputToInputWeights"</span>,</div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  m_InputParams.m_InputToInputWeights,</div><div class="line"><a name="l00132"></a><span class="lineno"> 132</span>  inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#affcee5f4ab5994a21bee3b78b4e43de3">m_InputToInputWeights</a>);</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>  CheckConstTensorPtrs(<span class="stringliteral">"InputToForgetWeights"</span>,</div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span>  m_InputParams.m_InputToForgetWeights,</div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a>);</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span> </div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span>  CheckConstTensorPtrs(<span class="stringliteral">"InputToCellWeights"</span>,</div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span>  m_InputParams.m_InputToCellWeights,</div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span>  inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a>);</div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span> </div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span>  CheckConstTensorPtrs(<span class="stringliteral">"InputToOutputWeights"</span>,</div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span>  m_InputParams.m_InputToOutputWeights,</div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a>);</div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span> </div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span>  CheckConstTensorPtrs(<span class="stringliteral">"RecurrentToInputWeights"</span>,</div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  m_InputParams.m_RecurrentToInputWeights,</div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a435d3651482bbfcc11263b4e4e0c900f">m_RecurrentToInputWeights</a>);</div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span> </div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span>  CheckConstTensorPtrs(<span class="stringliteral">"RecurrentToForgetWeights"</span>,</div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span>  m_InputParams.m_RecurrentToForgetWeights,</div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a>);</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>  CheckConstTensorPtrs(<span class="stringliteral">"RecurrentToCellWeights"</span>,</div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  m_InputParams.m_RecurrentToCellWeights,</div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span>  inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a>);</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>  CheckConstTensorPtrs(<span class="stringliteral">"RecurrentToOutputWeights"</span>,</div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span>  m_InputParams.m_RecurrentToOutputWeights,</div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span>  inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a>);</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>  CheckConstTensorPtrs(<span class="stringliteral">"InputGateBias"</span>, m_InputParams.m_InputGateBias, inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a9e081a9b94defb30d1558dc912507e0e">m_InputGateBias</a>);</div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  CheckConstTensorPtrs(<span class="stringliteral">"ForgetGateBias"</span>, m_InputParams.m_ForgetGateBias, inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a>);</div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span>  CheckConstTensorPtrs(<span class="stringliteral">"CellBias"</span>, m_InputParams.m_CellBias, inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a>);</div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  CheckConstTensorPtrs(<span class="stringliteral">"OutputGateBias"</span>, m_InputParams.m_OutputGateBias, inputParams.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a>);</div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span> }</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> <a class="code" href="_output_shape_of_squeeze_8cpp.xhtml#ae3a6cb217a792718f2bd0e8f45e3ca9e">BOOST_AUTO_TEST_SUITE</a>(TestConstTensorLayerVisitor)</div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span> </div><div class="line"><a name="l00170"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b"> 170</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckConvolution2dLayer)</div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span> {</div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  <a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml">Convolution2dDescriptor</a> descriptor;</div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> = 2;</div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> = 3;</div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> = 1;</div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> = 5;</div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> = 2;</div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> = 3;</div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span> </div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span> </div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span>  <a class="code" href="classarmnn_1_1_test_convolution2d_layer_visitor.xhtml">TestConvolution2dLayerVisitor</a> visitor(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>());</div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span> </div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</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>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a865189c08aa64d448d05efc92a43725a">AddConvolution2dLayer</a>(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>());</div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00191"></a><span class="lineno"> 191</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"><a class="line" href="namespacearmnn.xhtml#a62448ee306fc41cc7980c4b7eac3ebb6"> 193</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedConvolution2dLayer)</div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span> {</div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"Convolution2dLayer"</span>;</div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span>  <a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml">Convolution2dDescriptor</a> descriptor;</div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> = 2;</div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> = 3;</div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> = 1;</div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> = 5;</div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> = 2;</div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> = 3;</div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span> </div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span> </div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  <a class="code" href="classarmnn_1_1_test_convolution2d_layer_visitor.xhtml">TestConvolution2dLayerVisitor</a> visitor(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>(), layerName);</div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span> </div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span> </div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a865189c08aa64d448d05efc92a43725a">AddConvolution2dLayer</a>(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>(), layerName);</div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span> }</div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span> </div><div class="line"><a name="l00217"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a66e9fcc01969d6afa35dfaa212ded223"> 217</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckConvolution2dLayerWithBiases)</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>  <a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml">Convolution2dDescriptor</a> descriptor;</div><div class="line"><a name="l00220"></a><span class="lineno"> 220</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> = 2;</div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> = 3;</div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> = 1;</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> = 5;</div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> = 2;</div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> = 3;</div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span> </div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span> </div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span>  std::vector<float> biasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  std::vector<unsigned int> biasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> biases(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, biasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), biasData);</div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span>  <a class="code" href="classarmnn_1_1_optional.xhtml">Optional<ConstTensor></a> optionalBiases(biases);</div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span> </div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  <a class="code" href="classarmnn_1_1_test_convolution2d_layer_visitor.xhtml">TestConvolution2dLayerVisitor</a> visitor(descriptor, weights, optionalBiases);</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>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00241"></a><span class="lineno"> 241</span> </div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a865189c08aa64d448d05efc92a43725a">AddConvolution2dLayer</a>(descriptor, weights, optionalBiases);</div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</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> </div><div class="line"><a name="l00246"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a154c5a01df05412929d89e06fc4d0d6d"> 246</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedConvolution2dLayerWithBiases)</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="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"Convolution2dLayer"</span>;</div><div class="line"><a name="l00249"></a><span class="lineno"> 249</span>  <a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml">Convolution2dDescriptor</a> descriptor;</div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> = 2;</div><div class="line"><a name="l00251"></a><span class="lineno"> 251</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> = 3;</div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> = 1;</div><div class="line"><a name="l00253"></a><span class="lineno"> 253</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> = 5;</div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> = 2;</div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> = 3;</div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  descriptor.<a class="code" href="structarmnn_1_1_convolution2d_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span> </div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00261"></a><span class="lineno"> 261</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00262"></a><span class="lineno"> 262</span> </div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span>  std::vector<float> biasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00264"></a><span class="lineno"> 264</span>  std::vector<unsigned int> biasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00265"></a><span class="lineno"> 265</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> biases(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, biasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), biasData);</div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  <a class="code" href="classarmnn_1_1_optional.xhtml">Optional<ConstTensor></a> optionalBiases(biases);</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>  <a class="code" href="classarmnn_1_1_test_convolution2d_layer_visitor.xhtml">TestConvolution2dLayerVisitor</a> visitor(descriptor, weights, optionalBiases, layerName);</div><div class="line"><a name="l00269"></a><span class="lineno"> 269</span> </div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span> </div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a865189c08aa64d448d05efc92a43725a">AddConvolution2dLayer</a>(descriptor, weights, optionalBiases, layerName);</div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00274"></a><span class="lineno"> 274</span> }</div><div class="line"><a name="l00275"></a><span class="lineno"> 275</span> </div><div class="line"><a name="l00276"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a6eadb1671955b1bf7cdd8b29fd34aa33"> 276</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckDepthwiseConvolution2dLayer)</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>  <a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml">DepthwiseConvolution2dDescriptor</a> descriptor;</div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> = 2;</div><div class="line"><a name="l00280"></a><span class="lineno"> 280</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> = 3;</div><div class="line"><a name="l00281"></a><span class="lineno"> 281</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> = 1;</div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> = 5;</div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> = 2;</div><div class="line"><a name="l00284"></a><span class="lineno"> 284</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> = 3;</div><div class="line"><a name="l00285"></a><span class="lineno"> 285</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span> </div><div class="line"><a name="l00287"></a><span class="lineno"> 287</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00289"></a><span class="lineno"> 289</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00290"></a><span class="lineno"> 290</span> </div><div class="line"><a name="l00291"></a><span class="lineno"> 291</span>  <a class="code" href="classarmnn_1_1_test_depthwise_convolution2d_layer_visitor.xhtml">TestDepthwiseConvolution2dLayerVisitor</a> visitor(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>());</div><div class="line"><a name="l00292"></a><span class="lineno"> 292</span> </div><div class="line"><a name="l00293"></a><span class="lineno"> 293</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00294"></a><span class="lineno"> 294</span> </div><div class="line"><a name="l00295"></a><span class="lineno"> 295</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a1add5219a64f4249a282f52202828451">AddDepthwiseConvolution2dLayer</a>(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>());</div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00297"></a><span class="lineno"> 297</span> }</div><div class="line"><a name="l00298"></a><span class="lineno"> 298</span> </div><div class="line"><a name="l00299"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#ac36bd2336c0e3caefecde40bc07e2bf3"> 299</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedDepthwiseConvolution2dLayer)</div><div class="line"><a name="l00300"></a><span class="lineno"> 300</span> {</div><div class="line"><a name="l00301"></a><span class="lineno"> 301</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"DepthwiseConvolution2dLayer"</span>;</div><div class="line"><a name="l00302"></a><span class="lineno"> 302</span>  <a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml">DepthwiseConvolution2dDescriptor</a> descriptor;</div><div class="line"><a name="l00303"></a><span class="lineno"> 303</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> = 2;</div><div class="line"><a name="l00304"></a><span class="lineno"> 304</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> = 3;</div><div class="line"><a name="l00305"></a><span class="lineno"> 305</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> = 1;</div><div class="line"><a name="l00306"></a><span class="lineno"> 306</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> = 5;</div><div class="line"><a name="l00307"></a><span class="lineno"> 307</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> = 2;</div><div class="line"><a name="l00308"></a><span class="lineno"> 308</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> = 3;</div><div class="line"><a name="l00309"></a><span class="lineno"> 309</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00310"></a><span class="lineno"> 310</span> </div><div class="line"><a name="l00311"></a><span class="lineno"> 311</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00312"></a><span class="lineno"> 312</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00313"></a><span class="lineno"> 313</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00314"></a><span class="lineno"> 314</span> </div><div class="line"><a name="l00315"></a><span class="lineno"> 315</span>  <a class="code" href="classarmnn_1_1_test_depthwise_convolution2d_layer_visitor.xhtml">TestDepthwiseConvolution2dLayerVisitor</a> visitor(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>(), layerName);</div><div class="line"><a name="l00316"></a><span class="lineno"> 316</span> </div><div class="line"><a name="l00317"></a><span class="lineno"> 317</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00318"></a><span class="lineno"> 318</span> </div><div class="line"><a name="l00319"></a><span class="lineno"> 319</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a1add5219a64f4249a282f52202828451">AddDepthwiseConvolution2dLayer</a>(descriptor,</div><div class="line"><a name="l00320"></a><span class="lineno"> 320</span>  weights,</div><div class="line"><a name="l00321"></a><span class="lineno"> 321</span>  <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>(),</div><div class="line"><a name="l00322"></a><span class="lineno"> 322</span>  layerName);</div><div class="line"><a name="l00323"></a><span class="lineno"> 323</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00324"></a><span class="lineno"> 324</span> }</div><div class="line"><a name="l00325"></a><span class="lineno"> 325</span> </div><div class="line"><a name="l00326"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a14bcc6125921389dceb27e432bc7a489"> 326</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckDepthwiseConvolution2dLayerWithBiases)</div><div class="line"><a name="l00327"></a><span class="lineno"> 327</span> {</div><div class="line"><a name="l00328"></a><span class="lineno"> 328</span>  <a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml">DepthwiseConvolution2dDescriptor</a> descriptor;</div><div class="line"><a name="l00329"></a><span class="lineno"> 329</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> = 2;</div><div class="line"><a name="l00330"></a><span class="lineno"> 330</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> = 3;</div><div class="line"><a name="l00331"></a><span class="lineno"> 331</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> = 1;</div><div class="line"><a name="l00332"></a><span class="lineno"> 332</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> = 5;</div><div class="line"><a name="l00333"></a><span class="lineno"> 333</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> = 2;</div><div class="line"><a