Skip to content

P
Paddle

PaddlePaddle / Paddle
大约 1 年 前同步成功

通知 2298
Star 20931
Fork 5422
P
Paddle
提交 d690e184 编写于 作者: T Travis CI
浏览文件
操作

Deploy to GitHub Pages: de89b472

上级 5b3bce93
展开全部 隐藏空白更改
内联 并排
Showing with 114 addition and 2 deletion
develop/doc/_sources/api/v2/fluid/layers.rst.txt
浏览文件 @ d690e184
......@@ -529,3 +529,8 @@ sequence_reshape
----------------
.. autofunction:: paddle.v2.fluid.layers.sequence_reshape
:noindex:
row_conv
--------
.. autofunction:: paddle.v2.fluid.layers.row_conv
:noindex:
develop/doc/api/v2/fluid/layers.html
浏览文件 @ d690e184
......@@ -3670,6 +3670,57 @@ with shape being [N, M] where M for dimension.</li>
</div>
</dd></dl>
</div>
<div class="section" id="row-conv">
<h2>row_conv<a class="headerlink" href="#row-conv" title="Permalink to this headline"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.layers.</code><code class="descname">row_conv</code><span class="sig-paren">(</span><em>input</em>, <em>future_context_size</em>, <em>param_attr=None</em>, <em>act=None</em><span class="sig-paren">)</span></dt>
<dd><p>Row Conv Operator. This layer will apply lookahead convolution to
<strong>input</strong>. The input variable should be a 2D LoDTensor with shape [T, D].
Parameters with shape [future_context_size + 1, D] will be created. The math
equation of row convolution is as follows:</p>
<div class="math">
\[Out_{i} = \sum_{j = i} ^ {i + \tau} X_{j} \odot W_{i - j}\]</div>
<p>In the above equation:</p>
<ul class="simple">
<li><span class="math">\(Out_{i}\)</span>: The i-th row of output variable with shape [1, D].</li>
<li><span class="math">\(\tau\)</span>: Future context size.</li>
<li><span class="math">\(X_{j}\)</span>: The j-th row of input variable with shape [1, D].</li>
<li><span class="math">\(W_{i-j}\)</span>: The (i-j)-th row of parameters with shape [1, D].</li>
</ul>
<p>More details about row_conv please refer to the paper (<a class="reference external" href="http://www.cs.cmu.edu/~dyogatam/papers/wang+etal.iclrworkshop2016.pdf">http://www.cs.cmu.edu/~dyogatam/papers/wang+etal.iclrworkshop2016.pdf</a>) and
the design document (<a class="reference external" href="https://github.com/PaddlePaddle/Paddle/issues/2228#issuecomment-303903645">https://github.com/PaddlePaddle/Paddle/issues/2228#issuecomment-303903645</a>).</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>input</strong> (<em>Variable</em>) &#8211; Input variable, a 2D LoDTensor with shape [T, D].</li>
<li><strong>future_context_size</strong> (<em>int</em>) &#8211; Future context size. Please note, the shape
of convolution kernel is [future_context_size + 1, D].</li>
<li><strong>param_attr</strong> (<em>ParamAttr</em>) &#8211; Attributes of parameters, including
name, initializer etc.</li>
<li><strong>act</strong> (<em>str</em>) &#8211; Non-linear activation to be applied to output variable.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">The output tensor with same shape as input tensor.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">Variable</p>
</td>
</tr>
</tbody>
</table>
<p class="rubric">Examples</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">x</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">data</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;x&#39;</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="mi">16</span><span class="p">],</span>
<span class="n">dtype</span><span class="o">=</span><span class="s1">&#39;float32&#39;</span><span class="p">,</span> <span class="n">lod_level</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">out</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">row_conv</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">x</span><span class="p">,</span> <span class="n">future_context_size</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
</pre></div>
</div>
</dd></dl>
</div>
</div>
......
develop/doc/searchindex.js
浏览文件 @ d690e184
因为 它太大了无法显示 source diff 。你可以改为 查看blob。
develop/doc_cn/_sources/api/v2/fluid/layers.rst.txt
浏览文件 @ d690e184
......@@ -529,3 +529,8 @@ sequence_reshape
----------------
.. autofunction:: paddle.v2.fluid.layers.sequence_reshape
:noindex:
row_conv
--------
.. autofunction:: paddle.v2.fluid.layers.row_conv
:noindex:
develop/doc_cn/api/v2/fluid/layers.html
浏览文件 @ d690e184
......@@ -3689,6 +3689,57 @@ with shape being [N, M] where M for dimension.</li>
</div>
</dd></dl>
</div>
<div class="section" id="row-conv">
<h2>row_conv<a class="headerlink" href="#row-conv" title="永久链接至标题"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.layers.</code><code class="descname">row_conv</code><span class="sig-paren">(</span><em>input</em>, <em>future_context_size</em>, <em>param_attr=None</em>, <em>act=None</em><span class="sig-paren">)</span></dt>
<dd><p>Row Conv Operator. This layer will apply lookahead convolution to
<strong>input</strong>. The input variable should be a 2D LoDTensor with shape [T, D].
Parameters with shape [future_context_size + 1, D] will be created. The math
equation of row convolution is as follows:</p>
<div class="math">
\[Out_{i} = \sum_{j = i} ^ {i + \tau} X_{j} \odot W_{i - j}\]</div>
<p>In the above equation:</p>
<ul class="simple">
<li><span class="math">\(Out_{i}\)</span>: The i-th row of output variable with shape [1, D].</li>
<li><span class="math">\(\tau\)</span>: Future context size.</li>
<li><span class="math">\(X_{j}\)</span>: The j-th row of input variable with shape [1, D].</li>
<li><span class="math">\(W_{i-j}\)</span>: The (i-j)-th row of parameters with shape [1, D].</li>
</ul>
<p>More details about row_conv please refer to the paper (<a class="reference external" href="http://www.cs.cmu.edu/~dyogatam/papers/wang+etal.iclrworkshop2016.pdf">http://www.cs.cmu.edu/~dyogatam/papers/wang+etal.iclrworkshop2016.pdf</a>) and
the design document (<a class="reference external" href="https://github.com/PaddlePaddle/Paddle/issues/2228#issuecomment-303903645">https://github.com/PaddlePaddle/Paddle/issues/2228#issuecomment-303903645</a>).</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>input</strong> (<em>Variable</em>) &#8211; Input variable, a 2D LoDTensor with shape [T, D].</li>
<li><strong>future_context_size</strong> (<em>int</em>) &#8211; Future context size. Please note, the shape
of convolution kernel is [future_context_size + 1, D].</li>
<li><strong>param_attr</strong> (<em>ParamAttr</em>) &#8211; Attributes of parameters, including
name, initializer etc.</li>
<li><strong>act</strong> (<em>str</em>) &#8211; Non-linear activation to be applied to output variable.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">The output tensor with same shape as input tensor.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">Variable</p>
</td>
</tr>
</tbody>
</table>
<p class="rubric">Examples</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">x</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">data</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;x&#39;</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="mi">16</span><span class="p">],</span>
<span class="n">dtype</span><span class="o">=</span><span class="s1">&#39;float32&#39;</span><span class="p">,</span> <span class="n">lod_level</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">out</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">row_conv</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">x</span><span class="p">,</span> <span class="n">future_context_size</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
</pre></div>
</div>
</dd></dl>
</div>
</div>
......
develop/doc_cn/searchindex.js
浏览文件 @ d690e184
此差异已折叠。
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或