Skip to content

P
Paddle

BaiXuePrincess / Paddle
与 Fork 源项目一致

Fork自 PaddlePaddle / Paddle

通知 1
Star 1
Fork 0
P
Paddle
提交 bf265015 编写于 作者: T Travis CI
浏览文件
操作

Deploy to GitHub Pages: 374e1685

上级 f62eabb3
隐藏空白更改
内联 并排
Showing with 616 addition and 484 deletion
develop/doc/api/v2/config/layer.html
浏览文件 @ bf265015
...@@ -237,7 +237,7 @@ ...@@ -237,7 +237,7 @@
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; The input of this layer.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; The layer dimension.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The layer dimension.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Tanh is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The Parameter Attribute|list.</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The Parameter Attribute|list.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
...@@ -263,7 +263,7 @@ parameter is set to True, the bias is initialized to zero.</li> ...@@ -263,7 +263,7 @@ parameter is set to True, the bias is initialized to zero.</li>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">selective_fc</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">selective_fc</code></dt>
<dd><p>Selectived fully connected layer. Different from fc, the output <dd><p>Selectived fully connected layer. Different from fc, the output
of this layer maybe sparse. It requires an additional input to indicate of this layer can be sparse. It requires an additional input to indicate
several selected columns for output. If the selected columns is not several selected columns for output. If the selected columns is not
specified, selective_fc acts exactly like fc.</p> specified, selective_fc acts exactly like fc.</p>
<p>The simple usage is:</p> <p>The simple usage is:</p>
...@@ -277,17 +277,26 @@ specified, selective_fc acts exactly like fc.</p> ...@@ -277,17 +277,26 @@ specified, selective_fc acts exactly like fc.</p>
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; The input of this layer.</li>
<li><strong>select</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The select layer. The output of select layer should be a <li><strong>select</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The layer to select columns to output. It should be a sparse
sparse binary matrix, and treat as the mask of selective fc. binary matrix, and is treated as the mask of selective fc. If
If is None, acts exactly like fc.</li> it is not set or set to None, selective_fc acts exactly
<li><strong>size</strong> (<em>int</em>) &#8211; The layer dimension.</li> like fc.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer, which should be equal to that of
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The Parameter Attribute.</li> the layer &#8216;select&#8217;.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>pass_generation</strong> (<em>bool</em>) &#8211; The flag which indicates whether it is during generation.</li>
<li><strong>has_selected_colums</strong> (<em>bool</em>) &#8211; The flag which indicates whether the parameter &#8216;select&#8217;
has been set. True is the default.</li>
<li><strong>mul_ratio</strong> (<em>float</em>) &#8211; A ratio helps to judge how sparse the output is and determine
the computation method for speed consideration.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to
False or an object whose type is not paddle.v2.attr.ParameterAttribute, False or an object whose type is not paddle.v2.attr.ParameterAttribute,
no bias is defined. If this parameter is set to True, no bias is defined. If this parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -313,7 +322,7 @@ the bias is initialized to zero.</li> ...@@ -313,7 +322,7 @@ the bias is initialized to zero.</li>
<dd><p>Different from img_conv, conv_op is an Operator, which can be used <dd><p>Different from img_conv, conv_op is an Operator, which can be used
in mixed. And conv_op takes two inputs to perform convolution. in mixed. And conv_op takes two inputs to perform convolution.
The first input is the image and the second is filter kernel. It only The first input is the image and the second is filter kernel. It only
support GPU mode.</p> supports GPU mode.</p>
<p>The example usage is:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">op</span> <span class="o">=</span> <span class="n">conv_operator</span><span class="p">(</span><span class="n">img</span><span class="o">=</span><span class="n">input1</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">op</span> <span class="o">=</span> <span class="n">conv_operator</span><span class="p">(</span><span class="n">img</span><span class="o">=</span><span class="n">input1</span><span class="p">,</span>
<span class="nb">filter</span><span class="o">=</span><span class="n">input2</span><span class="p">,</span> <span class="nb">filter</span><span class="o">=</span><span class="n">input2</span><span class="p">,</span>
...@@ -327,18 +336,22 @@ support GPU mode.</p> ...@@ -327,18 +336,22 @@ support GPU mode.</p>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>img</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input image</li> <li><strong>img</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input image.</li>
<li><strong>filter</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input filter</li> <li><strong>filter</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input filter.</li>
<li><strong>filter_size</strong> (<em>int</em>) &#8211; The x dimension of a filter kernel.</li> <li><strong>filter_size</strong> (<em>int</em>) &#8211; The dimension of the filter kernel on the x axis.</li>
<li><strong>filter_size_y</strong> (<em>int</em>) &#8211; The y dimension of a filter kernel. Since <li><strong>filter_size_y</strong> (<em>int</em>) &#8211; The dimension of the filter kernel on the y axis.