name="l00334"></a><span class="lineno"> 334</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> = 3;</div><div class="line"><a name="l00335"></a><span class="lineno"> 335</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00336"></a><span class="lineno"> 336</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00337"></a><span class="lineno"> 337</span> </div><div class="line"><a name="l00338"></a><span class="lineno"> 338</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00339"></a><span class="lineno"> 339</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00340"></a><span class="lineno"> 340</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00341"></a><span class="lineno"> 341</span> </div><div class="line"><a name="l00342"></a><span class="lineno"> 342</span>  std::vector<float> biasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00343"></a><span class="lineno"> 343</span>  std::vector<unsigned int> biasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00344"></a><span class="lineno"> 344</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> biases(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, biasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), biasData);</div><div class="line"><a name="l00345"></a><span class="lineno"> 345</span>  <a class="code" href="classarmnn_1_1_optional.xhtml">Optional<ConstTensor></a> optionalBiases(biases);</div><div class="line"><a name="l00346"></a><span class="lineno"> 346</span> </div><div class="line"><a name="l00347"></a><span class="lineno"> 347</span>  <a class="code" href="classarmnn_1_1_test_depthwise_convolution2d_layer_visitor.xhtml">TestDepthwiseConvolution2dLayerVisitor</a> visitor(descriptor, weights, optionalBiases);</div><div class="line"><a name="l00348"></a><span class="lineno"> 348</span> </div><div class="line"><a name="l00349"></a><span class="lineno"> 349</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00350"></a><span class="lineno"> 350</span> </div><div class="line"><a name="l00351"></a><span class="lineno"> 351</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a1add5219a64f4249a282f52202828451">AddDepthwiseConvolution2dLayer</a>(descriptor, weights, optionalBiases);</div><div class="line"><a name="l00352"></a><span class="lineno"> 352</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00353"></a><span class="lineno"> 353</span> }</div><div class="line"><a name="l00354"></a><span class="lineno"> 354</span> </div><div class="line"><a name="l00355"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#aaeafd5f3786a0bd215468714c1e743b1"> 355</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedDepthwiseConvolution2dLayerWithBiases)</div><div class="line"><a name="l00356"></a><span class="lineno"> 356</span> {</div><div class="line"><a name="l00357"></a><span class="lineno"> 357</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"DepthwiseConvolution2dLayer"</span>;</div><div class="line"><a name="l00358"></a><span class="lineno"> 358</span>  <a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml">DepthwiseConvolution2dDescriptor</a> descriptor;</div><div class="line"><a name="l00359"></a><span class="lineno"> 359</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac18546ebbebbb32fe0a03baa9bf2c600">m_PadLeft</a> = 2;</div><div class="line"><a name="l00360"></a><span class="lineno"> 360</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a002bc30e590d78cbb4f4d12171055ca7">m_PadRight</a> = 3;</div><div class="line"><a name="l00361"></a><span class="lineno"> 361</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#aa9e49717ebdb741e8c767741647fc618">m_PadBottom</a> = 1;</div><div class="line"><a name="l00362"></a><span class="lineno"> 362</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a56b51f56cef50cdfa554258eecdab046">m_PadTop</a> = 5;</div><div class="line"><a name="l00363"></a><span class="lineno"> 363</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#afe6a3377c4531315354def9023c8fdda">m_StrideX</a> = 2;</div><div class="line"><a name="l00364"></a><span class="lineno"> 364</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#ac1fe174bbadfb39a2b636940c2e647c8">m_StrideY</a> = 3;</div><div class="line"><a name="l00365"></a><span class="lineno"> 365</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00366"></a><span class="lineno"> 366</span>  descriptor.<a class="code" href="structarmnn_1_1_depthwise_convolution2d_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00367"></a><span class="lineno"> 367</span> </div><div class="line"><a name="l00368"></a><span class="lineno"> 368</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00369"></a><span class="lineno"> 369</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00370"></a><span class="lineno"> 370</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00371"></a><span class="lineno"> 371</span> </div><div class="line"><a name="l00372"></a><span class="lineno"> 372</span>  std::vector<float> biasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00373"></a><span class="lineno"> 373</span>  std::vector<unsigned int> biasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00374"></a><span class="lineno"> 374</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> biases(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, biasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), biasData);</div><div class="line"><a name="l00375"></a><span class="lineno"> 375</span>  <a class="code" href="classarmnn_1_1_optional.xhtml">Optional<ConstTensor></a> optionalBiases(biases);</div><div class="line"><a name="l00376"></a><span class="lineno"> 376</span> </div><div class="line"><a name="l00377"></a><span class="lineno"> 377</span>  <a class="code" href="classarmnn_1_1_test_depthwise_convolution2d_layer_visitor.xhtml">TestDepthwiseConvolution2dLayerVisitor</a> visitor(descriptor, weights, optionalBiases, layerName);</div><div class="line"><a name="l00378"></a><span class="lineno"> 378</span> </div><div class="line"><a name="l00379"></a><span class="lineno"> 379</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00380"></a><span class="lineno"> 380</span> </div><div class="line"><a name="l00381"></a><span class="lineno"> 381</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a1add5219a64f4249a282f52202828451">AddDepthwiseConvolution2dLayer</a>(descriptor, weights, optionalBiases, layerName);</div><div class="line"><a name="l00382"></a><span class="lineno"> 382</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00383"></a><span class="lineno"> 383</span> }</div><div class="line"><a name="l00384"></a><span class="lineno"> 384</span> </div><div class="line"><a name="l00385"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a3425db69ef4e4927a82e99025c16294a"> 385</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckFullyConnectedLayer)</div><div class="line"><a name="l00386"></a><span class="lineno"> 386</span> {</div><div class="line"><a name="l00387"></a><span class="lineno"> 387</span>  <a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml">FullyConnectedDescriptor</a> descriptor;</div><div class="line"><a name="l00388"></a><span class="lineno"> 388</span>  descriptor.<a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml#a281fcaec86e17c97f7b8402633f6b55a">m_TransposeWeightMatrix</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00389"></a><span class="lineno"> 389</span> </div><div class="line"><a name="l00390"></a><span class="lineno"> 390</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00391"></a><span class="lineno"> 391</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00392"></a><span class="lineno"> 392</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00393"></a><span class="lineno"> 393</span> </div><div class="line"><a name="l00394"></a><span class="lineno"> 394</span>  <a class="code" href="classarmnn_1_1_test_fully_connected_layer_vistor.xhtml">TestFullyConnectedLayerVistor</a> visitor(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>());</div><div class="line"><a name="l00395"></a><span class="lineno"> 395</span> </div><div class="line"><a name="l00396"></a><span class="lineno"> 396</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00397"></a><span class="lineno"> 397</span> </div><div class="line"><a name="l00398"></a><span class="lineno"> 398</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a80dc86e975ff991ef63aa8b523d4fcdf">AddFullyConnectedLayer</a>(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>());</div><div class="line"><a name="l00399"></a><span class="lineno"> 399</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00400"></a><span class="lineno"> 400</span> }</div><div class="line"><a name="l00401"></a><span class="lineno"> 401</span> </div><div class="line"><a name="l00402"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a631f8c0c9bceff4bef761eb7fd865686"> 402</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedFullyConnectedLayer)</div><div class="line"><a name="l00403"></a><span class="lineno"> 403</span> {</div><div class="line"><a name="l00404"></a><span class="lineno"> 404</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"FullyConnectedLayer"</span>;</div><div class="line"><a name="l00405"></a><span class="lineno"> 405</span>  <a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml">FullyConnectedDescriptor</a> descriptor;</div><div class="line"><a name="l00406"></a><span class="lineno"> 406</span>  descriptor.<a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml#a281fcaec86e17c97f7b8402633f6b55a">m_TransposeWeightMatrix</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00407"></a><span class="lineno"> 407</span> </div><div class="line"><a name="l00408"></a><span class="lineno"> 408</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00409"></a><span class="lineno"> 409</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00410"></a><span class="lineno"> 410</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00411"></a><span class="lineno"> 411</span> </div><div class="line"><a name="l00412"></a><span class="lineno"> 412</span>  <a class="code" href="classarmnn_1_1_test_fully_connected_layer_vistor.xhtml">TestFullyConnectedLayerVistor</a> visitor(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>(), layerName);</div><div class="line"><a name="l00413"></a><span class="lineno"> 413</span> </div><div class="line"><a name="l00414"></a><span class="lineno"> 414</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00415"></a><span class="lineno"> 415</span> </div><div class="line"><a name="l00416"></a><span class="lineno"> 416</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a80dc86e975ff991ef63aa8b523d4fcdf">AddFullyConnectedLayer</a>(descriptor, weights, <a class="code" href="structarmnn_1_1_empty_optional.xhtml">EmptyOptional</a>(), layerName);</div><div class="line"><a name="l00417"></a><span class="lineno"> 417</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00418"></a><span class="lineno"> 418</span> }</div><div class="line"><a name="l00419"></a><span class="lineno"> 419</span> </div><div class="line"><a name="l00420"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a7b017a692367333d1035e276f252f46c"> 420</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckFullyConnectedLayerWithBiases)</div><div class="line"><a name="l00421"></a><span class="lineno"> 421</span> {</div><div class="line"><a name="l00422"></a><span class="lineno"> 422</span>  <a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml">FullyConnectedDescriptor</a> descriptor;</div><div class="line"><a name="l00423"></a><span class="lineno"> 423</span>  descriptor.<a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml#a281fcaec86e17c97f7b8402633f6b55a">m_TransposeWeightMatrix</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00424"></a><span class="lineno"> 424</span>  descriptor.<a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00425"></a><span class="lineno"> 425</span> </div><div class="line"><a name="l00426"></a><span class="lineno"> 426</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00427"></a><span class="lineno"> 427</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00428"></a><span class="lineno"> 428</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00429"></a><span class="lineno"> 429</span> </div><div class="line"><a name="l00430"></a><span class="lineno"> 430</span>  std::vector<float> biasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00431"></a><span class="lineno"> 431</span>  std::vector<unsigned int> biasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00432"></a><span class="lineno"> 432</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> biases(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, biasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), biasData);</div><div class="line"><a name="l00433"></a><span class="lineno"> 433</span>  <a class="code" href="classarmnn_1_1_optional.xhtml">Optional<ConstTensor></a> optionalBiases(biases);</div><div class="line"><a name="l00434"></a><span class="lineno"> 434</span> </div><div class="line"><a name="l00435"></a><span class="lineno"> 435</span>  <a class="code" href="classarmnn_1_1_test_fully_connected_layer_vistor.xhtml">TestFullyConnectedLayerVistor</a> visitor(descriptor, weights, optionalBiases);</div><div class="line"><a name="l00436"></a><span class="lineno"> 436</span> </div><div class="line"><a name="l00437"></a><span class="lineno"> 437</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00438"></a><span class="lineno"> 438</span> </div><div class="line"><a name="l00439"></a><span class="lineno"> 439</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a80dc86e975ff991ef63aa8b523d4fcdf">AddFullyConnectedLayer</a>(descriptor, weights, optionalBiases);</div><div class="line"><a name="l00440"></a><span class="lineno"> 440</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00441"></a><span class="lineno"> 441</span> }</div><div class="line"><a name="l00442"></a><span class="lineno"> 442</span> </div><div class="line"><a name="l00443"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a5f3e4faca1d063ad73764571f898dc2d"> 443</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedFullyConnectedLayerWithBiases)</div><div class="line"><a name="l00444"></a><span class="lineno"> 444</span> {</div><div class="line"><a name="l00445"></a><span class="lineno"> 445</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"FullyConnectedLayer"</span>;</div><div class="line"><a name="l00446"></a><span class="lineno"> 446</span>  <a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml">FullyConnectedDescriptor</a> descriptor;</div><div class="line"><a name="l00447"></a><span class="lineno"> 447</span>  descriptor.<a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml#a281fcaec86e17c97f7b8402633f6b55a">m_TransposeWeightMatrix</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00448"></a><span class="lineno"> 448</span>  descriptor.<a class="code" href="structarmnn_1_1_fully_connected_descriptor.xhtml#aea202e14d8874cefd9a0f778022b7e25">m_BiasEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00449"></a><span class="lineno"> 449</span> </div><div class="line"><a name="l00450"></a><span class="lineno"> 450</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00451"></a><span class="lineno"> 451</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00452"></a><span class="lineno"> 452</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> weights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00453"></a><span class="lineno"> 453</span> </div><div class="line"><a name="l00454"></a><span class="lineno"> 454</span>  std::vector<float> biasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00455"></a><span class="lineno"> 455</span>  std::vector<unsigned int> biasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00456"></a><span class="lineno"> 456</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> biases(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, biasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), biasData);</div><div class="line"><a name="l00457"></a><span class="lineno"> 457</span>  <a class="code" href="classarmnn_1_1_optional.xhtml">Optional<ConstTensor></a> optionalBiases(biases);</div><div class="line"><a name="l00458"></a><span class="lineno"> 458</span> </div><div class="line"><a name="l00459"></a><span class="lineno"> 459</span>  <a class="code" href="classarmnn_1_1_test_fully_connected_layer_vistor.xhtml">TestFullyConnectedLayerVistor</a> visitor(descriptor, weights, optionalBiases, layerName);</div><div class="line"><a name="l00460"></a><span class="lineno"> 460</span> </div><div class="line"><a name="l00461"></a><span class="lineno"> 461</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00462"></a><span class="lineno"> 462</span> </div><div class="line"><a name="l00463"></a><span class="lineno"> 463</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a80dc86e975ff991ef63aa8b523d4fcdf">AddFullyConnectedLayer</a>(descriptor, weights, optionalBiases, layerName);</div><div class="line"><a name="l00464"></a><span class="lineno"> 464</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00465"></a><span class="lineno"> 465</span> }</div><div class="line"><a name="l00466"></a><span class="lineno"> 466</span> </div><div class="line"><a name="l00467"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a199581e11ebd49e1322b090484f3dd29"> 467</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckBatchNormalizationLayer)</div><div class="line"><a name="l00468"></a><span class="lineno"> 468</span> {</div><div class="line"><a name="l00469"></a><span class="lineno"> 469</span>  <a class="code" href="structarmnn_1_1_batch_normalization_descriptor.xhtml">BatchNormalizationDescriptor</a> descriptor;</div><div class="line"><a name="l00470"></a><span class="lineno"> 470</span>  descriptor.<a class="code" href="structarmnn_1_1_batch_normalization_descriptor.xhtml#a11c821c7524251004a72ed13c510853c">m_Eps</a> = 0.0002f;</div><div class="line"><a name="l00471"></a><span class="lineno"> 471</span>  descriptor.