Skip to content

P
Paddle

机器未来 / Paddle
与 Fork 源项目一致

Fork自 PaddlePaddle / Paddle

通知 1
Star 1
Fork 0
P
Paddle
提交 e9fd3f6b 编写于 作者: T Travis CI
浏览文件
操作

Deploy to GitHub Pages: a3123e21

上级 efdfa193
展开全部 隐藏空白更改
内联 并排
Showing with 156 addition and 24 deletion
develop/doc/_sources/api/v2/config/layer.rst.txt
浏览文件 @ e9fd3f6b
...@@ -130,7 +130,7 @@ recurrent_group ...@@ -130,7 +130,7 @@ recurrent_group
--------------- ---------------
.. autoclass:: paddle.v2.layer.recurrent_group .. autoclass:: paddle.v2.layer.recurrent_group
:noindex: :noindex:
lstm_step lstm_step
--------- ---------
.. autoclass:: paddle.v2.layer.lstm_step .. autoclass:: paddle.v2.layer.lstm_step
...@@ -145,12 +145,12 @@ beam_search ...@@ -145,12 +145,12 @@ beam_search
------------ ------------
.. autoclass:: paddle.v2.layer.beam_search .. autoclass:: paddle.v2.layer.beam_search
:noindex: :noindex:
get_output get_output
---------- ----------
.. autoclass:: paddle.v2.layer.get_output .. autoclass:: paddle.v2.layer.get_output
:noindex: :noindex:
Mixed Layer Mixed Layer
=========== ===========
...@@ -203,7 +203,7 @@ trans_full_matrix_projection ...@@ -203,7 +203,7 @@ trans_full_matrix_projection
---------------------------- ----------------------------
.. autoclass:: paddle.v2.layer.trans_full_matrix_projection .. autoclass:: paddle.v2.layer.trans_full_matrix_projection
:noindex: :noindex:
Aggregate Layers Aggregate Layers
================ ================
...@@ -434,10 +434,19 @@ smooth_l1_cost ...@@ -434,10 +434,19 @@ smooth_l1_cost
.. autoclass:: paddle.v2.layer.smooth_l1_cost .. autoclass:: paddle.v2.layer.smooth_l1_cost
:noindex: :noindex:
Check Layer Check Layer
============ ============
eos eos
--- ---
.. autoclass:: paddle.v2.layer.eos .. autoclass:: paddle.v2.layer.eos
:noindex: :noindex:
Activation with learnable parameter
===================================
prelu
--------
.. autoclass:: paddle.v2.layer.prelu
:noindex:
develop/doc/api/v2/config/layer.html
浏览文件 @ e9fd3f6b
...@@ -2805,6 +2805,7 @@ in width dimension.</p> ...@@ -2805,6 +2805,7 @@ in width dimension.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">cross_entropy_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">cross_entropy_cost</code></dt>
<dd><p>A loss layer for multi class entropy.</p> <dd><p>A loss layer for multi class entropy.</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">cross_entropy</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">cross_entropy</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -2844,6 +2845,7 @@ will not be calculated for weight.</li> ...@@ -2844,6 +2845,7 @@ will not be calculated for weight.</li>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">cross_entropy_with_selfnorm_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">cross_entropy_with_selfnorm_cost</code></dt>
<dd><p>A loss layer for multi class entropy with selfnorm. <dd><p>A loss layer for multi class entropy with selfnorm.
