http://www.cslt.org/mediawiki/index.php?action=history&feed=atom&title=FreeNeb_ViviQA_Release-v1.1 2026-04-20T06:40:00Z 本wiki的该页面的版本历史 MediaWiki 1.23.3 http://www.cslt.org/mediawiki/index.php?title=FreeNeb_ViviQA_Release-v1.1&diff=27318&oldid=prev 2017-06-02T09:44:19Z

<p></p> <table class='diff diff-contentalign-left'> <col class='diff-marker' /> <col class='diff-content' /> <col class='diff-marker' /> <col class='diff-content' /> <tr style='vertical-align: top;'> <td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td> <td colspan='2' style="background-color: white; color:black; text-align: center;">2017年6月2日 (五) 09:44的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第1行：</td> <td colspan="2" class="diff-lineno">第1行：</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>&lt;pre&gt;</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>&lt;pre&gt;</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>RELEASE TITLE: vvQA-CDSSM-HUILAN &#160;</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>RELEASE TITLE: vvQA-CDSSM-HUILAN &#160;</div></td></tr> <tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>RELEASE VERSION: v1.<del class="diffchange diffchange-inline">0</del></div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>RELEASE VERSION: v1.<ins class="diffchange diffchange-inline">1</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>RELEASE TYPE: MAIN RELEASE</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>RELEASE TYPE: MAIN RELEASE</div></td></tr> <tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>RELEASE LOCATION: /work5/release/baizw/vvQA-CDSSM-HUILAN-v1.<del class="diffchange diffchange-inline">0</del></div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>RELEASE LOCATION: /work5/release/baizw/vvQA-CDSSM-HUILAN-v1.<ins class="diffchange diffchange-inline">1</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>RELATED BUGDB: 16</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>RELATED BUGDB: 16</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>RELEASE TIME: 2017/01/06</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>RELEASE TIME: 2017/01/06</div></td></tr> </table>

Cslt http://www.cslt.org/mediawiki/index.php?title=FreeNeb_ViviQA_Release-v1.1&diff=27317&oldid=prev 2017-06-02T09:43:55Z

<p></p> <table class='diff diff-contentalign-left'> <col class='diff-marker' /> <col class='diff-content' /> <col class='diff-marker' /> <col class='diff-content' /> <tr style='vertical-align: top;'> <td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td> <td colspan='2' style="background-color: white; color:black; text-align: center;">2017年6月2日 (五) 09:43的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第16行：</td> <td colspan="2" class="diff-lineno">第16行：</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. TECHNOLOGY SUMMARY:</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. TECHNOLOGY SUMMARY:</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>本发布基于CDSSM模型，以三组CNN通过不同窗口长度得到三组特征向量，拼接后经过全连接层给出句子向量。训练采用对比递度下降。具体技术文档见[[<del class="diffchange diffchange-inline">文件</del>:基于深度神经网路的检索相似问题模型.v4.pdf]]。</div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>本发布基于CDSSM模型，以三组CNN通过不同窗口长度得到三组特征向量，拼接后经过全连接层给出句子向量。训练采用对比递度下降。具体技术文档见[[<ins class="diffchange diffchange-inline">媒体文件</ins>:基于深度神经网路的检索相似问题模型.v4.pdf]]。</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> </table>

Cslt http://www.cslt.org/mediawiki/index.php?title=FreeNeb_ViviQA_Release-v1.1&diff=27316&oldid=prev 2017-06-02T09:43:40Z

<p></p> <table class='diff diff-contentalign-left'> <col class='diff-marker' /> <col class='diff-content' /> <col class='diff-marker' /> <col class='diff-content' /> <tr style='vertical-align: top;'> <td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td> <td colspan='2' style="background-color: white; color:black; text-align: center;">2017年6月2日 (五) 09:43的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第16行：</td> <td colspan="2" class="diff-lineno">第16行：</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. TECHNOLOGY SUMMARY:</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. TECHNOLOGY SUMMARY:</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>本发布基于CDSSM模型，以三组CNN通过不同窗口长度得到三组特征向量，拼接后经过全连接层给出句子向量。训练采用对比递度下降。具体技术文档见[[<del class="diffchange diffchange-inline">媒体文件</del>:基于深度神经网路的检索相似问题模型.v4.pdf]]。</div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>本发布基于CDSSM模型，以三组CNN通过不同窗口长度得到三组特征向量，拼接后经过全连接层给出句子向量。训练采用对比递度下降。具体技术文档见[[<ins class="diffchange diffchange-inline">文件</ins>:基于深度神经网路的检索相似问题模型.v4.pdf]]。</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> </table>

Cslt http://www.cslt.org/mediawiki/index.php?title=FreeNeb_ViviQA_Release-v1.1&diff=27315&oldid=prev 2017-06-02T09:43:29Z