<a class="code" href="structarmnn_1_1_batch_normalization_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00472"></a><span class="lineno"> 472</span> </div><div class="line"><a name="l00473"></a><span class="lineno"> 473</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00474"></a><span class="lineno"> 474</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00475"></a><span class="lineno"> 475</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> mean(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00476"></a><span class="lineno"> 476</span> </div><div class="line"><a name="l00477"></a><span class="lineno"> 477</span>  std::vector<float> varianceData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00478"></a><span class="lineno"> 478</span>  std::vector<unsigned int> varianceDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00479"></a><span class="lineno"> 479</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> variance(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, varianceDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), varianceData);</div><div class="line"><a name="l00480"></a><span class="lineno"> 480</span> </div><div class="line"><a name="l00481"></a><span class="lineno"> 481</span>  std::vector<float> betaData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00482"></a><span class="lineno"> 482</span>  std::vector<unsigned int> betaDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00483"></a><span class="lineno"> 483</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> beta(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, betaDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), betaData);</div><div class="line"><a name="l00484"></a><span class="lineno"> 484</span> </div><div class="line"><a name="l00485"></a><span class="lineno"> 485</span>  std::vector<float> gammaData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00486"></a><span class="lineno"> 486</span>  std::vector<unsigned int> gammaDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00487"></a><span class="lineno"> 487</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> gamma(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, gammaDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), gammaData);</div><div class="line"><a name="l00488"></a><span class="lineno"> 488</span> </div><div class="line"><a name="l00489"></a><span class="lineno"> 489</span>  <a class="code" href="classarmnn_1_1_test_batch_normalization_layer_visitor.xhtml">TestBatchNormalizationLayerVisitor</a> visitor(descriptor, mean, variance, beta, gamma);</div><div class="line"><a name="l00490"></a><span class="lineno"> 490</span> </div><div class="line"><a name="l00491"></a><span class="lineno"> 491</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00492"></a><span class="lineno"> 492</span> </div><div class="line"><a name="l00493"></a><span class="lineno"> 493</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#abd4965a5d1d28a91b975e6b0eef024c8">AddBatchNormalizationLayer</a>(descriptor, mean, variance, beta, gamma);</div><div class="line"><a name="l00494"></a><span class="lineno"> 494</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00495"></a><span class="lineno"> 495</span> }</div><div class="line"><a name="l00496"></a><span class="lineno"> 496</span> </div><div class="line"><a name="l00497"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#af1eda3afe49e91bf04d6e34a0e3be8ef"> 497</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedBatchNormalizationLayer)</div><div class="line"><a name="l00498"></a><span class="lineno"> 498</span> {</div><div class="line"><a name="l00499"></a><span class="lineno"> 499</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"BatchNormalizationLayer"</span>;</div><div class="line"><a name="l00500"></a><span class="lineno"> 500</span>  <a class="code" href="structarmnn_1_1_batch_normalization_descriptor.xhtml">BatchNormalizationDescriptor</a> descriptor;</div><div class="line"><a name="l00501"></a><span class="lineno"> 501</span>  descriptor.<a class="code" href="structarmnn_1_1_batch_normalization_descriptor.xhtml#a11c821c7524251004a72ed13c510853c">m_Eps</a> = 0.0002f;</div><div class="line"><a name="l00502"></a><span class="lineno"> 502</span>  descriptor.<a class="code" href="structarmnn_1_1_batch_normalization_descriptor.xhtml#a6089e1ca91914015777ea780a513131a">m_DataLayout</a> = <a class="code" href="namespacearmnn.xhtml#ad1d5cce2d9e9a5d61c243e5c989112e0ad066db54b89b0912e7e7c6da51e2da51">DataLayout::NHWC</a>;</div><div class="line"><a name="l00503"></a><span class="lineno"> 503</span> </div><div class="line"><a name="l00504"></a><span class="lineno"> 504</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00505"></a><span class="lineno"> 505</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00506"></a><span class="lineno"> 506</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> mean(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00507"></a><span class="lineno"> 507</span> </div><div class="line"><a name="l00508"></a><span class="lineno"> 508</span>  std::vector<float> varianceData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00509"></a><span class="lineno"> 509</span>  std::vector<unsigned int> varianceDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00510"></a><span class="lineno"> 510</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> variance(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, varianceDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), varianceData);</div><div class="line"><a name="l00511"></a><span class="lineno"> 511</span> </div><div class="line"><a name="l00512"></a><span class="lineno"> 512</span>  std::vector<float> betaData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00513"></a><span class="lineno"> 513</span>  std::vector<unsigned int> betaDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00514"></a><span class="lineno"> 514</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> beta(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, betaDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), betaData);</div><div class="line"><a name="l00515"></a><span class="lineno"> 515</span> </div><div class="line"><a name="l00516"></a><span class="lineno"> 516</span>  std::vector<float> gammaData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00517"></a><span class="lineno"> 517</span>  std::vector<unsigned int> gammaDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00518"></a><span class="lineno"> 518</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> gamma(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, gammaDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), gammaData);</div><div class="line"><a name="l00519"></a><span class="lineno"> 519</span> </div><div class="line"><a name="l00520"></a><span class="lineno"> 520</span>  <a class="code" href="classarmnn_1_1_test_batch_normalization_layer_visitor.xhtml">TestBatchNormalizationLayerVisitor</a> visitor(descriptor, mean, variance, beta, gamma, layerName);</div><div class="line"><a name="l00521"></a><span class="lineno"> 521</span> </div><div class="line"><a name="l00522"></a><span class="lineno"> 522</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00523"></a><span class="lineno"> 523</span> </div><div class="line"><a name="l00524"></a><span class="lineno"> 524</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#abd4965a5d1d28a91b975e6b0eef024c8">AddBatchNormalizationLayer</a>(</div><div class="line"><a name="l00525"></a><span class="lineno"> 525</span>  descriptor, mean, variance, beta, gamma, layerName);</div><div class="line"><a name="l00526"></a><span class="lineno"> 526</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00527"></a><span class="lineno"> 527</span> }</div><div class="line"><a name="l00528"></a><span class="lineno"> 528</span> </div><div class="line"><a name="l00529"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a1a8221833cf3d29cd6435aed632dfcce"> 529</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckConstLayer)</div><div class="line"><a name="l00530"></a><span class="lineno"> 530</span> {</div><div class="line"><a name="l00531"></a><span class="lineno"> 531</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00532"></a><span class="lineno"> 532</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00533"></a><span class="lineno"> 533</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> input(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00534"></a><span class="lineno"> 534</span> </div><div class="line"><a name="l00535"></a><span class="lineno"> 535</span>  <a class="code" href="classarmnn_1_1_test_constant_layer_visitor.xhtml">TestConstantLayerVisitor</a> visitor(input);</div><div class="line"><a name="l00536"></a><span class="lineno"> 536</span> </div><div class="line"><a name="l00537"></a><span class="lineno"> 537</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00538"></a><span class="lineno"> 538</span> </div><div class="line"><a name="l00539"></a><span class="lineno"> 539</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a8b2e7eb34ad5aacda72260f77fd880ce">AddConstantLayer</a>(input);</div><div class="line"><a name="l00540"></a><span class="lineno"> 540</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00541"></a><span class="lineno"> 541</span> }</div><div class="line"><a name="l00542"></a><span class="lineno"> 542</span> </div><div class="line"><a name="l00543"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a9da3b50de4d108b81264a22c5adacf05"> 543</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedConstLayer)</div><div class="line"><a name="l00544"></a><span class="lineno"> 544</span> {</div><div class="line"><a name="l00545"></a><span class="lineno"> 545</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"ConstantLayer"</span>;</div><div class="line"><a name="l00546"></a><span class="lineno"> 546</span>  std::vector<float> data = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00547"></a><span class="lineno"> 547</span>  std::vector<unsigned int> dimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00548"></a><span class="lineno"> 548</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> input(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, dimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), data);</div><div class="line"><a name="l00549"></a><span class="lineno"> 549</span> </div><div class="line"><a name="l00550"></a><span class="lineno"> 550</span>  <a class="code" href="classarmnn_1_1_test_constant_layer_visitor.xhtml">TestConstantLayerVisitor</a> visitor(input, layerName);</div><div class="line"><a name="l00551"></a><span class="lineno"> 551</span> </div><div class="line"><a name="l00552"></a><span class="lineno"> 552</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00553"></a><span class="lineno"> 553</span> </div><div class="line"><a name="l00554"></a><span class="lineno"> 554</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a8b2e7eb34ad5aacda72260f77fd880ce">AddConstantLayer</a>(input, layerName);</div><div class="line"><a name="l00555"></a><span class="lineno"> 555</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00556"></a><span class="lineno"> 556</span> }</div><div class="line"><a name="l00557"></a><span class="lineno"> 557</span> </div><div class="line"><a name="l00558"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#afefeb492b3446d34e413556a805210b6"> 558</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckLstmLayerBasic)</div><div class="line"><a name="l00559"></a><span class="lineno"> 559</span> {</div><div class="line"><a name="l00560"></a><span class="lineno"> 560</span>  <a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml">LstmDescriptor</a> descriptor;</div><div class="line"><a name="l00561"></a><span class="lineno"> 561</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ae1b07ed928036004bd257169e5aeeef4">m_ActivationFunc</a> = 3;</div><div class="line"><a name="l00562"></a><span class="lineno"> 562</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a86e88bef0df4df96df752b4b8955a3af">m_ClippingThresProj</a> = 0.5f;</div><div class="line"><a name="l00563"></a><span class="lineno"> 563</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a531a3907ec13d3772370da88030191a5">m_ClippingThresCell</a> = 0.3f;</div><div class="line"><a name="l00564"></a><span class="lineno"> 564</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ad474e5c51a0b194ef32e812b86c0cbdb">m_CifgEnabled</a> = <span class="keyword">true</span>; <span class="comment">// if this is true then we DON'T need to set the OptCifgParams</span></div><div class="line"><a name="l00565"></a><span class="lineno"> 565</span> </div><div class="line"><a name="l00566"></a><span class="lineno"> 566</span>  std::vector<float> inputToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00567"></a><span class="lineno"> 567</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00568"></a><span class="lineno"> 568</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l00569"></a><span class="lineno"> 569</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToForgetWeightsData);</div><div class="line"><a name="l00570"></a><span class="lineno"> 570</span> </div><div class="line"><a name="l00571"></a><span class="lineno"> 571</span>  std::vector<float> inputToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00572"></a><span class="lineno"> 572</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00573"></a><span class="lineno"> 573</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l00574"></a><span class="lineno"> 574</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToCellWeightsData);</div><div class="line"><a name="l00575"></a><span class="lineno"> 575</span> </div><div class="line"><a name="l00576"></a><span class="lineno"> 576</span>  std::vector<float> inputToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00577"></a><span class="lineno"> 577</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00578"></a><span class="lineno"> 578</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l00579"></a><span class="lineno"> 579</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToOutputWeightsData);</div><div class="line"><a name="l00580"></a><span class="lineno"> 580</span> </div><div class="line"><a name="l00581"></a><span class="lineno"> 581</span>  std::vector<float> recurrentToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00582"></a><span class="lineno"> 582</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00583"></a><span class="lineno"> 583</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00584"></a><span class="lineno"> 584</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l00585"></a><span class="lineno"> 585</span> </div><div class="line"><a name="l00586"></a><span class="lineno"> 586</span>  std::vector<float> recurrentToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00587"></a><span class="lineno"> 587</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00588"></a><span class="lineno"> 588</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00589"></a><span class="lineno"> 589</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l00590"></a><span class="lineno"> 590</span> </div><div class="line"><a name="l00591"></a><span class="lineno"> 591</span>  std::vector<float> recurrentToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00592"></a><span class="lineno"> 592</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00593"></a><span class="lineno"> 593</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00594"></a><span class="lineno"> 594</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l00595"></a><span class="lineno"> 595</span> </div><div class="line"><a name="l00596"></a><span class="lineno"> 596</span>  std::vector<float> forgetGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00597"></a><span class="lineno"> 597</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00598"></a><span class="lineno"> 598</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00599"></a><span class="lineno"> 599</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), forgetGateBiasData);</div><div class="line"><a name="l00600"></a><span class="lineno"> 600</span> </div><div class="line"><a name="l00601"></a><span class="lineno"> 601</span>  std::vector<float> cellBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00602"></a><span class="lineno"> 602</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00603"></a><span class="lineno"> 603</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00604"></a><span class="lineno"> 604</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellBiasData);</div><div class="line"><a name="l00605"></a><span class="lineno"> 605</span> </div><div class="line"><a name="l00606"></a><span class="lineno"> 606</span>  std::vector<float> outputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00607"></a><span class="lineno"> 607</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00608"></a><span class="lineno"> 608</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00609"></a><span class="lineno"> 609</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), outputGateBiasData);</div><div class="line"><a name="l00610"></a><span class="lineno"> 610</span> </div><div class="line"><a name="l00611"></a><span class="lineno"> 611</span>  <a class="code" href="structarmnn_1_1_lstm_input_params.xhtml">LstmInputParams</a> params;</div><div class="line"><a name="l00612"></a><span class="lineno"> 612</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l00613"></a><span class="lineno"> 613</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l00614"></a><span class="lineno"> 614</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l00615"></a><span class="lineno"> 615</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l00616"></a><span class="lineno"> 616</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l00617"></a><span class="lineno"> 617</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l00618"></a><span class="lineno"> 618</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l00619"></a><span class="lineno"> 619</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l00620"></a><span class="lineno"> 620</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l00621"></a><span class="lineno"> 621</span> </div><div class="line"><a name="l00622"></a><span class="lineno"> 622</span>  <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml">TestLstmLayerVisitor</a> visitor(descriptor, params);</div><div class="line"><a name="l00623"></a><span class="lineno"> 623</span> </div><div class="line"><a name="l00624"></a><span class="lineno"> 624</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00625"></a><span class="lineno"> 625</span> </div><div class="line"><a name="l00626"></a><span class="lineno"> 626</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#ab1569dbf88b6511bde91bee3224a558c">AddLstmLayer</a>(descriptor, params);</div><div class="line"><a name="l00627"></a><span class="lineno"> 627</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00628"></a><span class="lineno"> 628</span> }</div><div class="line"><a name="l00629"></a><span class="lineno"> 629</span> </div><div class="line"><a name="l00630"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a8f6ad27911e2e711f665ae69c5b2cd1d"> 630</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedLstmLayerBasic)</div><div class="line"><a name="l00631"></a><span class="lineno"> 631</span> {</div><div class="line"><a name="l00632"></a><span class="lineno"> 632</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"LstmLayer"</span>;</div><div class="line"><a name="l00633"></a><span class="lineno"> 633</span>  <a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml">LstmDescriptor</a> descriptor;</div><div class="line"><a name="l00634"></a><span class="lineno"> 634</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ae1b07ed928036004bd257169e5aeeef4">m_ActivationFunc</a> = 3;</div><div class="line"><a name="l00635"></a><span class="lineno"> 635</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a86e88bef0df4df96df752b4b8955a3af">m_ClippingThresProj</a> = 0.5f;</div><div class="line"><a name="l00636"></a><span class="lineno"> 