Input should be a vector of positive numbers, without normalization.</p> Input should be a vector of positive numbers, without normalization.</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">cross_entropy_with_selfnorm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">cross_entropy_with_selfnorm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -2879,6 +2881,7 @@ Input should be a vector of positive numbers, without normalization.</p> ...@@ -2879,6 +2881,7 @@ Input should be a vector of positive numbers, without normalization.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">multi_binary_label_cross_entropy_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">multi_binary_label_cross_entropy_cost</code></dt>
<dd><p>A loss layer for multi binary label cross entropy.</p> <dd><p>A loss layer for multi binary label cross entropy.</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">multi_binary_label_cross_entropy</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">multi_binary_label_cross_entropy</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -2913,6 +2916,7 @@ Input should be a vector of positive numbers, without normalization.</p> ...@@ -2913,6 +2916,7 @@ Input should be a vector of positive numbers, without normalization.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">huber_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">huber_cost</code></dt>
<dd><p>A loss layer for huber loss.</p> <dd><p>A loss layer for huber loss.</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">huber_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">huber_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -2947,7 +2951,7 @@ Input should be a vector of positive numbers, without normalization.</p> ...@@ -2947,7 +2951,7 @@ Input should be a vector of positive numbers, without normalization.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">lambda_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">lambda_cost</code></dt>
<dd><p>lambdaCost for lambdaRank LTR approach.</p> <dd><p>lambdaCost for lambdaRank LTR approach.</p>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">lambda_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">lambda_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">score</span><span class="o">=</span><span class="n">score</span><span class="p">,</span> <span class="n">score</span><span class="o">=</span><span class="n">score</span><span class="p">,</span>
<span class="n">NDCG_num</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span> <span class="n">NDCG_num</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span>
...@@ -3043,7 +3047,7 @@ Their dimension is one.</li> ...@@ -3043,7 +3047,7 @@ Their dimension is one.</li>
</ul> </ul>
</dd> </dd>
</dl> </dl>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">rank_cost</span><span class="p">(</span><span class="n">left</span><span class="o">=</span><span class="n">out_left</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">rank_cost</span><span class="p">(</span><span class="n">left</span><span class="o">=</span><span class="n">out_left</span><span class="p">,</span>
<span class="n">right</span><span class="o">=</span><span class="n">out_right</span><span class="p">,</span> <span class="n">right</span><span class="o">=</span><span class="n">out_right</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
...@@ -3082,6 +3086,7 @@ It is an optional argument.</li> ...@@ -3082,6 +3086,7 @@ It is an optional argument.</li>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">sum_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">sum_cost</code></dt>
<dd><p>A loss layer which calculate the sum of the input as loss</p> <dd><p>A loss layer which calculate the sum of the input as loss</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">sum_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">sum_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span>
</pre></div> </pre></div>
</div> </div>
...@@ -3114,7 +3119,7 @@ It is an optional argument.</li> ...@@ -3114,7 +3119,7 @@ It is an optional argument.</li>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">crf</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">crf</code></dt>
<dd><p>A layer for calculating the cost of sequential conditional random <dd><p>A layer for calculating the cost of sequential conditional random
field model.</p> field model.</p>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">crf</span> <span class="o">=</span> <span class="n">crf</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">crf</span> <span class="o">=</span> <span class="n">crf</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="n">label_dim</span><span class="p">)</span> <span class="n">size</span><span class="o">=</span><span class="n">label_dim</span><span class="p">)</span>
...@@ -3158,7 +3163,7 @@ random field model. The decoding sequence is stored in output.ids. ...@@ -3158,7 +3163,7 @@ random field model. The decoding sequence is stored in output.ids.