PaddlePaddle now supports rectangular filters, If the parameter is not set or set to None, it will
the filter&#8217;s shape can be (filter_size, filter_size_y).</li> set to &#8216;filter_size&#8217; automatically.</li>
<li><strong>num_filters</strong> (<em>int</em>) &#8211; channel of output data.</li> <li><strong>num_filters</strong> (<em>int</em>) &#8211; The number of the output channels.</li>
<li><strong>num_channels</strong> (<em>int</em>) &#8211; channel of input data.</li> <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of the input channels. If the parameter is not set
<li><strong>stride</strong> (<em>int</em>) &#8211; The x dimension of the stride.</li> or set to None, it will be automatically set to the channel
<li><strong>stride_y</strong> (<em>int</em>) &#8211; The y dimension of the stride.</li> number of the &#8216;img&#8217;.</li>
<li><strong>padding</strong> (<em>int</em>) &#8211; The x dimension of padding.</li> <li><strong>stride</strong> (<em>int</em>) &#8211; The stride on the x axis.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The y dimension of padding.</li> <li><strong>stride_y</strong> (<em>int</em>) &#8211; The stride on the y axis. If the parameter is not set or
set to None, it will be set to &#8216;stride&#8217; automatically.</li>
<li><strong>padding</strong> (<em>int</em>) &#8211; The padding size on the x axis.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The padding size on the y axis. If the parameter is not set
or set to None, it will be set to &#8216;padding&#8217; automatically.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -358,9 +371,9 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li> ...@@ -358,9 +371,9 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">conv_projection</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">conv_projection</code></dt>
<dd><p>Different from img_conv and conv_op, conv_projection is an Projection, <dd><p>Different from img_conv and conv_op, conv_projection is a Projection,
which can be used in mixed and conat. It use cudnn to implement which can be used in mixed and concat. It uses cudnn to implement
conv and only support GPU mode.</p> convolution and only supports GPU mode.</p>
<p>The example usage is:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">proj</span> <span class="o">=</span> <span class="n">conv_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">input1</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">proj</span> <span class="o">=</span> <span class="n">conv_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">input1</span><span class="p">,</span>
<span class="n">filter_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">filter_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span>
...@@ -374,26 +387,39 @@ conv and only support GPU mode.</p> ...@@ -374,26 +387,39 @@ conv and only support GPU mode.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>filter_size</strong> (<em>int</em>) &#8211; The x dimension of a filter kernel.</li> <li><strong>filter_size</strong> (<em>int | tuple | list</em>) &#8211; The dimensions of the filter kernel. If the parameter is
<li><strong>filter_size_y</strong> (<em>int</em>) &#8211; The y dimension of a filter kernel. Since set to one integer, the two dimensions on x and y axises
PaddlePaddle now supports rectangular filters, will be same when filter_size_y is not set. If it is set
the filter&#8217;s shape can be (filter_size, filter_size_y).</li> to a list, the first element indicates the dimension on
<li><strong>num_filters</strong> (<em>int</em>) &#8211; channel of output data.</li> the x axis, and the second is used to specify the dimension
<li><strong>num_channels</strong> (<em>int</em>) &#8211; channel of input data.</li> on the y axis when filter_size is not provided.</li>
<li><strong>stride</strong> (<em>int</em>) &#8211; The x dimension of the stride.</li> <li><strong>filter_size_y</strong> (<em>int</em>) &#8211; The dimension of the filter kernel on the y axis. If the parameter
<li><strong>stride_y</strong> (<em>int</em>) &#8211; The y dimension of the stride.</li> is not set, it will be set automatically according to filter_size.</li>
<li><strong>padding</strong> (<em>int</em>) &#8211; The x dimension of padding.</li> <li><strong>num_filters</strong> (<em>int</em>) &#8211; The number of filters.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The y dimension of padding.</li> <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of the input channels.</li>
<li><strong>stride</strong> (<em>int | tuple | list</em>) &#8211; The strides. If the parameter is set to one integer, the strides
on x and y axises will be same when stride_y is not set. If it is
set to a list, the first element indicates the stride on the x axis,
and the second is used to specify the stride on the y axis when
stride_y is not provided.</li>
<li><strong>stride_y</strong> (<em>int</em>) &#8211; The stride on the y axis.</li>
<li><strong>padding</strong> (<em>int | tuple | list</em>) &#8211; The padding sizes. If the parameter is set to one integer, the padding
sizes on x and y axises will be same when padding_y is not set. If it
is set to a list, the first element indicates the padding size on the
x axis, and the second is used to specify the padding size on the y axis
when padding_y is not provided.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The padding size on the y axis.</li>
<li><strong>groups</strong> (<em>int</em>) &#8211; The group number.</li> <li><strong>groups</strong> (<em>int</em>) &#8211; The group number.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; Convolution param attribute. None means default attribute</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute of the convolution. See paddle.v2.attr.ParameterAttribute for
<li><strong>trans</strong> (<em>bool</em>) &#8211; whether it is convTrans or conv</li> details.</li>
<li><strong>trans</strong> (<em>bool</em>) &#8211; Whether it is ConvTransProjection or ConvProjection</li>
</ul> </ul>
</td> </td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">A DotMulProjection Object.</p> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">A Projection Object.</p>
</td> </td>
</tr> </tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">DotMulProjection</p> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">ConvTransProjection | ConvProjection</p>
</td> </td>
</tr> </tr>
</tbody> </tbody>
...@@ -407,7 +433,7 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li> ...@@ -407,7 +433,7 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">conv_shift</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">conv_shift</code></dt>
<dd><dl class="docutils"> <dd><dl class="docutils">
<dt>This layer performs cyclic convolution for two input. For example:</dt> <dt>This layer performs cyclic convolution on two inputs. For example:</dt>
<dd><ul class="first last simple"> <dd><ul class="first last simple">
<li>a[in]: contains M elements.</li> <li>a[in]: contains M elements.</li>
<li>b[in]: contains N elements (N should be odd).</li> <li>b[in]: contains N elements (N should be odd).</li>
...@@ -418,7 +444,7 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li> ...@@ -418,7 +444,7 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li>
<div class="math"> <div class="math">
\[c[i] = \sum_{j=-(N-1)/2}^{(N-1)/2}a_{i+j} * b_{j}\]</div> \[c[i] = \sum_{j=-(N-1)/2}^{(N-1)/2}a_{i+j} * b_{j}\]</div>
<dl class="docutils"> <dl class="docutils">
<dt>In this formular:</dt> <dt>In this formula:</dt>
<dd><ul class="first last simple"> <dd><ul class="first last simple">
<li>a&#8217;s index is computed modulo M. When it is negative, then get item from <li>a&#8217;s index is computed modulo M. When it is negative, then get item from
the right side (which is the end of array) to the left.</li> the right side (which is the end of array) to the left.</li>
...@@ -437,9 +463,10 @@ the right size (which is the end of array) to the left.</li> ...@@ -437,9 +463,10 @@ the right size (which is the end of array) to the left.</li>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Input layer a.</li> <li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input of this layer.</li>
<li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input layer b.</li> <li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The second input of this layer.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; layer&#8217;s extra attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -498,7 +525,7 @@ two image dimension.</li> ...@@ -498,7 +525,7 @@ two image dimension.</li>
currently supports rectangular filters, the filter&#8217;s currently supports rectangular filters, the filter&#8217;s
shape will be (filter_size, filter_size_y).</li> shape will be (filter_size, filter_size_y).</li>
<li><strong>num_filters</strong> &#8211; Each filter group&#8217;s number of filter</li> <li><strong>num_filters</strong> &#8211; Each filter group&#8217;s number of filter</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Relu is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Relu is the default activation.</li>
<li><strong>groups</strong> (<em>int</em>) &#8211; Group size of filters.</li> <li><strong>groups</strong> (<em>int</em>) &#8211; Group size of filters.</li>