636</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a531a3907ec13d3772370da88030191a5">m_ClippingThresCell</a> = 0.3f;</div><div class="line"><a name="l00637"></a><span class="lineno"> 637</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ad474e5c51a0b194ef32e812b86c0cbdb">m_CifgEnabled</a> = <span class="keyword">true</span>; <span class="comment">// if this is true then we DON'T need to set the OptCifgParams</span></div><div class="line"><a name="l00638"></a><span class="lineno"> 638</span> </div><div class="line"><a name="l00639"></a><span class="lineno"> 639</span>  std::vector<float> inputToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00640"></a><span class="lineno"> 640</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00641"></a><span class="lineno"> 641</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l00642"></a><span class="lineno"> 642</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToForgetWeightsData);</div><div class="line"><a name="l00643"></a><span class="lineno"> 643</span> </div><div class="line"><a name="l00644"></a><span class="lineno"> 644</span>  std::vector<float> inputToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00645"></a><span class="lineno"> 645</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00646"></a><span class="lineno"> 646</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l00647"></a><span class="lineno"> 647</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToCellWeightsData);</div><div class="line"><a name="l00648"></a><span class="lineno"> 648</span> </div><div class="line"><a name="l00649"></a><span class="lineno"> 649</span>  std::vector<float> inputToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00650"></a><span class="lineno"> 650</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00651"></a><span class="lineno"> 651</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l00652"></a><span class="lineno"> 652</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToOutputWeightsData);</div><div class="line"><a name="l00653"></a><span class="lineno"> 653</span> </div><div class="line"><a name="l00654"></a><span class="lineno"> 654</span>  std::vector<float> recurrentToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00655"></a><span class="lineno"> 655</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00656"></a><span class="lineno"> 656</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00657"></a><span class="lineno"> 657</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l00658"></a><span class="lineno"> 658</span> </div><div class="line"><a name="l00659"></a><span class="lineno"> 659</span>  std::vector<float> recurrentToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00660"></a><span class="lineno"> 660</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00661"></a><span class="lineno"> 661</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00662"></a><span class="lineno"> 662</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l00663"></a><span class="lineno"> 663</span> </div><div class="line"><a name="l00664"></a><span class="lineno"> 664</span>  std::vector<float> recurrentToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00665"></a><span class="lineno"> 665</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00666"></a><span class="lineno"> 666</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00667"></a><span class="lineno"> 667</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l00668"></a><span class="lineno"> 668</span> </div><div class="line"><a name="l00669"></a><span class="lineno"> 669</span>  std::vector<float> forgetGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00670"></a><span class="lineno"> 670</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00671"></a><span class="lineno"> 671</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00672"></a><span class="lineno"> 672</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), forgetGateBiasData);</div><div class="line"><a name="l00673"></a><span class="lineno"> 673</span> </div><div class="line"><a name="l00674"></a><span class="lineno"> 674</span>  std::vector<float> cellBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00675"></a><span class="lineno"> 675</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00676"></a><span class="lineno"> 676</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00677"></a><span class="lineno"> 677</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellBiasData);</div><div class="line"><a name="l00678"></a><span class="lineno"> 678</span> </div><div class="line"><a name="l00679"></a><span class="lineno"> 679</span>  std::vector<float> outputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00680"></a><span class="lineno"> 680</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00681"></a><span class="lineno"> 681</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00682"></a><span class="lineno"> 682</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), outputGateBiasData);</div><div class="line"><a name="l00683"></a><span class="lineno"> 683</span> </div><div class="line"><a name="l00684"></a><span class="lineno"> 684</span>  <a class="code" href="structarmnn_1_1_lstm_input_params.xhtml">LstmInputParams</a> params;</div><div class="line"><a name="l00685"></a><span class="lineno"> 685</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l00686"></a><span class="lineno"> 686</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l00687"></a><span class="lineno"> 687</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l00688"></a><span class="lineno"> 688</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l00689"></a><span class="lineno"> 689</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l00690"></a><span class="lineno"> 690</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l00691"></a><span class="lineno"> 691</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l00692"></a><span class="lineno"> 692</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l00693"></a><span class="lineno"> 693</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l00694"></a><span class="lineno"> 694</span> </div><div class="line"><a name="l00695"></a><span class="lineno"> 695</span>  <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml">TestLstmLayerVisitor</a> visitor(descriptor, params, layerName);</div><div class="line"><a name="l00696"></a><span class="lineno"> 696</span> </div><div class="line"><a name="l00697"></a><span class="lineno"> 697</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00698"></a><span class="lineno"> 698</span> </div><div class="line"><a name="l00699"></a><span class="lineno"> 699</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#ab1569dbf88b6511bde91bee3224a558c">AddLstmLayer</a>(descriptor, params, layerName);</div><div class="line"><a name="l00700"></a><span class="lineno"> 700</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00701"></a><span class="lineno"> 701</span> }</div><div class="line"><a name="l00702"></a><span class="lineno"> 702</span> </div><div class="line"><a name="l00703"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a5400bc09082eab59bdfdbd61a06578f5"> 703</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckLstmLayerCifgDisabled)</div><div class="line"><a name="l00704"></a><span class="lineno"> 704</span> {</div><div class="line"><a name="l00705"></a><span class="lineno"> 705</span>  <a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml">LstmDescriptor</a> descriptor;</div><div class="line"><a name="l00706"></a><span class="lineno"> 706</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ae1b07ed928036004bd257169e5aeeef4">m_ActivationFunc</a> = 3;</div><div class="line"><a name="l00707"></a><span class="lineno"> 707</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a86e88bef0df4df96df752b4b8955a3af">m_ClippingThresProj</a> = 0.5f;</div><div class="line"><a name="l00708"></a><span class="lineno"> 708</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a531a3907ec13d3772370da88030191a5">m_ClippingThresCell</a> = 0.3f;</div><div class="line"><a name="l00709"></a><span class="lineno"> 709</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ad474e5c51a0b194ef32e812b86c0cbdb">m_CifgEnabled</a> = <span class="keyword">false</span>; <span class="comment">// if this is true then we DON'T need to set the OptCifgParams</span></div><div class="line"><a name="l00710"></a><span class="lineno"> 710</span> </div><div class="line"><a name="l00711"></a><span class="lineno"> 711</span>  std::vector<float> inputToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00712"></a><span class="lineno"> 712</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00713"></a><span class="lineno"> 713</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l00714"></a><span class="lineno"> 714</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToForgetWeightsData);</div><div class="line"><a name="l00715"></a><span class="lineno"> 715</span> </div><div class="line"><a name="l00716"></a><span class="lineno"> 716</span>  std::vector<float> inputToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00717"></a><span class="lineno"> 717</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00718"></a><span class="lineno"> 718</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l00719"></a><span class="lineno"> 719</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToCellWeightsData);</div><div class="line"><a name="l00720"></a><span class="lineno"> 720</span> </div><div class="line"><a name="l00721"></a><span class="lineno"> 721</span>  std::vector<float> inputToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00722"></a><span class="lineno"> 722</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00723"></a><span class="lineno"> 723</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l00724"></a><span class="lineno"> 724</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToOutputWeightsData);</div><div class="line"><a name="l00725"></a><span class="lineno"> 725</span> </div><div class="line"><a name="l00726"></a><span class="lineno"> 726</span>  std::vector<float> recurrentToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00727"></a><span class="lineno"> 727</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00728"></a><span class="lineno"> 728</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00729"></a><span class="lineno"> 729</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l00730"></a><span class="lineno"> 730</span> </div><div class="line"><a name="l00731"></a><span class="lineno"> 731</span>  std::vector<float> recurrentToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00732"></a><span class="lineno"> 732</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00733"></a><span class="lineno"> 733</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00734"></a><span class="lineno"> 734</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l00735"></a><span class="lineno"> 735</span> </div><div class="line"><a name="l00736"></a><span class="lineno"> 736</span>  std::vector<float> recurrentToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00737"></a><span class="lineno"> 737</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00738"></a><span class="lineno"> 738</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00739"></a><span class="lineno"> 739</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l00740"></a><span class="lineno"> 740</span> </div><div class="line"><a name="l00741"></a><span class="lineno"> 741</span>  std::vector<float> forgetGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00742"></a><span class="lineno"> 742</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00743"></a><span class="lineno"> 743</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00744"></a><span class="lineno"> 744</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), forgetGateBiasData);</div><div class="line"><a name="l00745"></a><span class="lineno"> 745</span> </div><div class="line"><a name="l00746"></a><span class="lineno"> 746</span>  std::vector<float> cellBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00747"></a><span class="lineno"> 747</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00748"></a><span class="lineno"> 748</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00749"></a><span class="lineno"> 749</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellBiasData);</div><div class="line"><a name="l00750"></a><span class="lineno"> 750</span> </div><div class="line"><a name="l00751"></a><span class="lineno"> 751</span>  std::vector<float> outputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00752"></a><span class="lineno"> 752</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00753"></a><span class="lineno"> 753</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00754"></a><span class="lineno"> 754</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), outputGateBiasData);</div><div class="line"><a name="l00755"></a><span class="lineno"> 755</span> </div><div class="line"><a name="l00756"></a><span class="lineno"> 756</span>  std::vector<float> inputToInputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00757"></a><span class="lineno"> 757</span>  std::vector<unsigned int> inputToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00758"></a><span class="lineno"> 758</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToInputWeights(</div><div class="line"><a name="l00759"></a><span class="lineno"> 759</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToInputWeightsData);</div><div class="line"><a name="l00760"></a><span class="lineno"> 760</span> </div><div class="line"><a name="l00761"></a><span class="lineno"> 761</span>  std::vector<float> recurrentToInputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00762"></a><span class="lineno"> 762</span>  std::vector<unsigned int> recurrentToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00763"></a><span class="lineno"> 763</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToInputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00764"></a><span class="lineno"> 764</span>  4, recurrentToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToInputWeightsData);</div><div class="line"><a name="l00765"></a><span class="lineno"> 765</span> </div><div class="line"><a name="l00766"></a><span class="lineno"> 766</span>  std::vector<float> cellToInputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00767"></a><span class="lineno"> 767</span>  std::vector<unsigned int> cellToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00768"></a><span class="lineno"> 768</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellToInputWeights(</div><div class="line"><a name="l00769"></a><span class="lineno"> 769</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, cellToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellToInputWeightsData);</div><div class="line"><a name="l00770"></a><span class="lineno"> 770</span> </div><div class="line"><a name="l00771"></a><span class="lineno"> 771</span>  std::vector<float> inputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00772"></a><span class="lineno"> 772</span>  std::vector<unsigned int> inputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00773"></a><span class="lineno"> 773</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputGateBias(</div><div class="line"><a name="l00774"></a><span class="lineno"> 774</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputGateBiasData);</div><div class="line"><a name="l00775"></a><span class="lineno"> 775</span> </div><div class="line"><a name="l00776"></a><span class="lineno"> 776</span>  <a class="code" href="structarmnn_1_1_lstm_input_params.xhtml">LstmInputParams</a> params;</div><div class="line"><a name="l00777"></a><span class="lineno"> 777</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l00778"></a><span class="lineno"> 778</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l00779"></a><span class="lineno"> 779</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l00780"></a><span class="lineno"> 780</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l00781"></a><span class="lineno"> 781</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l00782"></a><span class="lineno"> 782</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l00783"></a><span class="lineno"> 783</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l00784"></a><span class="lineno"> 784</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l00785"></a><span class="lineno"> 785</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l00786"></a><span class="lineno"> 786</span> </div><div class="line"><a name="l00787"></a><span class="lineno"> 787</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#affcee5f4ab5994a21bee3b78b4e43de3">m_InputToInputWeights</a> = &inputToInputWeights;</div><div class="line"><a name="l00788"></a><span class="lineno"> 788</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a435d3651482bbfcc11263b4e4e0c900f">m_RecurrentToInputWeights</a> = &recurrentToInputWeights;</div><div class="line"><a name="l00789"></a><span class="lineno"> 789</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a484bafa2f8453a7c5a4a00b92a61b006">m_CellToInputWeights</a> = &cellToInputWeights;</div><div class="line"><a name="l00790"></a><span class="lineno"> 790</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a9e081a9b94defb30d1558dc912507e0e">m_InputGateBias</a> = &inputGateBias;</div><div class="line"><a name="l00791"></a><span class="lineno"> 791</span> </div><div class="line"><a name="l00792"></a><span class="lineno"> 792</span>  <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml">TestLstmLayerVisitor</a> visitor(descriptor, params);</div><div class="line"><a name="l00793"></a><span class="lineno"> 793</span> </div><div class="line"><a name="l00794"></a><span class="lineno"> 794</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00795"></a><span class="lineno"> 795</span> </div><div class="line"><a name="l00796"></a><span class="lineno"> 796</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#ab1569dbf88b6511bde91bee3224a558c">AddLstmLayer</a>(descriptor, params);</div><div class="line"><a name="l00797"></a><span class="lineno"> 797</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00798"></a><span class="lineno"> 798</span> }</div><div class="line"><a name="l00799"></a><span class="lineno"> 799</span> </div><div class="line"><a name="l00800"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#ad956f3db79c93a658cbccb41714e1542"> 800</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedLstmLayerCifgDisabled)</div><div class="line"><a name="l00801"></a><span class="lineno"> 801</span> {</div><div class="line"><a name="l00802"></a><span class="lineno"> 802</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"LstmLayer"</span>;</div><div class="line"><a name="l00803"></a><span class="lineno"> 803</span>  <a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml">LstmDescriptor</a> descriptor;</div><div class="line"><a name="l00804"></a><span class="lineno"> 804</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ae1b07ed928036004bd257169e5aeeef4">m_ActivationFunc</a> = 