If a second input is provided, it is treated as the ground-truth label, and If a second input is provided, it is treated as the ground-truth label, and
this layer will also calculate error. output.value[i] is 1 for incorrect this layer will also calculate error. output.value[i] is 1 for incorrect
decoding or 0 for correct decoding.</p> decoding or 0 for correct decoding.</p>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">crf_decoding</span> <span class="o">=</span> <span class="n">crf_decoding</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">crf_decoding</span> <span class="o">=</span> <span class="n">crf_decoding</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="n">label_dim</span><span class="p">)</span> <span class="n">size</span><span class="o">=</span><span class="n">label_dim</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -3207,7 +3212,7 @@ And the &#8216;blank&#8217; is the last category index. So the size of &#8216;in ...@@ -3207,7 +3212,7 @@ And the &#8216;blank&#8217; is the last category index. So the size of &#8216;in
fc with softmax activation, should be num_classes + 1. The size of ctc fc with softmax activation, should be num_classes + 1. The size of ctc
should also be num_classes + 1.</p> should also be num_classes + 1.</p>
</div> </div>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">ctc</span> <span class="o">=</span> <span class="n">ctc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">ctc</span> <span class="o">=</span> <span class="n">ctc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="mi">9055</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">9055</span><span class="p">,</span>
...@@ -3274,7 +3279,7 @@ should be consistent as that used in your labels.</li> ...@@ -3274,7 +3279,7 @@ should be consistent as that used in your labels.</li>
&#8216;linear&#8217; activation is expected instead in the &#8216;input&#8217; layer.</li> &#8216;linear&#8217; activation is expected instead in the &#8216;input&#8217; layer.</li>
</ul> </ul>
</div> </div>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">ctc</span> <span class="o">=</span> <span class="n">warp_ctc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">ctc</span> <span class="o">=</span> <span class="n">warp_ctc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="mi">1001</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">1001</span><span class="p">,</span>
...@@ -3409,6 +3414,7 @@ size of input and label are equal. The formula is as follows,</p> ...@@ -3409,6 +3414,7 @@ size of input and label are equal. The formula is as follows,</p>
<div class="math"> <div class="math">
\[\begin{split}smooth_{L1}(x) = \begin{cases} 0.5x^2&amp; \text{if} \ |x| &lt; 1 \\ |x|-0.5&amp; \text{otherwise} \end{cases}\end{split}\]</div> \[\begin{split}smooth_{L1}(x) = \begin{cases} 0.5x^2&amp; \text{if} \ |x| &lt; 1 \\ |x|-0.5&amp; \text{otherwise} \end{cases}\end{split}\]</div>
<p>More details can be found by referring to <a class="reference external" href="https://arxiv.org/pdf/1504.08083v2.pdf">Fast R-CNN</a></p> <p>More details can be found by referring to <a class="reference external" href="https://arxiv.org/pdf/1504.08083v2.pdf">Fast R-CNN</a></p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">smooth_l1_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">smooth_l1_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -3475,6 +3481,57 @@ It is used by recurrent layer group.</p> ...@@ -3475,6 +3481,57 @@ It is used by recurrent layer group.</p>
</table> </table>
</dd></dl> </dd></dl>
</div>
</div>
<div class="section" id="activation-with-learnable-parameter">
<h2>Activation with learnable parameter<a class="headerlink" href="#activation-with-learnable-parameter" title="Permalink to this headline"></a></h2>
<div class="section" id="prelu">
<h3>prelu<a class="headerlink" href="#prelu" 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">prelu</code></dt>
<dd><p>The Parameter Relu activation that actives outputs with a learnable weight.</p>
<dl class="docutils">
<dt>Reference:</dt>
<dd>Delving Deep into Rectifiers: Surpassing Human-Level Performance on
ImageNet Classification <a class="reference external" href="http://arxiv.org/pdf/1502.01852v1.pdf">http://arxiv.org/pdf/1502.01852v1.pdf</a></dd>
</dl>
<div class="math">
\[\begin{split}z_i &amp;\quad if \quad z_i &gt; 0 \\
a_i * z_i &amp;\quad \mathrm{otherwise}\end{split}\]</div>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">prelu</span> <span class="o">=</span> <span class="n">prelu</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layers</span><span class="p">,</span> <span class="n">partial_sum</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
</pre></div>
</div>
<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>name</strong> (<em>basestring</em>) &#8211; Name of this layer.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input layer.</li>
<li><strong>partial_sum</strong> (<em>int</em>) &#8211; <p>this parameter makes a group of inputs share a same weight.</p>
<ul>
<li>partial_sum = 1, indicates the element-wise activation: each element has a weight.</li>
<li>partial_sum = number of elements in one channel, indicates the channel-wise activation, elements in a channel share a same weight.</li>
<li>partial_sum = number of outputs, indicates all elements share a same weight.</li>
</ul>
</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for details.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Extra layer configurations. Default is None.</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> </div>
</div> </div>
......