<li><strong>stride</strong> (<em>int | tuple | list</em>) &#8211; The x dimension of the stride. Or input a tuple for two image <li><strong>stride</strong> (<em>int | tuple | list</em>) &#8211; The x dimension of the stride. Or input a tuple for two image
dimension.</li> dimension.</li>
...@@ -614,7 +641,7 @@ number plus one equals context_len.</p> ...@@ -614,7 +641,7 @@ number plus one equals context_len.</p>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>context_len</strong> (<em>int</em>) &#8211; The context length equals the lookahead step number <li><strong>context_len</strong> (<em>int</em>) &#8211; The context length equals the lookahead step number
plus one.</li> plus one.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</li> details.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
...@@ -746,15 +773,23 @@ The details please refer to ...@@ -746,15 +773,23 @@ The details please refer to
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">maxout</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">maxout</code></dt>
<dd><dl class="docutils"> <dd><dl class="docutils">
<dt>A layer to do max out on conv layer output.</dt> <dt>A layer to do max out on convolutional layer output.</dt>
<dd><ul class="first last simple"> <dd><ul class="first last simple">
<li>Input: output of a conv layer.</li> <li>Input: the output of a convolutional layer.</li>
<li>Output: feature map size same as input. Channel is (input channel) / groups.</li> <li>Output: feature map size same as the input&#8217;s, and its channel number is
(input channel) / groups.</li>
</ul> </ul>
</dd> </dd>
</dl> </dl>
<p>So groups should be larger than 1, and the num of channels should be able <p>So groups should be larger than 1, and the num of channels should be able
to devided by groups.</p> to be devided by groups.</p>
<dl class="docutils">
<dt>Reference:</dt>
<dd>Maxout Networks
<a class="reference external" href="http://www.jmlr.org/proceedings/papers/v28/goodfellow13.pdf">http://www.jmlr.org/proceedings/papers/v28/goodfellow13.pdf</a>
Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
<a class="reference external" href="https://arxiv.org/pdf/1312.6082v4.pdf">https://arxiv.org/pdf/1312.6082v4.pdf</a></dd>
</dl>
<div class="math"> <div class="math">
\[y_{si+j} = \max_k x_{gsi + sk + j} \[y_{si+j} = \max_k x_{gsi + sk + j}
g = groups g = groups
...@@ -762,14 +797,6 @@ s = input.size / num_channels ...@@ -762,14 +797,6 @@ s = input.size / num_channels
0 \le i &lt; num_channels / groups 0 \le i &lt; num_channels / groups
0 \le j &lt; s 0 \le j &lt; s
0 \le k &lt; groups\]</div> 0 \le k &lt; groups\]</div>
<dl class="docutils">
<dt>Please refer to Paper:</dt>
<dd><ul class="first last simple">
<li>Maxout Networks: <a class="reference external" href="http://www.jmlr.org/proceedings/papers/v28/goodfellow13.pdf">http://www.jmlr.org/proceedings/papers/v28/goodfellow13.pdf</a></li>
<li>Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks: <a class="reference external" href="https://arxiv.org/pdf/1312.6082v4.pdf">https://arxiv.org/pdf/1312.6082v4.pdf</a></li>
</ul>
</dd>
</dl>
<p>The simple usage is:</p> <p>The simple usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">maxout</span> <span class="o">=</span> <span class="n">maxout</span><span class="p">(</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">maxout</span> <span class="o">=</span> <span class="n">maxout</span><span class="p">(</span><span class="nb">input</span><span class="p">,</span>
<span class="n">num_channels</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span> <span class="n">num_channels</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span>
...@@ -782,11 +809,13 @@ s = input.size / num_channels ...@@ -782,11 +809,13 @@ s = input.size / num_channels
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>num_channels</strong> (<em>int | None</em>) &#8211; The channel number of input layer. If None will be set <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of input channels. If the parameter is not set or
automatically from previous output.</li> set to None, its actual value will be automatically set to
the channels number of the input.</li>
<li><strong>groups</strong> (<em>int</em>) &#8211; The group number of input layer.</li> <li><strong>groups</strong> (<em>int</em>) &#8211; The group number of input layer.</li>
<li><strong>name</strong> (<em>None | basestring.</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1084,14 +1113,16 @@ out_{i} = act(in_{i} + out_{i+1} * W) \ \ \text{for} \ start &lt;= i &lt; end\en ...@@ -1084,14 +1113,16 @@ out_{i} = act(in_{i} + out_{i+1} * W) \ \ \text{for} \ start &lt;= i &lt; end\en
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to
False or an object whose type is not paddle.v2.attr.ParameterAttribute, False or an object whose type is not paddle.v2.attr.ParameterAttribute,
no bias is defined. If the parameter is set to True, no bias is defined. If the parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; parameter attribute.</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1135,7 +1166,7 @@ more details about LSTM.</p> ...@@ -1135,7 +1166,7 @@ more details about LSTM.</p>
<li><strong>size</strong> (<em>int</em>) &#8211; DEPRECATED. size of the lstm cell</li> <li><strong>size</strong> (<em>int</em>) &#8211; DEPRECATED. size of the lstm cell</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>reverse</strong> (<em>bool</em>) &#8211; is sequence process reversed or not.</li> <li><strong>reverse</strong> (<em>bool</em>) &#8211; is sequence process reversed or not.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default. <span class="math">\(h_t\)</span></li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; gate activation type, paddle.v2.activation.Sigmoid by default.</li> <li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; gate activation type, paddle.v2.activation.Sigmoid by default.</li>
<li><strong>state_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; state activation type, paddle.v2.activation.Tanh by default.</li> <li><strong>state_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; state activation type, paddle.v2.activation.Tanh by default.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
...@@ -1295,8 +1326,8 @@ It is ignored when name is provided.</li> ...@@ -1295,8 +1326,8 @@ It is ignored when name is provided.</li>
<dd><p>Recurrent layer group is an extremely flexible recurrent unit in <dd><p>Recurrent layer group is an extremely flexible recurrent unit in
PaddlePaddle. As long as the user defines the calculation done within a PaddlePaddle. As long as the user defines the calculation done within a
time step, PaddlePaddle will iterate such a recurrent calculation over time step, PaddlePaddle will iterate such a recurrent calculation over
sequence input. This is extremely usefull for attention based model, or sequence input. This is useful for attention-based models, or Neural
Neural Turning Machine like models.</p> Turning Machine like models.</p>
<p>The basic usage (time steps) is:</p> <p>The basic usage (time steps) is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="nb">input</span><span class="p">):</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="nb">input</span><span class="p">):</span>
<span class="n">output</span> <span class="o">=</span> <span class="n">fc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span> <span class="n">output</span> <span class="o">=</span> <span class="n">fc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span>
...@@ -1319,22 +1350,21 @@ Neural Turning Machine like models.</p> ...@@ -1319,22 +1350,21 @@ Neural Turning Machine like models.</p>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>step</strong> (<em>callable</em>) &#8211; <p>recurrent one time step function.The input of this function is <li><strong>step</strong> (<em>callable</em>) &#8211; <p>A step function which takes the input of recurrent_group as its own
input of the group. The return of this function will be input and returns values as recurrent_group&#8217;s output every time step.</p>
recurrent group&#8217;s return value.</p> <p>The recurrent group scatters a sequence into time steps. And
<p>The recurrent group scatter a sequence into time steps. And for each time step, it will invoke step function, and return
for each time step, will invoke step function, and return a time step result. Then gather outputs of each time step into
a time step result. Then gather each time step of output into
layer group&#8217;s output.</p> layer group&#8217;s output.</p>
</li> </li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; recurrent_group&#8217;s name.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The recurrent_group&#8217;s name. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | StaticInput | SubsequenceInput | list | tuple</em>) &#8211; <p>Input links array.</p> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | StaticInput | SubsequenceInput | list | tuple</em>) &#8211; <p>Input links array.</p>
<p>paddle.v2.config_base.Layer will be scattered into time steps. <p>paddle.v2.config_base.Layer will be scattered into time steps.