3;</div><div class="line"><a name="l00805"></a><span class="lineno"> 805</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a86e88bef0df4df96df752b4b8955a3af">m_ClippingThresProj</a> = 0.5f;</div><div class="line"><a name="l00806"></a><span class="lineno"> 806</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a531a3907ec13d3772370da88030191a5">m_ClippingThresCell</a> = 0.3f;</div><div class="line"><a name="l00807"></a><span class="lineno"> 807</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ad474e5c51a0b194ef32e812b86c0cbdb">m_CifgEnabled</a> = <span class="keyword">false</span>; <span class="comment">// if this is true then we DON'T need to set the OptCifgParams</span></div><div class="line"><a name="l00808"></a><span class="lineno"> 808</span> </div><div class="line"><a name="l00809"></a><span class="lineno"> 809</span>  std::vector<float> inputToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00810"></a><span class="lineno"> 810</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00811"></a><span class="lineno"> 811</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l00812"></a><span class="lineno"> 812</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToForgetWeightsData);</div><div class="line"><a name="l00813"></a><span class="lineno"> 813</span> </div><div class="line"><a name="l00814"></a><span class="lineno"> 814</span>  std::vector<float> inputToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00815"></a><span class="lineno"> 815</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00816"></a><span class="lineno"> 816</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l00817"></a><span class="lineno"> 817</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToCellWeightsData);</div><div class="line"><a name="l00818"></a><span class="lineno"> 818</span> </div><div class="line"><a name="l00819"></a><span class="lineno"> 819</span>  std::vector<float> inputToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00820"></a><span class="lineno"> 820</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00821"></a><span class="lineno"> 821</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l00822"></a><span class="lineno"> 822</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToOutputWeightsData);</div><div class="line"><a name="l00823"></a><span class="lineno"> 823</span> </div><div class="line"><a name="l00824"></a><span class="lineno"> 824</span>  std::vector<float> recurrentToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00825"></a><span class="lineno"> 825</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00826"></a><span class="lineno"> 826</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00827"></a><span class="lineno"> 827</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l00828"></a><span class="lineno"> 828</span> </div><div class="line"><a name="l00829"></a><span class="lineno"> 829</span>  std::vector<float> recurrentToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00830"></a><span class="lineno"> 830</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00831"></a><span class="lineno"> 831</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00832"></a><span class="lineno"> 832</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l00833"></a><span class="lineno"> 833</span> </div><div class="line"><a name="l00834"></a><span class="lineno"> 834</span>  std::vector<float> recurrentToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00835"></a><span class="lineno"> 835</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00836"></a><span class="lineno"> 836</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00837"></a><span class="lineno"> 837</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l00838"></a><span class="lineno"> 838</span> </div><div class="line"><a name="l00839"></a><span class="lineno"> 839</span>  std::vector<float> forgetGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00840"></a><span class="lineno"> 840</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00841"></a><span class="lineno"> 841</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00842"></a><span class="lineno"> 842</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), forgetGateBiasData);</div><div class="line"><a name="l00843"></a><span class="lineno"> 843</span> </div><div class="line"><a name="l00844"></a><span class="lineno"> 844</span>  std::vector<float> cellBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00845"></a><span class="lineno"> 845</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00846"></a><span class="lineno"> 846</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00847"></a><span class="lineno"> 847</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellBiasData);</div><div class="line"><a name="l00848"></a><span class="lineno"> 848</span> </div><div class="line"><a name="l00849"></a><span class="lineno"> 849</span>  std::vector<float> outputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00850"></a><span class="lineno"> 850</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00851"></a><span class="lineno"> 851</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00852"></a><span class="lineno"> 852</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), outputGateBiasData);</div><div class="line"><a name="l00853"></a><span class="lineno"> 853</span> </div><div class="line"><a name="l00854"></a><span class="lineno"> 854</span>  std::vector<float> inputToInputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00855"></a><span class="lineno"> 855</span>  std::vector<unsigned int> inputToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00856"></a><span class="lineno"> 856</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToInputWeights(</div><div class="line"><a name="l00857"></a><span class="lineno"> 857</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToInputWeightsData);</div><div class="line"><a name="l00858"></a><span class="lineno"> 858</span> </div><div class="line"><a name="l00859"></a><span class="lineno"> 859</span>  std::vector<float> recurrentToInputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00860"></a><span class="lineno"> 860</span>  std::vector<unsigned int> recurrentToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00861"></a><span class="lineno"> 861</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToInputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00862"></a><span class="lineno"> 862</span>  4, recurrentToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToInputWeightsData);</div><div class="line"><a name="l00863"></a><span class="lineno"> 863</span> </div><div class="line"><a name="l00864"></a><span class="lineno"> 864</span>  std::vector<float> cellToInputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00865"></a><span class="lineno"> 865</span>  std::vector<unsigned int> cellToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00866"></a><span class="lineno"> 866</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellToInputWeights(</div><div class="line"><a name="l00867"></a><span class="lineno"> 867</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, cellToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellToInputWeightsData);</div><div class="line"><a name="l00868"></a><span class="lineno"> 868</span> </div><div class="line"><a name="l00869"></a><span class="lineno"> 869</span>  std::vector<float> inputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00870"></a><span class="lineno"> 870</span>  std::vector<unsigned int> inputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00871"></a><span class="lineno"> 871</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputGateBias(</div><div class="line"><a name="l00872"></a><span class="lineno"> 872</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputGateBiasData);</div><div class="line"><a name="l00873"></a><span class="lineno"> 873</span> </div><div class="line"><a name="l00874"></a><span class="lineno"> 874</span>  <a class="code" href="structarmnn_1_1_lstm_input_params.xhtml">LstmInputParams</a> params;</div><div class="line"><a name="l00875"></a><span class="lineno"> 875</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l00876"></a><span class="lineno"> 876</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l00877"></a><span class="lineno"> 877</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l00878"></a><span class="lineno"> 878</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l00879"></a><span class="lineno"> 879</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l00880"></a><span class="lineno"> 880</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l00881"></a><span class="lineno"> 881</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l00882"></a><span class="lineno"> 882</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l00883"></a><span class="lineno"> 883</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l00884"></a><span class="lineno"> 884</span> </div><div class="line"><a name="l00885"></a><span class="lineno"> 885</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#affcee5f4ab5994a21bee3b78b4e43de3">m_InputToInputWeights</a> = &inputToInputWeights;</div><div class="line"><a name="l00886"></a><span class="lineno"> 886</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a435d3651482bbfcc11263b4e4e0c900f">m_RecurrentToInputWeights</a> = &recurrentToInputWeights;</div><div class="line"><a name="l00887"></a><span class="lineno"> 887</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a484bafa2f8453a7c5a4a00b92a61b006">m_CellToInputWeights</a> = &cellToInputWeights;</div><div class="line"><a name="l00888"></a><span class="lineno"> 888</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a9e081a9b94defb30d1558dc912507e0e">m_InputGateBias</a> = &inputGateBias;</div><div class="line"><a name="l00889"></a><span class="lineno"> 889</span> </div><div class="line"><a name="l00890"></a><span class="lineno"> 890</span>  <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml">TestLstmLayerVisitor</a> visitor(descriptor, params, layerName);</div><div class="line"><a name="l00891"></a><span class="lineno"> 891</span> </div><div class="line"><a name="l00892"></a><span class="lineno"> 892</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00893"></a><span class="lineno"> 893</span> </div><div class="line"><a name="l00894"></a><span class="lineno"> 894</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a> *<span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#ab1569dbf88b6511bde91bee3224a558c">AddLstmLayer</a>(descriptor, params, layerName);</div><div class="line"><a name="l00895"></a><span class="lineno"> 895</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00896"></a><span class="lineno"> 896</span> }</div><div class="line"><a name="l00897"></a><span class="lineno"> 897</span> </div><div class="line"><a name="l00898"></a><span class="lineno"> 898</span> <span class="comment">// TODO add one with peephole</span></div><div class="line"><a name="l00899"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#aa524f33d3d2b294847c3929237947b20"> 899</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckLstmLayerPeephole)</div><div class="line"><a name="l00900"></a><span class="lineno"> 900</span> {</div><div class="line"><a name="l00901"></a><span class="lineno"> 901</span>  <a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml">LstmDescriptor</a> descriptor;</div><div class="line"><a name="l00902"></a><span class="lineno"> 902</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ae1b07ed928036004bd257169e5aeeef4">m_ActivationFunc</a> = 3;</div><div class="line"><a name="l00903"></a><span class="lineno"> 903</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a86e88bef0df4df96df752b4b8955a3af">m_ClippingThresProj</a> = 0.5f;</div><div class="line"><a name="l00904"></a><span class="lineno"> 904</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a531a3907ec13d3772370da88030191a5">m_ClippingThresCell</a> = 0.3f;</div><div class="line"><a name="l00905"></a><span class="lineno"> 905</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ad474e5c51a0b194ef32e812b86c0cbdb">m_CifgEnabled</a> = <span class="keyword">true</span>; <span class="comment">// if this is true then we DON'T need to set the OptCifgParams</span></div><div class="line"><a name="l00906"></a><span class="lineno"> 906</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a2837b4396f20c956952d1a7286cab5f8">m_PeepholeEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00907"></a><span class="lineno"> 907</span> </div><div class="line"><a name="l00908"></a><span class="lineno"> 908</span>  std::vector<float> inputToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00909"></a><span class="lineno"> 909</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00910"></a><span class="lineno"> 910</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l00911"></a><span class="lineno"> 911</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToForgetWeightsData);</div><div class="line"><a name="l00912"></a><span class="lineno"> 912</span> </div><div class="line"><a name="l00913"></a><span class="lineno"> 913</span>  std::vector<float> inputToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00914"></a><span class="lineno"> 914</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00915"></a><span class="lineno"> 915</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l00916"></a><span class="lineno"> 916</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToCellWeightsData);</div><div class="line"><a name="l00917"></a><span class="lineno"> 917</span> </div><div class="line"><a name="l00918"></a><span class="lineno"> 918</span>  std::vector<float> inputToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00919"></a><span class="lineno"> 919</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00920"></a><span class="lineno"> 920</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l00921"></a><span class="lineno"> 921</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToOutputWeightsData);</div><div class="line"><a name="l00922"></a><span class="lineno"> 922</span> </div><div class="line"><a name="l00923"></a><span class="lineno"> 923</span>  std::vector<float> recurrentToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00924"></a><span class="lineno"> 924</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00925"></a><span class="lineno"> 925</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00926"></a><span class="lineno"> 926</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l00927"></a><span class="lineno"> 927</span> </div><div class="line"><a name="l00928"></a><span class="lineno"> 928</span>  std::vector<float> recurrentToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00929"></a><span class="lineno"> 929</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00930"></a><span class="lineno"> 930</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00931"></a><span class="lineno"> 931</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l00932"></a><span class="lineno"> 932</span> </div><div class="line"><a name="l00933"></a><span class="lineno"> 933</span>  std::vector<float> recurrentToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00934"></a><span class="lineno"> 934</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00935"></a><span class="lineno"> 935</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00936"></a><span class="lineno"> 936</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l00937"></a><span class="lineno"> 937</span> </div><div class="line"><a name="l00938"></a><span class="lineno"> 938</span>  std::vector<float> forgetGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00939"></a><span class="lineno"> 939</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00940"></a><span class="lineno"> 940</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00941"></a><span class="lineno"> 941</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), forgetGateBiasData);</div><div class="line"><a name="l00942"></a><span class="lineno"> 942</span> </div><div class="line"><a name="l00943"></a><span class="lineno"> 943</span>  std::vector<float> cellBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00944"></a><span class="lineno"> 944</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00945"></a><span class="lineno"> 945</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00946"></a><span class="lineno"> 946</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellBiasData);</div><div class="line"><a name="l00947"></a><span class="lineno"> 947</span> </div><div class="line"><a name="l00948"></a><span class="lineno"> 948</span>  std::vector<float> outputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00949"></a><span class="lineno"> 949</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00950"></a><span class="lineno"> 950</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l00951"></a><span class="lineno"> 951</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), outputGateBiasData);</div><div class="line"><a name="l00952"></a><span class="lineno"> 952</span> </div><div class="line"><a name="l00953"></a><span class="lineno"> 953</span>  std::vector<float> cellToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00954"></a><span class="lineno"> 954</span>  std::vector<unsigned int> cellToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00955"></a><span class="lineno"> 955</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellToForgetWeights(</div><div class="line"><a name="l00956"></a><span class="lineno"> 956</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, cellToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellToForgetWeightsData);</div><div class="line"><a name="l00957"></a><span class="lineno"> 957</span> </div><div class="line"><a name="l00958"></a><span class="lineno"> 958</span>  std::vector<float> cellToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00959"></a><span class="lineno"> 959</span>  std::vector<unsigned int> cellToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00960"></a><span class="lineno"> 960</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellToOutputWeights(</div><div class="line"><a name="l00961"></a><span class="lineno"> 961</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, cellToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellToOutputWeightsData);</div><div class="line"><a name="l00962"></a><span class="lineno"> 962</span> </div><div class="line"><a name="l00963"></a><span class="lineno"> 963</span>  <a class="code" href="structarmnn_1_1_lstm_input_params.xhtml">LstmInputParams</a> params;</div><div class="line"><a name="l00964"></a><span class="lineno"> 964</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l00965"></a><span class="lineno"> 965</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l00966"></a><span class="lineno"> 966</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l00967"></a><span class="lineno"> 967</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l00968"></a><span class="lineno"> 968</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l00969"></a><span