develop/doc/searchindex.js
浏览文件 @ e9fd3f6b
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/config/layer.rst.txt
浏览文件 @ e9fd3f6b
...@@ -130,7 +130,7 @@ recurrent_group ...@@ -130,7 +130,7 @@ recurrent_group
--------------- ---------------
.. autoclass:: paddle.v2.layer.recurrent_group .. autoclass:: paddle.v2.layer.recurrent_group
:noindex: :noindex:
lstm_step lstm_step
--------- ---------
.. autoclass:: paddle.v2.layer.lstm_step .. autoclass:: paddle.v2.layer.lstm_step
...@@ -145,12 +145,12 @@ beam_search ...@@ -145,12 +145,12 @@ beam_search
------------ ------------
.. autoclass:: paddle.v2.layer.beam_search .. autoclass:: paddle.v2.layer.beam_search
:noindex: :noindex:
get_output get_output
---------- ----------
.. autoclass:: paddle.v2.layer.get_output .. autoclass:: paddle.v2.layer.get_output
:noindex: :noindex:
Mixed Layer Mixed Layer
=========== ===========
...@@ -203,7 +203,7 @@ trans_full_matrix_projection ...@@ -203,7 +203,7 @@ trans_full_matrix_projection
---------------------------- ----------------------------
.. autoclass:: paddle.v2.layer.trans_full_matrix_projection .. autoclass:: paddle.v2.layer.trans_full_matrix_projection
:noindex: :noindex:
Aggregate Layers Aggregate Layers
================ ================
...@@ -434,10 +434,19 @@ smooth_l1_cost ...@@ -434,10 +434,19 @@ smooth_l1_cost
.. autoclass:: paddle.v2.layer.smooth_l1_cost .. autoclass:: paddle.v2.layer.smooth_l1_cost
:noindex: :noindex:
Check Layer Check Layer
============ ============
eos eos
--- ---
.. autoclass:: paddle.v2.layer.eos .. autoclass:: paddle.v2.layer.eos
:noindex: :noindex:
Activation with learnable parameter
===================================
prelu
--------
.. autoclass:: paddle.v2.layer.prelu
:noindex:
develop/doc_cn/api/v2/config/layer.html
浏览文件 @ e9fd3f6b
...@@ -2812,6 +2812,7 @@ in width dimension.</p> ...@@ -2812,6 +2812,7 @@ in width dimension.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">cross_entropy_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">cross_entropy_cost</code></dt>
<dd><p>A loss layer for multi class entropy.</p> <dd><p>A loss layer for multi class entropy.</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">cross_entropy</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">cross_entropy</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -2851,6 +2852,7 @@ will not be calculated for weight.</li> ...@@ -2851,6 +2852,7 @@ will not be calculated for weight.</li>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">cross_entropy_with_selfnorm_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">cross_entropy_with_selfnorm_cost</code></dt>
<dd><p>A loss layer for multi class entropy with selfnorm. <dd><p>A loss layer for multi class entropy with selfnorm.