SubsequenceInput will be scattered into sequence steps. SubsequenceInput will be scattered into sequence steps.
StaticInput will be imported to each time step, and doesn&#8217;t change StaticInput will be imported to each time step, and doesn&#8217;t change
through time. It&#8217;s a mechanism to access layer outside step function.</p> over time. It&#8217;s a mechanism to access layer outside step function.</p>
</li> </li>
<li><strong>reverse</strong> (<em>bool</em>) &#8211; If reverse is set true, the recurrent unit will process the <li><strong>reverse</strong> (<em>bool</em>) &#8211; If reverse is set to True, the recurrent unit will process the
input sequence in a reverse order.</li> input sequence in a reverse order.</li>
<li><strong>targetInlink</strong> (<em>paddle.v2.config_base.Layer | SubsequenceInput</em>) &#8211; <p>DEPRECATED. <li><strong>targetInlink</strong> (<em>paddle.v2.config_base.Layer | SubsequenceInput</em>) &#8211; <p>DEPRECATED.
The input layer which share info with layer group&#8217;s output</p> The input layer which share info with layer group&#8217;s output</p>
...@@ -1373,8 +1403,8 @@ input vectors.</p> ...@@ -1373,8 +1403,8 @@ input vectors.</p>
<p>The state of lstm step is <span class="math">\(c_{t-1}\)</span>. And lstm step layer will do</p> <p>The state of lstm step is <span class="math">\(c_{t-1}\)</span>. And lstm step layer will do</p>
<div class="math"> <div class="math">
\[ \begin{align}\begin{aligned}i_t = \sigma(input + W_{ci}c_{t-1} + b_i)\\...\end{aligned}\end{align} \]</div> \[ \begin{align}\begin{aligned}i_t = \sigma(input + W_{ci}c_{t-1} + b_i)\\...\end{aligned}\end{align} \]</div>
<p>This layer has two outputs. Default output is <span class="math">\(h_t\)</span>. The other <p>This layer has two outputs. The default output is <span class="math">\(h_t\)</span>. The other
output is <span class="math">\(o_t\)</span>, whose name is &#8216;state&#8217; and can use output is <span class="math">\(o_t\)</span>, whose name is &#8216;state&#8217; and users can use
<code class="code docutils literal"><span class="pre">get_output</span></code> to extract this output.</p> <code class="code docutils literal"><span class="pre">get_output</span></code> to extract this output.</p>
<table class="docutils field-list" frame="void" rules="none"> <table class="docutils field-list" frame="void" rules="none">
<col class="field-name" /> <col class="field-name" />
...@@ -1382,17 +1412,19 @@ output is <span class="math">\(o_t\)</span>, whose name is &#8216;state&#8217; a ...@@ -1382,17 +1412,19 @@ output is <span class="math">\(o_t\)</span>, whose name is &#8216;state&#8217; a
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; Layer&#8217;s size. NOTE: lstm layer&#8217;s size, should be equal to <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer&#8217;s output, which must be
<code class="code docutils literal"><span class="pre">input.size/4</span></code>, and should be equal to equal to the dimension of the state.</li>
<code class="code docutils literal"><span class="pre">state.size</span></code>.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input layer. <span class="math">\(Wx_t + Wh_{t-1}\)</span></li> <li><strong>state</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The state of the LSTM unit.</li>
<li><strong>state</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; State Layer. <span class="math">\(c_{t-1}\)</span></li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default.</li> <li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of the gate. paddle.v2.activation.Sigmoid is the
<li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Gate Activation Type. paddle.v2.activation.Sigmoid is the default.</li> default activation.</li>
<li><strong>state_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; State Activation Type. paddle.v2.activation.Tanh is the default.</li> <li><strong>state_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of the state. paddle.v2.activation.Tanh is the
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | True</em>) &#8211; The parameter attribute for bias. If this parameter is default activation.</li>
set to True or None, the bias is initialized to zero.</li> <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; layer&#8217;s extra attribute.</li> whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1417,19 +1449,22 @@ set to True or None, the bias is initialized to zero.</li> ...@@ -1417,19 +1449,22 @@ set to True or None, the bias is initialized to zero.</li>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; </li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer, whose dimension can be divided by 3.</li>
<li><strong>output_mem</strong> &#8211; </li> <li><strong>output_mem</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; A memory which memorizes the output of this layer at previous
<li><strong>size</strong> &#8211; </li> time step.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; </li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer&#8217;s output. If it is not set or set to None,
<li><strong>name</strong> &#8211; The name of this layer. It is optional.</li> it will be set to one-third of the dimension of the input automatically.</li>
<li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of this layer&#8217;s two gates. Default is Sigmoid.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of this layer&#8217;s output. paddle.v2.activation.Tanh
is the default activation.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of this layer&#8217;s two gates. paddle.v2.activation.Sigmoid is
the default activation.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to
False or an object whose type is not paddle.v2.attr.ParameterAttribute, no bias False or an object whose type is not paddle.v2.attr.ParameterAttribute, no bias
is defined. If this parameter is set to True, is defined. If this parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>param_attr</strong> &#8211; the parameter_attribute for transforming the output_mem <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for details.</li>
from previous step.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for details.</li>
<li><strong>layer_attr</strong> &#8211; </li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1483,7 +1518,8 @@ to maintain tractability.</p> ...@@ -1483,7 +1518,8 @@ to maintain tractability.</p>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>name</strong> (<em>base string</em>) &#8211; Name of the recurrent unit that generates sequences.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of the recurrent unit that is responsible for
generating sequences. It is optional.</li>
<li><strong>step</strong> (<em>callable</em>) &#8211; <p>A callable function that defines the calculation in a time <li><strong>step</strong> (<em>callable</em>) &#8211; <p>A callable function that defines the calculation in a time
step, and it is applied to sequences with arbitrary length by step, and it is applied to sequences with arbitrary length by
sharing a same set of weights.</p> sharing a same set of weights.</p>
...@@ -1541,10 +1577,11 @@ the output from input.</p> ...@@ -1541,10 +1577,11 @@ the output from input.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; get output layer&#8217;s input. And this layer should contains <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input layer. And this layer should contain
multiple outputs.</li> multiple outputs.</li>
<li><strong>arg_name</strong> (<em>basestring</em>) &#8211; Output name from input.</li> <li><strong>arg_name</strong> (<em>basestring</em>) &#8211; The name of the output to be extracted from the input layer.</li>
<li><strong>layer_attr</strong> &#8211; Layer&#8217;s extra attribute.</li> <li><strong>layer_attr</strong> &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1595,7 +1632,7 @@ Each inputs is a projection or operator.</p> ...@@ -1595,7 +1632,7 @@ Each inputs is a projection or operator.</p>
<li><strong>size</strong> (<em>int</em>) &#8211; layer size.</li> <li><strong>size</strong> (<em>int</em>) &#8211; layer size.</li>
<li><strong>input</strong> &#8211; The input of this layer. It is an optional parameter. If set, <li><strong>input</strong> &#8211; The input of this layer. It is an optional parameter. If set,
then this function will just return layer&#8217;s name.</li> then this function will just return layer&#8217;s name.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.</li> parameter is set to True, the bias is initialized to zero.</li>
...@@ -2138,7 +2175,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p> ...@@ -2138,7 +2175,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p>