class="lineno"> 969</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l00970"></a><span class="lineno"> 970</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l00971"></a><span class="lineno"> 971</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l00972"></a><span class="lineno"> 972</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l00973"></a><span class="lineno"> 973</span> </div><div class="line"><a name="l00974"></a><span class="lineno"> 974</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a35b112e30c3eb153806a2a8c16d178e3">m_CellToForgetWeights</a> = &cellToForgetWeights;</div><div class="line"><a name="l00975"></a><span class="lineno"> 975</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#afe204ca375b74e9a72640c9227918d0a">m_CellToOutputWeights</a> = &cellToOutputWeights;</div><div class="line"><a name="l00976"></a><span class="lineno"> 976</span> </div><div class="line"><a name="l00977"></a><span class="lineno"> 977</span>  <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml">TestLstmLayerVisitor</a> visitor(descriptor, params);</div><div class="line"><a name="l00978"></a><span class="lineno"> 978</span> </div><div class="line"><a name="l00979"></a><span class="lineno"> 979</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l00980"></a><span class="lineno"> 980</span> </div><div class="line"><a name="l00981"></a><span class="lineno"> 981</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a> *<span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#ab1569dbf88b6511bde91bee3224a558c">AddLstmLayer</a>(descriptor, params);</div><div class="line"><a name="l00982"></a><span class="lineno"> 982</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l00983"></a><span class="lineno"> 983</span> }</div><div class="line"><a name="l00984"></a><span class="lineno"> 984</span> </div><div class="line"><a name="l00985"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a0f1dc6ab5dccc96c5a4df37cc5bcb923"> 985</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedLstmLayerPeephole)</div><div class="line"><a name="l00986"></a><span class="lineno"> 986</span> {</div><div class="line"><a name="l00987"></a><span class="lineno"> 987</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"LstmLayer"</span>;</div><div class="line"><a name="l00988"></a><span class="lineno"> 988</span>  <a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml">LstmDescriptor</a> descriptor;</div><div class="line"><a name="l00989"></a><span class="lineno"> 989</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ae1b07ed928036004bd257169e5aeeef4">m_ActivationFunc</a> = 3;</div><div class="line"><a name="l00990"></a><span class="lineno"> 990</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a86e88bef0df4df96df752b4b8955a3af">m_ClippingThresProj</a> = 0.5f;</div><div class="line"><a name="l00991"></a><span class="lineno"> 991</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a531a3907ec13d3772370da88030191a5">m_ClippingThresCell</a> = 0.3f;</div><div class="line"><a name="l00992"></a><span class="lineno"> 992</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ad474e5c51a0b194ef32e812b86c0cbdb">m_CifgEnabled</a> = <span class="keyword">true</span>; <span class="comment">// if this is true then we DON'T need to set the OptCifgParams</span></div><div class="line"><a name="l00993"></a><span class="lineno"> 993</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a2837b4396f20c956952d1a7286cab5f8">m_PeepholeEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l00994"></a><span class="lineno"> 994</span> </div><div class="line"><a name="l00995"></a><span class="lineno"> 995</span>  std::vector<float> inputToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l00996"></a><span class="lineno"> 996</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l00997"></a><span class="lineno"> 997</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l00998"></a><span class="lineno"> 998</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToForgetWeightsData);</div><div class="line"><a name="l00999"></a><span class="lineno"> 999</span> </div><div class="line"><a name="l01000"></a><span class="lineno"> 1000</span>  std::vector<float> inputToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01001"></a><span class="lineno"> 1001</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01002"></a><span class="lineno"> 1002</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l01003"></a><span class="lineno"> 1003</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToCellWeightsData);</div><div class="line"><a name="l01004"></a><span class="lineno"> 1004</span> </div><div class="line"><a name="l01005"></a><span class="lineno"> 1005</span>  std::vector<float> inputToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01006"></a><span class="lineno"> 1006</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01007"></a><span class="lineno"> 1007</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l01008"></a><span class="lineno"> 1008</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToOutputWeightsData);</div><div class="line"><a name="l01009"></a><span class="lineno"> 1009</span> </div><div class="line"><a name="l01010"></a><span class="lineno"> 1010</span>  std::vector<float> recurrentToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01011"></a><span class="lineno"> 1011</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01012"></a><span class="lineno"> 1012</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01013"></a><span class="lineno"> 1013</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l01014"></a><span class="lineno"> 1014</span> </div><div class="line"><a name="l01015"></a><span class="lineno"> 1015</span>  std::vector<float> recurrentToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01016"></a><span class="lineno"> 1016</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01017"></a><span class="lineno"> 1017</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01018"></a><span class="lineno"> 1018</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l01019"></a><span class="lineno"> 1019</span> </div><div class="line"><a name="l01020"></a><span class="lineno"> 1020</span>  std::vector<float> recurrentToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01021"></a><span class="lineno"> 1021</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01022"></a><span class="lineno"> 1022</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01023"></a><span class="lineno"> 1023</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l01024"></a><span class="lineno"> 1024</span> </div><div class="line"><a name="l01025"></a><span class="lineno"> 1025</span>  std::vector<float> forgetGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01026"></a><span class="lineno"> 1026</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01027"></a><span class="lineno"> 1027</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01028"></a><span class="lineno"> 1028</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), forgetGateBiasData);</div><div class="line"><a name="l01029"></a><span class="lineno"> 1029</span> </div><div class="line"><a name="l01030"></a><span class="lineno"> 1030</span>  std::vector<float> cellBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01031"></a><span class="lineno"> 1031</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01032"></a><span class="lineno"> 1032</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01033"></a><span class="lineno"> 1033</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellBiasData);</div><div class="line"><a name="l01034"></a><span class="lineno"> 1034</span> </div><div class="line"><a name="l01035"></a><span class="lineno"> 1035</span>  std::vector<float> outputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01036"></a><span class="lineno"> 1036</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01037"></a><span class="lineno"> 1037</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01038"></a><span class="lineno"> 1038</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), outputGateBiasData);</div><div class="line"><a name="l01039"></a><span class="lineno"> 1039</span> </div><div class="line"><a name="l01040"></a><span class="lineno"> 1040</span>  std::vector<float> cellToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01041"></a><span class="lineno"> 1041</span>  std::vector<unsigned int> cellToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01042"></a><span class="lineno"> 1042</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellToForgetWeights(</div><div class="line"><a name="l01043"></a><span class="lineno"> 1043</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, cellToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellToForgetWeightsData);</div><div class="line"><a name="l01044"></a><span class="lineno"> 1044</span> </div><div class="line"><a name="l01045"></a><span class="lineno"> 1045</span>  std::vector<float> cellToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01046"></a><span class="lineno"> 1046</span>  std::vector<unsigned int> cellToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01047"></a><span class="lineno"> 1047</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellToOutputWeights(</div><div class="line"><a name="l01048"></a><span class="lineno"> 1048</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, cellToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellToOutputWeightsData);</div><div class="line"><a name="l01049"></a><span class="lineno"> 1049</span> </div><div class="line"><a name="l01050"></a><span class="lineno"> 1050</span>  <a class="code" href="structarmnn_1_1_lstm_input_params.xhtml">LstmInputParams</a> params;</div><div class="line"><a name="l01051"></a><span class="lineno"> 1051</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l01052"></a><span class="lineno"> 1052</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l01053"></a><span class="lineno"> 1053</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l01054"></a><span class="lineno"> 1054</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l01055"></a><span class="lineno"> 1055</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l01056"></a><span class="lineno"> 1056</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l01057"></a><span class="lineno"> 1057</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l01058"></a><span class="lineno"> 1058</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l01059"></a><span class="lineno"> 1059</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l01060"></a><span class="lineno"> 1060</span> </div><div class="line"><a name="l01061"></a><span class="lineno"> 1061</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a35b112e30c3eb153806a2a8c16d178e3">m_CellToForgetWeights</a> = &cellToForgetWeights;</div><div class="line"><a name="l01062"></a><span class="lineno"> 1062</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#afe204ca375b74e9a72640c9227918d0a">m_CellToOutputWeights</a> = &cellToOutputWeights;</div><div class="line"><a name="l01063"></a><span class="lineno"> 1063</span> </div><div class="line"><a name="l01064"></a><span class="lineno"> 1064</span>  <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml">TestLstmLayerVisitor</a> visitor(descriptor, params, layerName);</div><div class="line"><a name="l01065"></a><span class="lineno"> 1065</span> </div><div class="line"><a name="l01066"></a><span class="lineno"> 1066</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l01067"></a><span class="lineno"> 1067</span> </div><div class="line"><a name="l01068"></a><span class="lineno"> 1068</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a> *<span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#ab1569dbf88b6511bde91bee3224a558c">AddLstmLayer</a>(descriptor, params, layerName);</div><div class="line"><a name="l01069"></a><span class="lineno"> 1069</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l01070"></a><span class="lineno"> 1070</span> }</div><div class="line"><a name="l01071"></a><span class="lineno"> 1071</span> </div><div class="line"><a name="l01072"></a><span class="lineno"> 1072</span> <span class="comment">// TODO add one with projection</span></div><div class="line"><a name="l01073"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a0d00c75b42e46b3a7dd78f9a40324c33"> 1073</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckLstmLayerProjection)</div><div class="line"><a name="l01074"></a><span class="lineno"> 1074</span> {</div><div class="line"><a name="l01075"></a><span class="lineno"> 1075</span>  <a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml">LstmDescriptor</a> descriptor;</div><div class="line"><a name="l01076"></a><span class="lineno"> 1076</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ae1b07ed928036004bd257169e5aeeef4">m_ActivationFunc</a> = 3;</div><div class="line"><a name="l01077"></a><span class="lineno"> 1077</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a86e88bef0df4df96df752b4b8955a3af">m_ClippingThresProj</a> = 0.5f;</div><div class="line"><a name="l01078"></a><span class="lineno"> 1078</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a531a3907ec13d3772370da88030191a5">m_ClippingThresCell</a> = 0.3f;</div><div class="line"><a name="l01079"></a><span class="lineno"> 1079</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ad474e5c51a0b194ef32e812b86c0cbdb">m_CifgEnabled</a> = <span class="keyword">true</span>; <span class="comment">// if this is true then we DON'T need to set the OptCifgParams</span></div><div class="line"><a name="l01080"></a><span class="lineno"> 1080</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a6c9de81fc65b3c4924cab11907075a17">m_ProjectionEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l01081"></a><span class="lineno"> 1081</span> </div><div class="line"><a name="l01082"></a><span class="lineno"> 1082</span>  std::vector<float> inputToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01083"></a><span class="lineno"> 1083</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01084"></a><span class="lineno"> 1084</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l01085"></a><span class="lineno"> 1085</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToForgetWeightsData);</div><div class="line"><a name="l01086"></a><span class="lineno"> 1086</span> </div><div class="line"><a name="l01087"></a><span class="lineno"> 1087</span>  std::vector<float> inputToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01088"></a><span class="lineno"> 1088</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01089"></a><span class="lineno"> 1089</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l01090"></a><span class="lineno"> 1090</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToCellWeightsData);</div><div class="line"><a name="l01091"></a><span class="lineno"> 1091</span> </div><div class="line"><a name="l01092"></a><span class="lineno"> 1092</span>  std::vector<float> inputToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01093"></a><span class="lineno"> 1093</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01094"></a><span class="lineno"> 1094</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l01095"></a><span class="lineno"> 1095</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToOutputWeightsData);</div><div class="line"><a name="l01096"></a><span class="lineno"> 1096</span> </div><div class="line"><a name="l01097"></a><span class="lineno"> 1097</span>  std::vector<float> recurrentToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01098"></a><span class="lineno"> 1098</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01099"></a><span class="lineno"> 1099</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01100"></a><span class="lineno"> 1100</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l01101"></a><span class="lineno"> 1101</span> </div><div class="line"><a name="l01102"></a><span class="lineno"> 1102</span>  std::vector<float> recurrentToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01103"></a><span class="lineno"> 1103</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01104"></a><span class="lineno"> 1104</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01105"></a><span class="lineno"> 1105</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l01106"></a><span class="lineno"> 1106</span> </div><div class="line"><a name="l01107"></a><span class="lineno"> 1107</span>  std::vector<float> recurrentToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01108"></a><span class="lineno"> 1108</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01109"></a><span class="lineno"> 1109</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01110"></a><span class="lineno"> 1110</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l01111"></a><span class="lineno"> 1111</span> </div><div class="line"><a name="l01112"></a><span class="lineno"> 1112</span>  std::vector<float> forgetGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01113"></a><span class="lineno"> 1113</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01114"></a><span class="lineno"> 1114</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01115"></a><span class="lineno"> 1115</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), forgetGateBiasData);</div><div class="line"><a name="l01116"></a><span class="lineno"> 1116</span> </div><div class="line"><a name="l01117"></a><span class="lineno"> 1117</span>  std::vector<float> cellBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01118"></a><span class="lineno"> 1118</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01119"></a><span class="lineno"> 1119</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01120"></a><span class="lineno"> 1120</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellBiasData);</div><div class="line"><a name="l01121"></a><span class="lineno"> 1121</span> </div><div class="line"><a name="l01122"></a><span class="lineno"> 1122</span>  std::vector<float> outputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01123"></a><span class="lineno"> 1123</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01124"></a><span class="lineno"> 1124</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01125"></a><span class="lineno"> 1125</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), outputGateBiasData);</div><div class="line"><a name="l01126"></a><span class="lineno"> 1126</span> </div><div class="line"><a name="l01127"></a><span class="lineno"> 1127</span>  std::vector<float> projectionBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01128"></a><span class="lineno"> 1128</span>  std::vector<unsigned int> projectionBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01129"></a><span class="lineno"> 1129</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> projectionBias(</div><div class="line"><a name="l01130"></a><span class="lineno"> 1130</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, projectionBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), projectionBiasData);</div><div class="line"><a name="l01131"></a><span class="lineno"> 