Input should be a vector of positive numbers, without normalization.</p> Input should be a vector of positive numbers, without normalization.</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">cross_entropy_with_selfnorm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">cross_entropy_with_selfnorm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -2886,6 +2888,7 @@ Input should be a vector of positive numbers, without normalization.</p> ...@@ -2886,6 +2888,7 @@ Input should be a vector of positive numbers, without normalization.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">multi_binary_label_cross_entropy_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">multi_binary_label_cross_entropy_cost</code></dt>
<dd><p>A loss layer for multi binary label cross entropy.</p> <dd><p>A loss layer for multi binary label cross entropy.</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">multi_binary_label_cross_entropy</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">multi_binary_label_cross_entropy</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -2920,6 +2923,7 @@ Input should be a vector of positive numbers, without normalization.</p> ...@@ -2920,6 +2923,7 @@ Input should be a vector of positive numbers, without normalization.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">huber_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">huber_cost</code></dt>
<dd><p>A loss layer for huber loss.</p> <dd><p>A loss layer for huber loss.</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">huber_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">huber_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -2954,7 +2958,7 @@ Input should be a vector of positive numbers, without normalization.</p> ...@@ -2954,7 +2958,7 @@ Input should be a vector of positive numbers, without normalization.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">lambda_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">lambda_cost</code></dt>
<dd><p>lambdaCost for lambdaRank LTR approach.</p> <dd><p>lambdaCost for lambdaRank LTR approach.</p>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">lambda_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">lambda_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">score</span><span class="o">=</span><span class="n">score</span><span class="p">,</span> <span class="n">score</span><span class="o">=</span><span class="n">score</span><span class="p">,</span>
<span class="n">NDCG_num</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span> <span class="n">NDCG_num</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span>
...@@ -3050,7 +3054,7 @@ Their dimension is one.</li> ...@@ -3050,7 +3054,7 @@ Their dimension is one.</li>
</ul> </ul>
</dd> </dd>
</dl> </dl>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">rank_cost</span><span class="p">(</span><span class="n">left</span><span class="o">=</span><span class="n">out_left</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">rank_cost</span><span class="p">(</span><span class="n">left</span><span class="o">=</span><span class="n">out_left</span><span class="p">,</span>
<span class="n">right</span><span class="o">=</span><span class="n">out_right</span><span class="p">,</span> <span class="n">right</span><span class="o">=</span><span class="n">out_right</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
...@@ -3089,6 +3093,7 @@ It is an optional argument.</li> ...@@ -3089,6 +3093,7 @@ It is an optional argument.</li>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">sum_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">sum_cost</code></dt>
<dd><p>A loss layer which calculate the sum of the input as loss</p> <dd><p>A loss layer which calculate the sum of the input as loss</p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">sum_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">sum_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span>
</pre></div> </pre></div>
</div> </div>
...@@ -3121,7 +3126,7 @@ It is an optional argument.</li> ...@@ -3121,7 +3126,7 @@ It is an optional argument.</li>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">crf</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">crf</code></dt>
<dd><p>A layer for calculating the cost of sequential conditional random <dd><p>A layer for calculating the cost of sequential conditional random
field model.</p> field model.</p>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">crf</span> <span class="o">=</span> <span class="n">crf</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">crf</span> <span class="o">=</span> <span class="n">crf</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="n">label_dim</span><span class="p">)</span> <span class="n">size</span><span class="o">=</span><span class="n">label_dim</span><span class="p">)</span>
...@@ -3165,7 +3170,7 @@ random field model. The decoding sequence is stored in output.ids. ...@@ -3165,7 +3170,7 @@ random field model. The decoding sequence is stored in output.ids.
If a second input is provided, it is treated as the ground-truth label, and If a second input is provided, it is treated as the ground-truth label, and
this layer will also calculate error. output.value[i] is 1 for incorrect this layer will also calculate error. output.value[i] is 1 for incorrect