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>list | tuple | collections.Sequence</em>) &#8211; input layers or projections</li> <li><strong>input</strong> (<em>list | tuple | collections.Sequence</em>) &#8211; input layers or projections</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default activation.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li>
</ul> </ul>
</td> </td>
...@@ -2183,7 +2220,7 @@ processed in one batch.</p> ...@@ -2183,7 +2220,7 @@ processed in one batch.</p>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input sequence layer</li> <li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input sequence layer</li>
<li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input sequence layer</li> <li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input sequence layer</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default activation.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
...@@ -2307,11 +2344,11 @@ beam training.</p> ...@@ -2307,11 +2344,11 @@ beam training.</p>
</dl> </dl>
<div class="math"> <div class="math">
\[ \begin{align}\begin{aligned}outputH = 1 + (2 * padding_y + imgSizeH - block_y + stride_y - 1) / stride_y\\outputW = 1 + (2 * padding_x + imgSizeW - block_x + stride_x - 1) / stride_x\end{aligned}\end{align} \]</div> \[ \begin{align}\begin{aligned}outputH = 1 + (2 * padding_y + imgSizeH - block_y + stride_y - 1) / stride_y\\outputW = 1 + (2 * padding_x + imgSizeW - block_x + stride_x - 1) / stride_x\end{aligned}\end{align} \]</div>
<p>The expand method is the same with ExpandConvLayer, but saved the transposed <p>The expanding method is the same with ExpandConvLayer, but saved the transposed
value. After expanding, output.sequenceStartPositions will store timeline. value. After expanding, output.sequenceStartPositions will store timeline.
The number of time steps are outputH * outputW and the dimension of each The number of time steps is outputH * outputW and the dimension of each
time step is block_y * block_x * num_channels. This layer can be used after time step is block_y * block_x * num_channels. This layer can be used after
convolution neural network, and before recurrent neural network.</p> convolutional neural network, and before recurrent neural network.</p>
<p>The simple usage is:</p> <p>The simple usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">block_expand</span> <span class="o">=</span> <span class="n">block_expand</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">block_expand</span> <span class="o">=</span> <span class="n">block_expand</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span>
<span class="n">num_channels</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span> <span class="n">num_channels</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span>
...@@ -2327,15 +2364,18 @@ convolution neural network, and before recurrent neural network.</p> ...@@ -2327,15 +2364,18 @@ convolution neural network, and before recurrent neural network.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>num_channels</strong> (<em>int | None</em>) &#8211; The channel number of input layer.</li> <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of input channels. If the parameter is not set or
set to None, its actual value will be automatically set to
the channels number of the input.</li>
<li><strong>block_x</strong> (<em>int</em>) &#8211; The width of sub block.</li> <li><strong>block_x</strong> (<em>int</em>) &#8211; The width of sub block.</li>
<li><strong>block_y</strong> (<em>int</em>) &#8211; The width of sub block.</li> <li><strong>block_y</strong> (<em>int</em>) &#8211; The width of sub block.</li>
<li><strong>stride_x</strong> (<em>int</em>) &#8211; The stride size in horizontal direction.</li> <li><strong>stride_x</strong> (<em>int</em>) &#8211; The stride size in horizontal direction.</li>
<li><strong>stride_y</strong> (<em>int</em>) &#8211; The stride size in vertical direction.</li> <li><strong>stride_y</strong> (<em>int</em>) &#8211; The stride size in vertical direction.</li>
<li><strong>padding_x</strong> (<em>int</em>) &#8211; The padding size in horizontal direction.</li> <li><strong>padding_x</strong> (<em>int</em>) &#8211; The padding size in horizontal direction.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The padding size in vertical direction.</li> <li><strong>padding_y</strong> (<em>int</em>) &#8211; The padding size in vertical direction.</li>
<li><strong>name</strong> (<em>None | basestring.</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring.</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -2441,7 +2481,7 @@ in the column direction. This is equivalent to apply ...@@ -2441,7 +2481,7 @@ in the column direction. This is equivalent to apply
concat() with num_repeats same input. concat() with num_repeats same input.
False for treating input as column vector and repeating False for treating input as column vector and repeating
in the row direction.</li> in the row direction.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default activation.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li>
</ul> </ul>
</td> </td>
...@@ -2517,7 +2557,7 @@ output sequence has T*M/N instances, the dimension of each instance is N.</p> ...@@ -2517,7 +2557,7 @@ output sequence has T*M/N instances, the dimension of each instance is N.</p>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>reshape_size</strong> (<em>int</em>) &#8211; the size of reshaped sequence.</li> <li><strong>reshape_size</strong> (<em>int</em>) &#8211; the size of reshaped sequence.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default activation.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
...@@ -2573,7 +2613,7 @@ Please refer to dropout for details.</p> ...@@ -2573,7 +2613,7 @@ Please refer to dropout for details.</p>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; Input layers. It could be a paddle.v2.config_base.Layer or list/tuple of <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; Input layers. It could be a paddle.v2.config_base.Layer or list/tuple of
paddle.v2.config_base.Layer.</li> paddle.v2.config_base.Layer.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.</li> parameter is set to True, the bias is initialized to zero.</li>
...@@ -2638,9 +2678,10 @@ processed in one batch.</p> ...@@ -2638,9 +2678,10 @@ processed in one batch.</p>
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>weights</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer.</li> <li><strong>weights</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer.</li>
<li><strong>vectors</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The vector layer.</li> <li><strong>vectors</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The vector layer.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; the dimension of this layer.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -2887,8 +2928,7 @@ where size is the parameter of this layer indicating the output dimension.</p> ...@@ -2887,8 +2928,7 @@ where size is the parameter of this layer indicating the output dimension.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">slope_intercept</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">slope_intercept</code></dt>
<dd><p>This layer for applying a slope and an intercept to the input <dd><p>This layer for applying a slope and an intercept to the input.</p>
element-wise. There is no activation and weight.</p>
<div class="math"> <div class="math">
\[y = slope * x + intercept\]</div> \[y = slope * x + intercept\]</div>
<p>The simple usage is:</p> <p>The simple usage is:</p>
...@@ -2902,9 +2942,10 @@ element-wise. There is no activation and weight.</p> ...@@ -2902,9 +2942,10 @@ element-wise. There is no activation and weight.</p>
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>slope</strong> (<em>float.</em>) &#8211; the scale factor.</li> <li><strong>slope</strong> (<em>float</em>) &#8211; The scale factor.</li>
<li><strong>intercept</strong> (<em>float.</em>) &#8211; the offset.</li> <li><strong>intercept</strong> (<em>float</em>) &#8211; The offset.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -2924,8 +2965,8 @@ element-wise. There is no activation and weight.</p> ...@@ -2924,8 +2965,8 @@ element-wise. There is no activation and weight.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">tensor</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">tensor</code></dt>
<dd><p>This layer performs tensor operation for two input. <dd><p>This layer performs tensor operation on two inputs.