<p></p> <table class='diff diff-contentalign-left'> <col class='diff-marker' /> <col class='diff-content' /> <col class='diff-marker' /> <col class='diff-content' /> <tr style='vertical-align: top;'> <td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td> <td colspan='2' style="background-color: white; color:black; text-align: center;">2017年6月2日 (五) 09:43的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第16行：</td> <td colspan="2" class="diff-lineno">第16行：</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. TECHNOLOGY SUMMARY:</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. TECHNOLOGY SUMMARY:</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>本发布基于CDSSM模型，以三组CNN通过不同窗口长度得到三组特征向量，拼接后经过全连接层给出句子向量。训练采用对比递度下降。具体技术文档见[[媒体文件:基于深度神经网路的检索相似问题模型.v4.pdf ]]。</div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>本发布基于CDSSM模型，以三组CNN通过不同窗口长度得到三组特征向量，拼接后经过全连接层给出句子向量。训练采用对比递度下降。具体技术文档见[[媒体文件:基于深度神经网路的检索相似问题模型.v4.pdf]]。</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> </table>

Cslt http://www.cslt.org/mediawiki/index.php?title=FreeNeb_ViviQA_Release-v1.1&diff=27314&oldid=prev 2017-06-02T09:43:13Z

<p></p> <table class='diff diff-contentalign-left'> <col class='diff-marker' /> <col class='diff-content' /> <col class='diff-marker' /> <col class='diff-content' /> <tr style='vertical-align: top;'> <td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td> <td colspan='2' style="background-color: white; color:black; text-align: center;">2017年6月2日 (五) 09:43的版本</td> </tr><tr><td colspan="2" class="diff-lineno">第16行：</td> <td colspan="2" class="diff-lineno">第16行：</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. TECHNOLOGY SUMMARY:</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. TECHNOLOGY SUMMARY:</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>−</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>本发布基于CDSSM模型，以三组CNN通过不同窗口长度得到三组特征向量，拼接后经过全连接层给出句子向量。训练采用对比递度下降。具体技术文档见[[媒体文件:<del class="diffchange diffchange-inline">CDSSM deliver</del>.<del class="diffchange diffchange-inline">v3</del>.pdf]]。</div></td><td class='diff-marker'>+</td><td style="color:black; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>本发布基于CDSSM模型，以三组CNN通过不同窗口长度得到三组特征向量，拼接后经过全连接层给出句子向量。训练采用对比递度下降。具体技术文档见[[媒体文件:<ins class="diffchange diffchange-inline">基于深度神经网路的检索相似问题模型</ins>.<ins class="diffchange diffchange-inline">v4</ins>.pdf ]]。</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr> </table>

Cslt http://www.cslt.org/mediawiki/index.php?title=FreeNeb_ViviQA_Release-v1.1&diff=27312&oldid=prev 2017-06-02T09:42:06Z

<p>以“&lt;pre&gt; RELEASE TITLE: vvQA-CDSSM-HUILAN RELEASE VERSION: v1.0 RELEASE TYPE: MAIN RELEASE RELEASE LOCATION: /work5/release/baizw/vvQA-CDSSM-HUILAN-v1.0 RELATED BUGDB:...”为内容创建页面</p> <p><b>新页面</b></p><div>&lt;pre&gt;<br /> RELEASE TITLE: vvQA-CDSSM-HUILAN <br /> RELEASE VERSION: v1.0<br /> RELEASE TYPE: MAIN RELEASE<br /> RELEASE LOCATION: /work5/release/baizw/vvQA-CDSSM-HUILAN-v1.0<br /> RELATED BUGDB: 16<br /> RELEASE TIME: 2017/01/06<br /> <br /> &lt;/pre&gt;<br /> <br /> 1. BACKGROUND:<br /> <br /> 本发布是汇联QA项目的领域问答部分，基于CDSSM实现基础问答系统。RELEASE名为vvQA，与vvBeam, vvEngine, vvPoem同属vv人工智能模块的一部分。<br /> 本项目属对汇联延期交付的第一部分，第二部分为vvChat。<br /> <br /> 2. TECHNOLOGY SUMMARY:<br /> <br /> 本发布基于CDSSM模型，以三组CNN通过不同窗口长度得到三组特征向量，拼接后经过全连接层给出句子向量。训练采用对比递度下降。具体技术文档见[[媒体文件:CDSSM deliver.v3.pdf]]。<br /> <br /> <br /> 3. TEST RESULT:<br /> <br /> *模型参数：<br /> <br /> :*conv: 3 1 2 3<br /> :*num_filter:100<br /> :*batch:500<br /> :*epoch:10<br /> <br /> 参数说明：不设置线性层和非线性层，卷积层有三层，每层的 Step 数分别为 1，2，3，filter 数量为 100。一个 batch 的大小为 500，一共训练 10 轮。<br /> <br /> *实验结果<br /> <br /> 我们一共准备了四组训练语料与测试语料。记为 data_0; data_1;data_2; data_3.<br /> <br /> {|<br /> !数据 !! data_0 !! data_1 !! data_2 !! data_3<br /> |-<br /> |Top1 || 0.9735 || 0.9697 ||0.97218 ||0.9449<br /> |-<br /> |Top5 || 0.9924 || 0.99092 ||0.99082 ||0.99238<br /> |-<br /> |Top10 ||0.9945 || 0.99388 ||0.99356 ||0.99516<br /> |-<br /> |}<br /> <br /> 4. RELEASE TEAM:<br /> <br /> *Author: 邢超、白子薇<br /> *Contributor: <br /> *Monitor: 王东</div>

Cslt