decoding or 0 for correct decoding.</p> decoding or 0 for correct decoding.</p>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">crf_decoding</span> <span class="o">=</span> <span class="n">crf_decoding</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">crf_decoding</span> <span class="o">=</span> <span class="n">crf_decoding</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="n">label_dim</span><span class="p">)</span> <span class="n">size</span><span class="o">=</span><span class="n">label_dim</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -3214,7 +3219,7 @@ And the &#8216;blank&#8217; is the last category index. So the size of &#8216;in ...@@ -3214,7 +3219,7 @@ And the &#8216;blank&#8217; is the last category index. So the size of &#8216;in
fc with softmax activation, should be num_classes + 1. The size of ctc fc with softmax activation, should be num_classes + 1. The size of ctc
should also be num_classes + 1.</p> should also be num_classes + 1.</p>
</div> </div>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">ctc</span> <span class="o">=</span> <span class="n">ctc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">ctc</span> <span class="o">=</span> <span class="n">ctc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="mi">9055</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">9055</span><span class="p">,</span>
...@@ -3281,7 +3286,7 @@ should be consistent as that used in your labels.</li> ...@@ -3281,7 +3286,7 @@ should be consistent as that used in your labels.</li>
&#8216;linear&#8217; activation is expected instead in the &#8216;input&#8217; layer.</li> &#8216;linear&#8217; activation is expected instead in the &#8216;input&#8217; layer.</li>
</ul> </ul>
</div> </div>
<p>The simple usage:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">ctc</span> <span class="o">=</span> <span class="n">warp_ctc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">ctc</span> <span class="o">=</span> <span class="n">warp_ctc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span>
<span class="n">size</span><span class="o">=</span><span class="mi">1001</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">1001</span><span class="p">,</span>
...@@ -3416,6 +3421,7 @@ size of input and label are equal. The formula is as follows,</p> ...@@ -3416,6 +3421,7 @@ size of input and label are equal. The formula is as follows,</p>
<div class="math"> <div class="math">
\[\begin{split}smooth_{L1}(x) = \begin{cases} 0.5x^2&amp; \text{if} \ |x| &lt; 1 \\ |x|-0.5&amp; \text{otherwise} \end{cases}\end{split}\]</div> \[\begin{split}smooth_{L1}(x) = \begin{cases} 0.5x^2&amp; \text{if} \ |x| &lt; 1 \\ |x|-0.5&amp; \text{otherwise} \end{cases}\end{split}\]</div>
<p>More details can be found by referring to <a class="reference external" href="https://arxiv.org/pdf/1504.08083v2.pdf">Fast R-CNN</a></p> <p>More details can be found by referring to <a class="reference external" href="https://arxiv.org/pdf/1504.08083v2.pdf">Fast R-CNN</a></p>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">smooth_l1_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">cost</span> <span class="o">=</span> <span class="n">smooth_l1_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">,</span>
<span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -3482,6 +3488,57 @@ It is used by recurrent layer group.</p> ...@@ -3482,6 +3488,57 @@ It is used by recurrent layer group.</p>
</table> </table>
</dd></dl> </dd></dl>
</div>
</div>
<div class="section" id="activation-with-learnable-parameter">
<h2>Activation with learnable parameter<a class="headerlink" href="#activation-with-learnable-parameter" title="永久链接至标题"></a></h2>
<div class="section" id="prelu">
<h3>prelu<a class="headerlink" href="#prelu" 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">prelu</code></dt>
<dd><p>The Parameter Relu activation that actives outputs with a learnable weight.</p>
<dl class="docutils">
<dt>Reference:</dt>
<dd>Delving Deep into Rectifiers: Surpassing Human-Level Performance on
ImageNet Classification <a class="reference external" href="http://arxiv.org/pdf/1502.01852v1.pdf">http://arxiv.org/pdf/1502.01852v1.pdf</a></dd>
</dl>
<div class="math">
\[\begin{split}z_i &amp;\quad if \quad z_i &gt; 0 \\
a_i * z_i &amp;\quad \mathrm{otherwise}\end{split}\]</div>
<p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">prelu</span> <span class="o">=</span> <span class="n">prelu</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layers</span><span class="p">,</span> <span class="n">partial_sum</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
</pre></div>
</div>
<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>name</strong> (<em>basestring</em>) &#8211; Name of this layer.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input layer.</li>
<li><strong>partial_sum</strong> (<em>int</em>) &#8211; <p>this parameter makes a group of inputs share a same weight.</p>
<ul>
<li>partial_sum = 1, indicates the element-wise activation: each element has a weight.</li>
<li>partial_sum = number of elements in one channel, indicates the channel-wise activation, elements in a channel share a same weight.</li>
<li>partial_sum = number of outputs, indicates all elements share a same weight.</li>
</ul>
</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|None</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for details.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Extra layer configurations. Default is None.</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> </div>
</div> </div>
......
develop/doc_cn/searchindex.js
浏览文件 @ e9fd3f6b
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