For example, each sample:</p> For example:</p>
<div class="math"> <div class="math">
\[y_{i} = a * W_{i} * {b^\mathrm{T}}, i=0,1,...,K-1\]</div> \[y_{i} = a * W_{i} * {b^\mathrm{T}}, i=0,1,...,K-1\]</div>
<dl class="docutils"> <dl class="docutils">
...@@ -2949,16 +2990,18 @@ For example, each sample:</p> ...@@ -2949,16 +2990,18 @@ For example, each sample:</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Input layer a.</li> <li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input of this layer.</li>
<li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input layer b.</li> <li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The second input of this layer.</li>
<li><strong>size</strong> (<em>int.</em>) &#8211; the layer dimension.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The Parameter Attribute.</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to
False or an object whose type is not paddle.v2.attr.ParameterAttribute, False or an object whose type is not paddle.v2.attr.ParameterAttribute,
no bias is defined. If this parameter is set to True, no bias is defined. If this parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3113,7 +3156,8 @@ The result is stored in output.ids.</p> ...@@ -3113,7 +3156,8 @@ The result is stored in output.ids.</p>
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3133,7 +3177,7 @@ The result is stored in output.ids.</p> ...@@ -3133,7 +3177,7 @@ The result is stored in output.ids.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">sampling_id</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">sampling_id</code></dt>
<dd><p>A layer for sampling id from multinomial distribution from the input layer. <dd><p>A layer for sampling id from a multinomial distribution from the input layer.
Sampling one id for one sample.</p> Sampling one id for one sample.</p>
<p>The simple usage is:</p> <p>The simple usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">samping_id</span> <span class="o">=</span> <span class="n">sampling_id</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">samping_id</span> <span class="o">=</span> <span class="n">sampling_id</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span>
...@@ -3146,7 +3190,8 @@ Sampling one id for one sample.</p> ...@@ -3146,7 +3190,8 @@ Sampling one id for one sample.</p>
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3215,12 +3260,12 @@ details.</li> ...@@ -3215,12 +3260,12 @@ details.</li>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">pad</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">pad</code></dt>
<dd><p>This operation pads zeros to the input data according to pad_c,pad_h <dd><p>This operation pads zeros to the input data according to pad_c,pad_h
and pad_w. pad_c, pad_h, pad_w specifies the which dimension and size and pad_w. pad_c, pad_h, pad_w specify the size in the corresponding
of padding. And the input data shape is NCHW.</p> dimension. And the input data shape is NCHW.</p>
<p>For example, pad_c=[2,3] means padding 2 zeros before the <p>For example, pad_c=[2,3] means padding 2 zeros before the input data
input data and 3 zeros after the input data in channel dimension. and 3 zeros after the input data in the channel dimension. pad_h means
pad_h means padding zeros in height dimension. pad_w means padding zeros padding zeros in the height dimension. pad_w means padding zeros in the
in width dimension.</p> width dimension.</p>
<p>For example,</p> <p>For example,</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="nb">input</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">)</span> <span class="o">=</span> <span class="p">[</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="nb">input</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">)</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">[</span> <span class="p">[[</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">],</span> <span class="p">[</span><span class="mi">3</span><span class="p">,</span><span class="mi">4</span><span class="p">,</span><span class="mi">5</span><span class="p">]],</span> <span class="p">[</span> <span class="p">[[</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">],</span> <span class="p">[</span><span class="mi">3</span><span class="p">,</span><span class="mi">4</span><span class="p">,</span><span class="mi">5</span><span class="p">]],</span>
...@@ -3256,10 +3301,11 @@ in width dimension.</p> ...@@ -3256,10 +3301,11 @@ in width dimension.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>pad_c</strong> (<em>list | None</em>) &#8211; padding size in channel dimension.</li> <li><strong>pad_c</strong> (<em>list | None</em>) &#8211; The padding size in the channel dimension.</li>
<li><strong>pad_h</strong> (<em>list | None</em>) &#8211; padding size in height dimension.</li> <li><strong>pad_h</strong> (<em>list | None</em>) &#8211; The padding size in the height dimension.</li>
<li><strong>pad_w</strong> (<em>list | None</em>) &#8211; padding size in width dimension.</li> <li><strong>pad_w</strong> (<em>list | None</em>) &#8211; The padding size in the width dimension.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
</ul> </ul>
</td> </td>
...@@ -3298,10 +3344,9 @@ in width dimension.</p> ...@@ -3298,10 +3344,9 @@ in width dimension.</p>
<li><strong>label</strong> &#8211; The input label.</li> <li><strong>label</strong> &#8211; The input label.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation. <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default.</li> 1.0 is the default value.</li>
<li><strong>weight</strong> (<em>LayerOutout</em>) &#8211; The cost of each sample is multiplied with each weight. <li><strong>weight</strong> (<em>LayerOutout</em>) &#8211; The weight layer defines a weight for each sample in the
The weight should be a layer with size=1. Note that gradient mini-batch. It is optional.</li>
will not be calculated for weight.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
</ul> </ul>
...@@ -3339,7 +3384,7 @@ Input should be a vector of positive numbers, without normalization.</p> ...@@ -3339,7 +3384,7 @@ Input should be a vector of positive numbers, without normalization.</p>
<li><strong>label</strong> &#8211; The input label.</li> <li><strong>label</strong> &#8211; The input label.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation. <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default.</li> 1.0 is the default value.</li>
<li><strong>softmax_selfnorm_alpha</strong> (<em>float</em>) &#8211; The scale factor affects the cost.</li> <li><strong>softmax_selfnorm_alpha</strong> (<em>float</em>) &#8211; The scale factor affects the cost.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
...@@ -3377,7 +3422,7 @@ details.</li> ...@@ -3377,7 +3422,7 @@ details.</li>
<li><strong>label</strong> &#8211; The input label.</li> <li><strong>label</strong> &#8211; The input label.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation. <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default.</li> 1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
</ul> </ul>
...@@ -3435,7 +3480,7 @@ ight <a href="#id2"><span class="problematic" id="id3">|</span></a>leq delta</p> ...@@ -3435,7 +3480,7 @@ ight <a href="#id2"><span class="problematic" id="id3">|</span></a>leq delta</p>
<tr class="field-even field"><th class="field-name">type delta:</th><td class="field-body">float</td> <tr class="field-even field"><th class="field-name">type delta:</th><td class="field-body">float</td>
</tr> </tr>
<tr class="field-odd field"><th class="field-name">param coeff:</th><td class="field-body">The weight of the gradient in the back propagation. <tr class="field-odd field"><th class="field-name">param coeff:</th><td class="field-body">The weight of the gradient in the back propagation.