1131</span> </div><div class="line"><a name="l01132"></a><span class="lineno"> 1132</span>  std::vector<float> projectionWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01133"></a><span class="lineno"> 1133</span>  std::vector<unsigned int> projectionWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01134"></a><span class="lineno"> 1134</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> projectionWeights(</div><div class="line"><a name="l01135"></a><span class="lineno"> 1135</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, projectionWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), projectionWeightsData);</div><div class="line"><a name="l01136"></a><span class="lineno"> 1136</span> </div><div class="line"><a name="l01137"></a><span class="lineno"> 1137</span>  <a class="code" href="structarmnn_1_1_lstm_input_params.xhtml">LstmInputParams</a> params;</div><div class="line"><a name="l01138"></a><span class="lineno"> 1138</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l01139"></a><span class="lineno"> 1139</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l01140"></a><span class="lineno"> 1140</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l01141"></a><span class="lineno"> 1141</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l01142"></a><span class="lineno"> 1142</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l01143"></a><span class="lineno"> 1143</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l01144"></a><span class="lineno"> 1144</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l01145"></a><span class="lineno"> 1145</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l01146"></a><span class="lineno"> 1146</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l01147"></a><span class="lineno"> 1147</span> </div><div class="line"><a name="l01148"></a><span class="lineno"> 1148</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ab03e6e1514f74427916c892f473fe04c">m_ProjectionWeights</a> = &projectionWeights;</div><div class="line"><a name="l01149"></a><span class="lineno"> 1149</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a44b0e6b16708df7f0d2bbab141688aaa">m_ProjectionBias</a> = &projectionBias;</div><div class="line"><a name="l01150"></a><span class="lineno"> 1150</span> </div><div class="line"><a name="l01151"></a><span class="lineno"> 1151</span>  <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml">TestLstmLayerVisitor</a> visitor(descriptor, params);</div><div class="line"><a name="l01152"></a><span class="lineno"> 1152</span> </div><div class="line"><a name="l01153"></a><span class="lineno"> 1153</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l01154"></a><span class="lineno"> 1154</span> </div><div class="line"><a name="l01155"></a><span class="lineno"> 1155</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a> *<span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#ab1569dbf88b6511bde91bee3224a558c">AddLstmLayer</a>(descriptor, params);</div><div class="line"><a name="l01156"></a><span class="lineno"> 1156</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l01157"></a><span class="lineno"> 1157</span> }</div><div class="line"><a name="l01158"></a><span class="lineno"> 1158</span> </div><div class="line"><a name="l01159"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a3a3105d08231d5f2e53511bab46224c9"> 1159</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedLstmLayerProjection)</div><div class="line"><a name="l01160"></a><span class="lineno"> 1160</span> {</div><div class="line"><a name="l01161"></a><span class="lineno"> 1161</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"LstmLayer"</span>;</div><div class="line"><a name="l01162"></a><span class="lineno"> 1162</span>  <a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml">LstmDescriptor</a> descriptor;</div><div class="line"><a name="l01163"></a><span class="lineno"> 1163</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ae1b07ed928036004bd257169e5aeeef4">m_ActivationFunc</a> = 3;</div><div class="line"><a name="l01164"></a><span class="lineno"> 1164</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a86e88bef0df4df96df752b4b8955a3af">m_ClippingThresProj</a> = 0.5f;</div><div class="line"><a name="l01165"></a><span class="lineno"> 1165</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a531a3907ec13d3772370da88030191a5">m_ClippingThresCell</a> = 0.3f;</div><div class="line"><a name="l01166"></a><span class="lineno"> 1166</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#ad474e5c51a0b194ef32e812b86c0cbdb">m_CifgEnabled</a> = <span class="keyword">true</span>; <span class="comment">// if this is true then we DON'T need to set the OptCifgParams</span></div><div class="line"><a name="l01167"></a><span class="lineno"> 1167</span>  descriptor.<a class="code" href="structarmnn_1_1_lstm_descriptor.xhtml#a6c9de81fc65b3c4924cab11907075a17">m_ProjectionEnabled</a> = <span class="keyword">true</span>;</div><div class="line"><a name="l01168"></a><span class="lineno"> 1168</span> </div><div class="line"><a name="l01169"></a><span class="lineno"> 1169</span>  std::vector<float> inputToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01170"></a><span class="lineno"> 1170</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01171"></a><span class="lineno"> 1171</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l01172"></a><span class="lineno"> 1172</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToForgetWeightsData);</div><div class="line"><a name="l01173"></a><span class="lineno"> 1173</span> </div><div class="line"><a name="l01174"></a><span class="lineno"> 1174</span>  std::vector<float> inputToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01175"></a><span class="lineno"> 1175</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01176"></a><span class="lineno"> 1176</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l01177"></a><span class="lineno"> 1177</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToCellWeightsData);</div><div class="line"><a name="l01178"></a><span class="lineno"> 1178</span> </div><div class="line"><a name="l01179"></a><span class="lineno"> 1179</span>  std::vector<float> inputToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01180"></a><span class="lineno"> 1180</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01181"></a><span class="lineno"> 1181</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l01182"></a><span class="lineno"> 1182</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), inputToOutputWeightsData);</div><div class="line"><a name="l01183"></a><span class="lineno"> 1183</span> </div><div class="line"><a name="l01184"></a><span class="lineno"> 1184</span>  std::vector<float> recurrentToForgetWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01185"></a><span class="lineno"> 1185</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01186"></a><span class="lineno"> 1186</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01187"></a><span class="lineno"> 1187</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l01188"></a><span class="lineno"> 1188</span> </div><div class="line"><a name="l01189"></a><span class="lineno"> 1189</span>  std::vector<float> recurrentToCellWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01190"></a><span class="lineno"> 1190</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01191"></a><span class="lineno"> 1191</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01192"></a><span class="lineno"> 1192</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l01193"></a><span class="lineno"> 1193</span> </div><div class="line"><a name="l01194"></a><span class="lineno"> 1194</span>  std::vector<float> recurrentToOutputWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01195"></a><span class="lineno"> 1195</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01196"></a><span class="lineno"> 1196</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01197"></a><span class="lineno"> 1197</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l01198"></a><span class="lineno"> 1198</span> </div><div class="line"><a name="l01199"></a><span class="lineno"> 1199</span>  std::vector<float> forgetGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01200"></a><span class="lineno"> 1200</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01201"></a><span class="lineno"> 1201</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01202"></a><span class="lineno"> 1202</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), forgetGateBiasData);</div><div class="line"><a name="l01203"></a><span class="lineno"> 1203</span> </div><div class="line"><a name="l01204"></a><span class="lineno"> 1204</span>  std::vector<float> cellBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01205"></a><span class="lineno"> 1205</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01206"></a><span class="lineno"> 1206</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01207"></a><span class="lineno"> 1207</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), cellBiasData);</div><div class="line"><a name="l01208"></a><span class="lineno"> 1208</span> </div><div class="line"><a name="l01209"></a><span class="lineno"> 1209</span>  std::vector<float> outputGateBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01210"></a><span class="lineno"> 1210</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01211"></a><span class="lineno"> 1211</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01212"></a><span class="lineno"> 1212</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), outputGateBiasData);</div><div class="line"><a name="l01213"></a><span class="lineno"> 1213</span> </div><div class="line"><a name="l01214"></a><span class="lineno"> 1214</span>  std::vector<float> projectionBiasData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01215"></a><span class="lineno"> 1215</span>  std::vector<unsigned int> projectionBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01216"></a><span class="lineno"> 1216</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> projectionBias(</div><div class="line"><a name="l01217"></a><span class="lineno"> 1217</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, projectionBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), projectionBiasData);</div><div class="line"><a name="l01218"></a><span class="lineno"> 1218</span> </div><div class="line"><a name="l01219"></a><span class="lineno"> 1219</span>  std::vector<float> projectionWeightsData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0};</div><div class="line"><a name="l01220"></a><span class="lineno"> 1220</span>  std::vector<unsigned int> projectionWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01221"></a><span class="lineno"> 1221</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> projectionWeights(</div><div class="line"><a name="l01222"></a><span class="lineno"> 1222</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, projectionWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a166495adc0d0f53bee6baecc577f5204">DataType::Float32</a>), projectionWeightsData);</div><div class="line"><a name="l01223"></a><span class="lineno"> 1223</span> </div><div class="line"><a name="l01224"></a><span class="lineno"> 1224</span>  <a class="code" href="structarmnn_1_1_lstm_input_params.xhtml">LstmInputParams</a> params;</div><div class="line"><a name="l01225"></a><span class="lineno"> 1225</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l01226"></a><span class="lineno"> 1226</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l01227"></a><span class="lineno"> 1227</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l01228"></a><span class="lineno"> 1228</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l01229"></a><span class="lineno"> 1229</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l01230"></a><span class="lineno"> 1230</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l01231"></a><span class="lineno"> 1231</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l01232"></a><span class="lineno"> 1232</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l01233"></a><span class="lineno"> 1233</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l01234"></a><span class="lineno"> 1234</span> </div><div class="line"><a name="l01235"></a><span class="lineno"> 1235</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#ab03e6e1514f74427916c892f473fe04c">m_ProjectionWeights</a> = &projectionWeights;</div><div class="line"><a name="l01236"></a><span class="lineno"> 1236</span>  params.<a class="code" href="structarmnn_1_1_lstm_input_params.xhtml#a44b0e6b16708df7f0d2bbab141688aaa">m_ProjectionBias</a> = &projectionBias;</div><div class="line"><a name="l01237"></a><span class="lineno"> 1237</span> </div><div class="line"><a name="l01238"></a><span class="lineno"> 1238</span>  <a class="code" href="classarmnn_1_1_test_lstm_layer_visitor.xhtml">TestLstmLayerVisitor</a> visitor(descriptor, params, layerName);</div><div class="line"><a name="l01239"></a><span class="lineno"> 1239</span> </div><div class="line"><a name="l01240"></a><span class="lineno"> 1240</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l01241"></a><span class="lineno"> 1241</span> </div><div class="line"><a name="l01242"></a><span class="lineno"> 1242</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a> *<span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#ab1569dbf88b6511bde91bee3224a558c">AddLstmLayer</a>(descriptor, params, layerName);</div><div class="line"><a name="l01243"></a><span class="lineno"> 1243</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l01244"></a><span class="lineno"> 1244</span> }</div><div class="line"><a name="l01245"></a><span class="lineno"> 1245</span> </div><div class="line"><a name="l01246"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a84e5356296be66aa930ec53118f5ef6b"> 1246</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckQuantizedLstmLayer)</div><div class="line"><a name="l01247"></a><span class="lineno"> 1247</span> {</div><div class="line"><a name="l01248"></a><span class="lineno"> 1248</span>  std::vector<uint8_t> inputToInputWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01249"></a><span class="lineno"> 1249</span>  std::vector<unsigned int> inputToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01250"></a><span class="lineno"> 1250</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToInputWeights(</div><div class="line"><a name="l01251"></a><span class="lineno"> 1251</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), inputToInputWeightsData);</div><div class="line"><a name="l01252"></a><span class="lineno"> 1252</span> </div><div class="line"><a name="l01253"></a><span class="lineno"> 1253</span>  std::vector<uint8_t> inputToForgetWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01254"></a><span class="lineno"> 1254</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01255"></a><span class="lineno"> 1255</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l01256"></a><span class="lineno"> 1256</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), inputToForgetWeightsData);</div><div class="line"><a name="l01257"></a><span class="lineno"> 1257</span> </div><div class="line"><a name="l01258"></a><span class="lineno"> 1258</span>  std::vector<uint8_t> inputToCellWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01259"></a><span class="lineno"> 1259</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01260"></a><span class="lineno"> 1260</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l01261"></a><span class="lineno"> 1261</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), inputToCellWeightsData);</div><div class="line"><a name="l01262"></a><span class="lineno"> 1262</span> </div><div class="line"><a name="l01263"></a><span class="lineno"> 1263</span>  std::vector<uint8_t> inputToOutputWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01264"></a><span class="lineno"> 1264</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01265"></a><span class="lineno"> 1265</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l01266"></a><span class="lineno"> 1266</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), inputToOutputWeightsData);</div><div class="line"><a name="l01267"></a><span class="lineno"> 1267</span> </div><div class="line"><a name="l01268"></a><span class="lineno"> 1268</span> </div><div class="line"><a name="l01269"></a><span class="lineno"> 1269</span>  std::vector<uint8_t> recurrentToInputWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01270"></a><span class="lineno"> 1270</span>  std::vector<unsigned int> recurrentToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01271"></a><span class="lineno"> 1271</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToInputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01272"></a><span class="lineno"> 1272</span>  4, recurrentToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), recurrentToInputWeightsData);</div><div class="line"><a name="l01273"></a><span class="lineno"> 1273</span> </div><div class="line"><a name="l01274"></a><span class="lineno"> 1274</span>  std::vector<uint8_t> recurrentToForgetWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01275"></a><span class="lineno"> 1275</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01276"></a><span class="lineno"> 1276</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01277"></a><span class="lineno"> 1277</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l01278"></a><span class="lineno"> 1278</span> </div><div class="line"><a name="l01279"></a><span class="lineno"> 1279</span>  std::vector<uint8_t> recurrentToCellWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01280"></a><span class="lineno"> 1280</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01281"></a><span class="lineno"> 1281</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01282"></a><span class="lineno"> 1282</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l01283"></a><span class="lineno"> 1283</span> </div><div class="line"><a name="l01284"></a><span class="lineno"> 1284</span>  std::vector<uint8_t> recurrentToOutputWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01285"></a><span class="lineno"> 1285</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01286"></a><span class="lineno"> 1286</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01287"></a><span class="lineno"> 1287</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l01288"></a><span class="lineno"> 1288</span> </div><div class="line"><a name="l01289"></a><span class="lineno"> 1289</span> </div><div class="line"><a name="l01290"></a><span class="lineno"> 1290</span>  std::vector<int32_t> inputGateBiasData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01291"></a><span class="lineno"> 1291</span>  std::vector<unsigned int> inputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01292"></a><span class="lineno"> 1292</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputGateBias(</div><div class="line"><a name="l01293"></a><span class="lineno"> 1293</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6accedffbc6e5308e33d3843e8bdc0dad7">DataType::Signed32</a>), inputGateBiasData);</div><div