Deploy to GitHub Pages: 581cf909

develop/doc/_sources/api/v2/config/layer.rst.txt

@@ -474,6 +474,11 @@ prelu
 ..  autoclass:: paddle.v2.layer.prelu
     :noindex:
 
+gated_unit
+-----------
+..  autoclass:: paddle.v2.layer.gated_unit
+    :noindex:
+
 Detection output Layer
 ======================
 

develop/doc/api/v2/config/layer.html

@@ -3724,6 +3724,62 @@ a_i * z_i  &amp;\quad \mathrm{otherwise}\end{split}\]</div>
 </table>
 </dd></dl>
 
+</div>
+<div class="section" id="gated-unit">
+<h3>gated_unit<a class="headerlink" href="#gated-unit" title="Permalink to this headline">¶</a></h3>
+<dl class="class">
+<dt>
+<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">gated_unit</code></dt>
+<dd><p>The gated unit layer implements a simple gating mechanism over the input.
+The input <span class="math">\(X\)</span> is first projected into a new space <span class="math">\(X'\)</span>, and
+it is also used to produce a gate weight <span class="math">\(\sigma\)</span>. Element-wise
+prodict between <a href="#id6"><span class="problematic" id="id7">:match:`X&#8217;`</span></a> and <span class="math">\(\sigma\)</span> is finally returned.</p>
+<dl class="docutils">
+<dt>Reference:</dt>
+<dd>Language Modeling with Gated Convolutional Networks
+<a class="reference external" href="https://arxiv.org/abs/1612.08083">https://arxiv.org/abs/1612.08083</a></dd>
+</dl>
+<div class="math">
+\[y=\text{act}(X \cdot W + b)\otimes \sigma(X \cdot V + c)\]</div>
+<p>The example usage is:</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>paddle.v2.config_base.Layer</em>) &#8211; input for this layer.</li>
+<li><strong>size</strong> (<em>int</em>) &#8211; output size of the gated unit.</li>
+<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; activation type of the projected input.</li>
+<li><strong>name</strong> (<em>basestring</em>) &#8211; name of this layer.</li>
+<li><strong>gate_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Attributes to tune the gate output, for example, error
+clipping threshold, dropout and so on. See paddle.v2.attr.ExtraAttribute for
+more details.</li>
+<li><strong>gate_param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; Attributes to tune the learnable projected matrix
+parameter of the gate.</li>
+<li><strong>gate_bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; Attributes to tune the learnable bias of the gate.</li>
+<li><strong>inproj_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Attributes to the tune the projected input, for
+example, error clipping threshold, dropout and so on. See
+paddle.v2.attr.ExtraAttribute for more details.</li>
+<li><strong>inproj_param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; Attributes to tune the learnable parameter of
+the projection of input.</li>
+<li><strong>inproj_bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; Attributes to tune the learnable bias of
+projection of the input.</li>
+<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Attributes to tune the final output of the gated unit,
+for example, error clipping threshold, dropout and so on. See
+paddle.v2.attr.ExtraAttribute for more details.</li>
+</ul>
+</td>
+</tr>
+<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">paddle.v2.config_base.Layer object.</p>
+</td>
+</tr>
+<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">paddle.v2.config_base.Layer</p>
+</td>
+</tr>
+</tbody>
+</table>
+</dd></dl>
+
 </div>
 </div>
 <div class="section" id="detection-output-layer">

develop/doc_cn/_sources/api/v2/config/layer.rst.txt

@@ -474,6 +474,11 @@ prelu
 ..  autoclass:: paddle.v2.layer.prelu
     :noindex:
 
+gated_unit
+-----------
+..  autoclass:: paddle.v2.layer.gated_unit
+    :noindex:
+
 Detection output Layer
 ======================
 

develop/doc_cn/api/v2/config/layer.html

@@ -3729,6 +3729,62 @@ a_i * z_i  &amp;\quad \mathrm{otherwise}\end{split}\]</div>
 </table>
 </dd></dl>
 
+</div>
+<div class="section" id="gated-unit">
+<h3>gated_unit<a class="headerlink" href="#gated-unit" title="永久链接至标题">¶</a></h3>
+<dl class="class">
+<dt>
+<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">gated_unit</code></dt>
+<dd><p>The gated unit layer implements a simple gating mechanism over the input.
+The input <span class="math">\(X\)</span> is first projected into a new space <span class="math">\(X'\)</span>, and
+it is also used to produce a gate weight <span class="math">\(\sigma\)</span>. Element-wise
+prodict between <a href="#id6"><span class="problematic" id="id7">:match:`X&#8217;`</span></a> and <span class="math">\(\sigma\)</span> is finally returned.</p>
+<dl class="docutils">
+<dt>Reference:</dt>
+<dd>Language Modeling with Gated Convolutional Networks
+<a class="reference external" href="https://arxiv.org/abs/1612.08083">https://arxiv.org/abs/1612.08083</a></dd>
+</dl>
+<div class="math">
+\[y=\text{act}(X \cdot W + b)\otimes \sigma(X \cdot V + c)\]</div>
+<p>The example usage is:</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>paddle.v2.config_base.Layer</em>) &#8211; input for this layer.</li>
+<li><strong>size</strong> (<em>int</em>) &#8211; output size of the gated unit.</li>
+<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; activation type of the projected input.</li>
+<li><strong>name</strong> (<em>basestring</em>) &#8211; name of this layer.</li>
+<li><strong>gate_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Attributes to tune the gate output, for example, error
+clipping threshold, dropout and so on. See paddle.v2.attr.ExtraAttribute for
+more details.</li>
+<li><strong>gate_param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; Attributes to tune the learnable projected matrix
+parameter of the gate.</li>
+<li><strong>gate_bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; Attributes to tune the learnable bias of the gate.</li>
+<li><strong>inproj_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Attributes to the tune the projected input, for
+example, error clipping threshold, dropout and so on. See
+paddle.v2.attr.ExtraAttribute for more details.</li>
+<li><strong>inproj_param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; Attributes to tune the learnable parameter of
+the projection of input.</li>
+<li><strong>inproj_bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; Attributes to tune the learnable bias of
+projection of the input.</li>
+<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Attributes to tune the final output of the gated unit,
+for example, error clipping threshold, dropout and so on. See
+paddle.v2.attr.ExtraAttribute for more details.</li>
+</ul>
+</td>
+</tr>
+<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">paddle.v2.config_base.Layer object.</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">paddle.v2.config_base.Layer</p>
+</td>
+</tr>
+</tbody>
+</table>
+</dd></dl>
+
 </div>
 </div>
 <div class="section" id="detection-output-layer">