1.0 is the default.</td> 1.0 is the default value.</td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">type coeff:</th><td class="field-body">float</td> <tr class="field-even field"><th class="field-name">type coeff:</th><td class="field-body">float</td>
</tr> </tr>
...@@ -3492,7 +3537,7 @@ a true binary class label :math:<a href="#id6"><span class="problematic" id="id7 ...@@ -3492,7 +3537,7 @@ a true binary class label :math:<a href="#id6"><span class="problematic" id="id7
<tr class="field-even field"><th class="field-name">type name:</th><td class="field-body">basestring</td> <tr class="field-even field"><th class="field-name">type name:</th><td class="field-body">basestring</td>
</tr> </tr>
<tr class="field-odd field"><th class="field-name">param coeff:</th><td class="field-body">The weight of the gradient in the back propagation. <tr class="field-odd field"><th class="field-name">param coeff:</th><td class="field-body">The weight of the gradient in the back propagation.
1.0 is the default.</td> 1.0 is the default value.</td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">type coeff:</th><td class="field-body">float</td> <tr class="field-even field"><th class="field-name">type coeff:</th><td class="field-body">float</td>
</tr> </tr>
...@@ -3532,20 +3577,20 @@ details.</td> ...@@ -3532,20 +3577,20 @@ details.</td>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; Samples of the same query should be loaded as sequence.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input of this layer, which is often a document
<li><strong>score</strong> &#8211; The 2nd input. Score of each sample.</li> samples list of the same query and whose type must be sequence.</li>
<li><strong>score</strong> &#8211; The scores of the samples.</li>
<li><strong>NDCG_num</strong> (<em>int</em>) &#8211; The size of NDCG (Normalized Discounted Cumulative Gain), <li><strong>NDCG_num</strong> (<em>int</em>) &#8211; The size of NDCG (Normalized Discounted Cumulative Gain),
e.g., 5 for NDCG&#64;5. It must be less than or equal to the e.g., 5 for NDCG&#64;5. It must be less than or equal to the
minimum size of lists.</li> minimum size of the list.</li>
<li><strong>max_sort_size</strong> (<em>int</em>) &#8211; The size of partial sorting in calculating gradient. <li><strong>max_sort_size</strong> (<em>int</em>) &#8211; The size of partial sorting in calculating gradient. If
If max_sort_size = -1, then for each list, the max_sort_size is equal to -1 or greater than the number
algorithm will sort the entire list to get gradient. of the samples in the list, then the algorithm will sort
In other cases, max_sort_size must be greater than or the entire list to compute the gradient. In other cases,
equal to NDCG_num. And if max_sort_size is greater max_sort_size must be greater than or equal to NDCG_num.</li>
than the size of a list, the algorithm will sort the <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
entire list of get gradient.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
<li><strong>name</strong> (<em>None | basestring</em>) &#8211; The name of this layer. It is optional.</li> details.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3574,12 +3619,14 @@ entire list of get gradient.</li> ...@@ -3574,12 +3619,14 @@ entire list of get gradient.</li>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Network prediction.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Data label.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight affects the cost, namely the scale of cost. <li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the
It is an optional argument.</li> mini-batch. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The coefficient affects the gradient in the backward.</li> <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; layer&#8217;s extra attribute.</li> 1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3599,10 +3646,12 @@ It is an optional argument.</li> ...@@ -3599,10 +3646,12 @@ It is an optional argument.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">rank_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">rank_cost</code></dt>
<dd><p>A cost Layer for learning to rank using gradient descent. Details can refer <dd><p>A cost Layer for learning to rank using gradient descent.</p>
to <a class="reference external" href="http://research.microsoft.com/en-us/um/people/cburges/papers/ICML_ranking.pdf">papers</a>. <dl class="docutils">
This layer contains at least three inputs. The weight is an optional <dt>Reference:</dt>
argument, which affects the cost.</p> <dd>Learning to Rank using Gradient Descent
<a class="reference external" href="http://research.microsoft.com/en-us/um/people/cburges/papers/ICML_ranking.pdf">http://research.microsoft.com/en-us/um/people/cburges/papers/ICML_ranking.pdf</a></dd>
</dl>
<div class="math"> <div class="math">
\[ \begin{align}\begin{aligned}C_{i,j} &amp; = -\tilde{P_{ij}} * o_{i,j} + log(1 + e^{o_{i,j}})\\o_{i,j} &amp; = o_i - o_j\\\tilde{P_{i,j}} &amp; = \{0, 0.5, 1\} \ or \ \{0, 1\}\end{aligned}\end{align} \]</div> \[ \begin{align}\begin{aligned}C_{i,j} &amp; = -\tilde{P_{ij}} * o_{i,j} + log(1 + e^{o_{i,j}})\\o_{i,j} &amp; = o_i - o_j\\\tilde{P_{i,j}} &amp; = \{0, 0.5, 1\} \ or \ \{0, 1\}\end{aligned}\end{align} \]</div>
<dl class="docutils"> <dl class="docutils">
...@@ -3630,11 +3679,13 @@ Their dimension is one.</li> ...@@ -3630,11 +3679,13 @@ Their dimension is one.</li>
<li><strong>left</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input, the size of this layer is 1.</li> <li><strong>left</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input, the size of this layer is 1.</li>
<li><strong>right</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The right input, the size of this layer is 1.</li> <li><strong>right</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The right input, the size of this layer is 1.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Label is 1 or 0, means positive order and reverse order.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Label is 1 or 0, means positive order and reverse order.</li>
<li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight affects the cost, namely the scale of cost. <li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the
It is an optional argument.</li> mini-batch. It is optional.</li>
<li><strong>name</strong> (<em>None | basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The coefficient affects the gradient in the backward.</li> <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> 1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3700,15 +3751,18 @@ field model.</p> ...@@ -3700,15 +3751,18 @@ field model.</p>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The first input layer is the feature.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The second input layer is label.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; The category number.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The category number.</li>
<li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The third layer is &#8220;weight&#8221; of each sample, which is an <li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the
optional argument.</li> mini-batch. It is optional.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; Parameter attribute. None means default attribute</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
<li><strong>name</strong> (<em>None | basestring</em>) &#8211; The name of this layer. It is optional.</li> details.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The coefficient affects the gradient in the backward.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3730,9 +3784,9 @@ optional argument.</li> ...@@ -3730,9 +3784,9 @@ optional argument.</li>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">crf_decoding</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">crf_decoding</code></dt>