class="line"><a name="l01294"></a><span class="lineno"> 1294</span> </div><div class="line"><a name="l01295"></a><span class="lineno"> 1295</span>  std::vector<int32_t> forgetGateBiasData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01296"></a><span class="lineno"> 1296</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01297"></a><span class="lineno"> 1297</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01298"></a><span class="lineno"> 1298</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6accedffbc6e5308e33d3843e8bdc0dad7">DataType::Signed32</a>), forgetGateBiasData);</div><div class="line"><a name="l01299"></a><span class="lineno"> 1299</span> </div><div class="line"><a name="l01300"></a><span class="lineno"> 1300</span>  std::vector<int32_t> cellBiasData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01301"></a><span class="lineno"> 1301</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01302"></a><span class="lineno"> 1302</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01303"></a><span class="lineno"> 1303</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6accedffbc6e5308e33d3843e8bdc0dad7">DataType::Signed32</a>), cellBiasData);</div><div class="line"><a name="l01304"></a><span class="lineno"> 1304</span> </div><div class="line"><a name="l01305"></a><span class="lineno"> 1305</span>  std::vector<int32_t> outputGateBiasData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01306"></a><span class="lineno"> 1306</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01307"></a><span class="lineno"> 1307</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01308"></a><span class="lineno"> 1308</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6accedffbc6e5308e33d3843e8bdc0dad7">DataType::Signed32</a>), outputGateBiasData);</div><div class="line"><a name="l01309"></a><span class="lineno"> 1309</span> </div><div class="line"><a name="l01310"></a><span class="lineno"> 1310</span>  <a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml">QuantizedLstmInputParams</a> params;</div><div class="line"><a name="l01311"></a><span class="lineno"> 1311</span> </div><div class="line"><a name="l01312"></a><span class="lineno"> 1312</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#affcee5f4ab5994a21bee3b78b4e43de3">m_InputToInputWeights</a> = &inputToInputWeights;</div><div class="line"><a name="l01313"></a><span class="lineno"> 1313</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l01314"></a><span class="lineno"> 1314</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l01315"></a><span class="lineno"> 1315</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l01316"></a><span class="lineno"> 1316</span> </div><div class="line"><a name="l01317"></a><span class="lineno"> 1317</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a435d3651482bbfcc11263b4e4e0c900f">m_RecurrentToInputWeights</a> = &recurrentToInputWeights;</div><div class="line"><a name="l01318"></a><span class="lineno"> 1318</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l01319"></a><span class="lineno"> 1319</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l01320"></a><span class="lineno"> 1320</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l01321"></a><span class="lineno"> 1321</span> </div><div class="line"><a name="l01322"></a><span class="lineno"> 1322</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a9e081a9b94defb30d1558dc912507e0e">m_InputGateBias</a> = &inputGateBias;</div><div class="line"><a name="l01323"></a><span class="lineno"> 1323</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l01324"></a><span class="lineno"> 1324</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l01325"></a><span class="lineno"> 1325</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l01326"></a><span class="lineno"> 1326</span> </div><div class="line"><a name="l01327"></a><span class="lineno"> 1327</span>  <a class="code" href="classarmnn_1_1_test_quantized_lstm_layer_visitor.xhtml">TestQuantizedLstmLayerVisitor</a> visitor(params);</div><div class="line"><a name="l01328"></a><span class="lineno"> 1328</span> </div><div class="line"><a name="l01329"></a><span class="lineno"> 1329</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l01330"></a><span class="lineno"> 1330</span> </div><div class="line"><a name="l01331"></a><span class="lineno"> 1331</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a6a6657fdd77cabea7a9e0a740635735e">AddQuantizedLstmLayer</a>(params);</div><div class="line"><a name="l01332"></a><span class="lineno"> 1332</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l01333"></a><span class="lineno"> 1333</span> }</div><div class="line"><a name="l01334"></a><span class="lineno"> 1334</span> </div><div class="line"><a name="l01335"></a><span class="lineno"><a class="line" href="namespacearmnn.xhtml#a492fae0605d06684297540bb9af319dc"> 1335</a></span> <a class="code" href="namespacearmnn.xhtml#a10d15f3df1ab52b3b915a4be1dbf386b">BOOST_AUTO_TEST_CASE</a>(CheckNamedQuantizedLstmLayer)</div><div class="line"><a name="l01336"></a><span class="lineno"> 1336</span> {</div><div class="line"><a name="l01337"></a><span class="lineno"> 1337</span>  <span class="keyword">const</span> <span class="keywordtype">char</span>* layerName = <span class="stringliteral">"LstmLayer"</span>;</div><div class="line"><a name="l01338"></a><span class="lineno"> 1338</span>  std::vector<uint8_t> inputToInputWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01339"></a><span class="lineno"> 1339</span>  std::vector<unsigned int> inputToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01340"></a><span class="lineno"> 1340</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToInputWeights(</div><div class="line"><a name="l01341"></a><span class="lineno"> 1341</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), inputToInputWeightsData);</div><div class="line"><a name="l01342"></a><span class="lineno"> 1342</span> </div><div class="line"><a name="l01343"></a><span class="lineno"> 1343</span>  std::vector<uint8_t> inputToForgetWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01344"></a><span class="lineno"> 1344</span>  std::vector<unsigned int> inputToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01345"></a><span class="lineno"> 1345</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToForgetWeights(</div><div class="line"><a name="l01346"></a><span class="lineno"> 1346</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), inputToForgetWeightsData);</div><div class="line"><a name="l01347"></a><span class="lineno"> 1347</span> </div><div class="line"><a name="l01348"></a><span class="lineno"> 1348</span>  std::vector<uint8_t> inputToCellWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01349"></a><span class="lineno"> 1349</span>  std::vector<unsigned int> inputToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01350"></a><span class="lineno"> 1350</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToCellWeights(</div><div class="line"><a name="l01351"></a><span class="lineno"> 1351</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), inputToCellWeightsData);</div><div class="line"><a name="l01352"></a><span class="lineno"> 1352</span> </div><div class="line"><a name="l01353"></a><span class="lineno"> 1353</span>  std::vector<uint8_t> inputToOutputWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01354"></a><span class="lineno"> 1354</span>  std::vector<unsigned int> inputToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01355"></a><span class="lineno"> 1355</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputToOutputWeights(</div><div class="line"><a name="l01356"></a><span class="lineno"> 1356</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), inputToOutputWeightsData);</div><div class="line"><a name="l01357"></a><span class="lineno"> 1357</span> </div><div class="line"><a name="l01358"></a><span class="lineno"> 1358</span> </div><div class="line"><a name="l01359"></a><span class="lineno"> 1359</span>  std::vector<uint8_t> recurrentToInputWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01360"></a><span class="lineno"> 1360</span>  std::vector<unsigned int> recurrentToInputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01361"></a><span class="lineno"> 1361</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToInputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01362"></a><span class="lineno"> 1362</span>  4, recurrentToInputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), recurrentToInputWeightsData);</div><div class="line"><a name="l01363"></a><span class="lineno"> 1363</span> </div><div class="line"><a name="l01364"></a><span class="lineno"> 1364</span>  std::vector<uint8_t> recurrentToForgetWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01365"></a><span class="lineno"> 1365</span>  std::vector<unsigned int> recurrentToForgetWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01366"></a><span class="lineno"> 1366</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToForgetWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01367"></a><span class="lineno"> 1367</span>  4, recurrentToForgetWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), recurrentToForgetWeightsData);</div><div class="line"><a name="l01368"></a><span class="lineno"> 1368</span> </div><div class="line"><a name="l01369"></a><span class="lineno"> 1369</span>  std::vector<uint8_t> recurrentToCellWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01370"></a><span class="lineno"> 1370</span>  std::vector<unsigned int> recurrentToCellWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01371"></a><span class="lineno"> 1371</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToCellWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01372"></a><span class="lineno"> 1372</span>  4, recurrentToCellWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), recurrentToCellWeightsData);</div><div class="line"><a name="l01373"></a><span class="lineno"> 1373</span> </div><div class="line"><a name="l01374"></a><span class="lineno"> 1374</span>  std::vector<uint8_t> recurrentToOutputWeightsData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01375"></a><span class="lineno"> 1375</span>  std::vector<unsigned int> recurrentToOutputWeightsDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01376"></a><span class="lineno"> 1376</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> recurrentToOutputWeights(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01377"></a><span class="lineno"> 1377</span>  4, recurrentToOutputWeightsDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6a0a3f57c876f5a230244c38e1453a8a6e">DataType::QAsymmU8</a>), recurrentToOutputWeightsData);</div><div class="line"><a name="l01378"></a><span class="lineno"> 1378</span> </div><div class="line"><a name="l01379"></a><span class="lineno"> 1379</span> </div><div class="line"><a name="l01380"></a><span class="lineno"> 1380</span>  std::vector<int32_t> inputGateBiasData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01381"></a><span class="lineno"> 1381</span>  std::vector<unsigned int> inputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01382"></a><span class="lineno"> 1382</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> inputGateBias(</div><div class="line"><a name="l01383"></a><span class="lineno"> 1383</span>  <a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(4, inputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6accedffbc6e5308e33d3843e8bdc0dad7">DataType::Signed32</a>), inputGateBiasData);</div><div class="line"><a name="l01384"></a><span class="lineno"> 1384</span> </div><div class="line"><a name="l01385"></a><span class="lineno"> 1385</span>  std::vector<int32_t> forgetGateBiasData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01386"></a><span class="lineno"> 1386</span>  std::vector<unsigned int> forgetGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01387"></a><span class="lineno"> 1387</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> forgetGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01388"></a><span class="lineno"> 1388</span>  4, forgetGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6accedffbc6e5308e33d3843e8bdc0dad7">DataType::Signed32</a>), forgetGateBiasData);</div><div class="line"><a name="l01389"></a><span class="lineno"> 1389</span> </div><div class="line"><a name="l01390"></a><span class="lineno"> 1390</span>  std::vector<int32_t> cellBiasData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01391"></a><span class="lineno"> 1391</span>  std::vector<unsigned int> cellBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01392"></a><span class="lineno"> 1392</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> cellBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01393"></a><span class="lineno"> 1393</span>  4, cellBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6accedffbc6e5308e33d3843e8bdc0dad7">DataType::Signed32</a>), cellBiasData);</div><div class="line"><a name="l01394"></a><span class="lineno"> 1394</span> </div><div class="line"><a name="l01395"></a><span class="lineno"> 1395</span>  std::vector<int32_t> outputGateBiasData = {1, 2, 3, 4, 5, 6, 7, 8, 9};</div><div class="line"><a name="l01396"></a><span class="lineno"> 1396</span>  std::vector<unsigned int> outputGateBiasDimensions = {1, 1, 3, 3};</div><div class="line"><a name="l01397"></a><span class="lineno"> 1397</span>  <a class="code" href="classarmnn_1_1_const_tensor.xhtml">ConstTensor</a> outputGateBias(<a class="code" href="classarmnn_1_1_tensor_info.xhtml">TensorInfo</a>(</div><div class="line"><a name="l01398"></a><span class="lineno"> 1398</span>  4, outputGateBiasDimensions.data(), <a class="code" href="namespacearmnn.xhtml#ad8ed01ff3ff33333d8e19db4d2818bb6accedffbc6e5308e33d3843e8bdc0dad7">DataType::Signed32</a>), outputGateBiasData);</div><div class="line"><a name="l01399"></a><span class="lineno"> 1399</span> </div><div class="line"><a name="l01400"></a><span class="lineno"> 1400</span>  <a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml">QuantizedLstmInputParams</a> params;</div><div class="line"><a name="l01401"></a><span class="lineno"> 1401</span> </div><div class="line"><a name="l01402"></a><span class="lineno"> 1402</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#affcee5f4ab5994a21bee3b78b4e43de3">m_InputToInputWeights</a> = &inputToInputWeights;</div><div class="line"><a name="l01403"></a><span class="lineno"> 1403</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a31da1ead6794dd64571afdd0b6efc771">m_InputToForgetWeights</a> = &inputToForgetWeights;</div><div class="line"><a name="l01404"></a><span class="lineno"> 1404</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a49e11acda22742cbaf6f1b259ead0d84">m_InputToCellWeights</a> = &inputToCellWeights;</div><div class="line"><a name="l01405"></a><span class="lineno"> 1405</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a6e30c7b3451da3ea9cf4259fb602e6e6">m_InputToOutputWeights</a> = &inputToOutputWeights;</div><div class="line"><a name="l01406"></a><span class="lineno"> 1406</span> </div><div class="line"><a name="l01407"></a><span class="lineno"> 1407</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a435d3651482bbfcc11263b4e4e0c900f">m_RecurrentToInputWeights</a> = &recurrentToInputWeights;</div><div class="line"><a name="l01408"></a><span class="lineno"> 1408</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#ae83131e16df1cace69395a5f99bc5ecb">m_RecurrentToForgetWeights</a> = &recurrentToForgetWeights;</div><div class="line"><a name="l01409"></a><span class="lineno"> 1409</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a1759754ccb88ecc9af44f3aae6e244ee">m_RecurrentToCellWeights</a> = &recurrentToCellWeights;</div><div class="line"><a name="l01410"></a><span class="lineno"> 1410</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a56b81ca8ba4b4937e0787e4951f043fc">m_RecurrentToOutputWeights</a> = &recurrentToOutputWeights;</div><div class="line"><a name="l01411"></a><span class="lineno"> 1411</span> </div><div class="line"><a name="l01412"></a><span class="lineno"> 1412</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a9e081a9b94defb30d1558dc912507e0e">m_InputGateBias</a> = &inputGateBias;</div><div class="line"><a name="l01413"></a><span class="lineno"> 1413</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#ace7a1f1f1041b412b7d8ef82b95ff352">m_ForgetGateBias</a> = &forgetGateBias;</div><div class="line"><a name="l01414"></a><span class="lineno"> 1414</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a4a9d678146f572808a361dbdc5489f38">m_CellBias</a> = &cellBias;</div><div class="line"><a name="l01415"></a><span class="lineno"> 1415</span>  params.<a class="code" href="structarmnn_1_1_quantized_lstm_input_params.xhtml#a8c0f6d48705f40c5590dde09be262222">m_OutputGateBias</a> = &outputGateBias;</div><div class="line"><a name="l01416"></a><span class="lineno"> 1416</span> </div><div class="line"><a name="l01417"></a><span class="lineno"> 1417</span>  <a class="code" href="classarmnn_1_1_test_quantized_lstm_layer_visitor.xhtml">TestQuantizedLstmLayerVisitor</a> visitor(params, layerName);</div><div class="line"><a name="l01418"></a><span class="lineno"> 1418</span> </div><div class="line"><a name="l01419"></a><span class="lineno"> 1419</span>  <a class="code" href="classarmnn_1_1_network.xhtml">Network</a> net;</div><div class="line"><a name="l01420"></a><span class="lineno"> 1420</span> </div><div class="line"><a name="l01421"></a><span class="lineno"> 1421</span>  <a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml">IConnectableLayer</a>* <span class="keyword">const</span> layer = net.<a class="code" href="classarmnn_1_1_network.xhtml#a6a6657fdd77cabea7a9e0a740635735e">AddQuantizedLstmLayer</a>(params, layerName);</div><div class="line"><a name="l01422"></a><span class="lineno"> 1422</span>  layer-><a class="code" href="classarmnn_1_1_i_connectable_layer.xhtml#a8c9198a992b02e61a6777329d487dde3">Accept</a>(visitor);</div><div class="line"><a name="l01423"></a><span class="lineno"> 1423</span> }</div><div class="line"><a name="l01424"></a><span class="lineno"> 1424</span> </div><div class="line"><a name="l01425"></a><span class="lineno"> 1425</span> <a class="code" href="_profiler_tests_8cpp.xhtml#af7f71af5c6c124222dd1c42c5df892f4">BOOST_AUTO_TEST_SUITE_END</a>()</div><div class="line"><a name="l01426"></a><span class="lineno"> 1426</span> </div><div class="line"><a name="l01427"></a><span class="lineno"> 1427</span> } <span class="comment">// namespace armnn</span></div><div class="ttc" id="classarmnn_1_1_test_batch_normalization_layer_visitor_xhtml_abb0d5c2c24fc8c43d01e0fe503df2e93"><div class="ttname"><a href="classarmnn_1_1_test_batch_normalization_layer_visitor.xhtml#abb0d5c2c24fc8c43d01e0fe503df2e93">armnn::TestBatchNormalizationLayerVisitor::CheckDescriptor</a></div><div class="ttdeci">void CheckDescriptor(const BatchNormalizationDescriptor &descriptor)</div><div class="ttdef"><b>Definition:</b> <a href="_const_tensor_layer_visitor_8cpp_source.xhtml#l00045">ConstTensorLayerVisitor.cpp:45</a></div></div> |