<dd><p>A layer for calculating the decoding sequence of sequential conditional <dd><p>A layer for calculating the decoding sequence of sequential conditional
random field model. The decoding sequence is stored in output.ids. 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 the input &#8216;label&#8217; 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 an incorrect
decoding or 0 for correct decoding.</p> decoding and 0 for the correct.</p>
<p>The example usage is:</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>
...@@ -3744,11 +3798,13 @@ decoding or 0 for correct decoding.</p> ...@@ -3744,11 +3798,13 @@ decoding or 0 for correct decoding.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The first input layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input layer.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; size of this layer.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em><em> or </em><em>None</em>) &#8211; None or ground-truth label.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer | None</em>) &#8211; The input label.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; Parameter attribute. None means default attribute</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
<li><strong>name</strong> (<em>None | basestring</em>) &#8211; The name of this layer. It is optional.</li> details.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3769,18 +3825,21 @@ decoding or 0 for correct decoding.</p> ...@@ -3769,18 +3825,21 @@ decoding or 0 for correct decoding.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">ctc</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">ctc</code></dt>
<dd><p>Connectionist Temporal Classification (CTC) is designed for temporal <dd><p>Connectionist Temporal Classification (CTC) is designed for temporal
classication task. That is, for sequence labeling problems where the classication task. e.g. sequence labeling problems where the
alignment between the inputs and the target labels is unknown.</p> alignment between the inputs and the target labels is unknown.</p>
<p>More details can be found by referring to <a class="reference external" href="http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf">Connectionist Temporal <dl class="docutils">
Classification: Labelling Unsegmented Sequence Data with Recurrent <dt>Reference:</dt>
Neural Networks</a></p> <dd>Connectionist Temporal Classification: Labelling Unsegmented Sequence Data
with Recurrent Neural Networks
<a class="reference external" href="http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf">http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf</a></dd>
</dl>
<div class="admonition note"> <div class="admonition note">
<p class="first admonition-title">Note</p> <p class="first admonition-title">Note</p>
<p class="last">Considering the &#8216;blank&#8217; label needed by CTC, you need to use <p class="last">Considering the &#8216;blank&#8217; label needed by CTC, you need to use (num_classes + 1)
(num_classes + 1) as the input size. num_classes is the category number. as the size of the input, where num_classes is the category number.
And the &#8216;blank&#8217; is the last category index. So the size of &#8216;input&#8217; layer, such as And the &#8216;blank&#8217; is the last category index. So the size of &#8216;input&#8217; layer (e.g.
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
should also be num_classes + 1.</p> ctc should also be (num_classes + 1).</p>
</div> </div>
<p>The example usage is:</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>
...@@ -3795,11 +3854,12 @@ should also be num_classes + 1.</p> ...@@ -3795,11 +3854,12 @@ should also be num_classes + 1.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The data layer of label with variable length.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; category numbers + 1.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer, which must be equal to (category number + 1).</li>
<li><strong>name</strong> (<em>basestring | None</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>norm_by_times</strong> (<em>bool</em>) &#8211; Whether to normalization by times. False by default.</li> <li><strong>norm_by_times</strong> (<em>bool</em>) &#8211; Whether to do normalization by times. False is the default.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3825,20 +3885,22 @@ Classification (CTC) loss. Besides, another <a class="reference external" href=" ...@@ -3825,20 +3885,22 @@ Classification (CTC) loss. Besides, another <a class="reference external" href="
the official one, is maintained to enable more compiling options. During the the official one, is maintained to enable more compiling options. During the
building process, PaddlePaddle will clone the source codes, build and building process, PaddlePaddle will clone the source codes, build and
install it to <code class="code docutils literal"><span class="pre">third_party/install/warpctc</span></code> directory.</p> install it to <code class="code docutils literal"><span class="pre">third_party/install/warpctc</span></code> directory.</p>
<p>More details of CTC can be found by referring to <a class="reference external" href="http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf">Connectionist Temporal <dl class="docutils">
Classification: Labelling Unsegmented Sequence Data with Recurrent <dt>Reference:</dt>
Neural Networks</a>.</p> <dd>Connectionist Temporal Classification: Labelling Unsegmented Sequence Data
with Recurrent Neural Networks
<a class="reference external" href="http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf">http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf</a></dd>
</dl>
<div class="admonition note"> <div class="admonition note">
<p class="first admonition-title">Note</p> <p class="first admonition-title">Note</p>
<ul class="last simple"> <ul class="last simple">
<li>Let num_classes represent the category number. Considering the &#8216;blank&#8217; <li>Let num_classes represents the category number. Considering the &#8216;blank&#8217;
label needed by CTC, you need to use (num_classes + 1) as the input size. label needed by CTC, you need to use (num_classes + 1) as the size of
Thus, the size of both warp_ctc layer and &#8216;input&#8217; layer should be set to warp_ctc layer.</li>
num_classes + 1.</li>
<li>You can set &#8216;blank&#8217; to any value ranged in [0, num_classes], which <li>You can set &#8216;blank&#8217; to any value ranged in [0, num_classes], which
should be consistent as that used in your labels.</li> should be consistent with those used in your labels.</li>
<li>As a native &#8216;softmax&#8217; activation is interated to the warp-ctc library, <li>As a native &#8216;softmax&#8217; activation is interated to the warp-ctc library,
&#8216;linear&#8217; activation is expected instead in the &#8216;input&#8217; layer.</li> &#8216;linear&#8217; activation is expected to be used instead in the &#8216;input&#8217; layer.</li>
</ul> </ul>
</div> </div>
<p>The example usage is:</p> <p>The example usage is:</p>
...@@ -3855,12 +3917,13 @@ should be consistent as that used in your labels.</li> ...@@ -3855,12 +3917,13 @@ should be consistent as that used in your labels.</li>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The data layer of label with variable length.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; category numbers + 1.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer, which must be equal to (category number + 1).</li>
<li><strong>name</strong> (<em>basestring | None</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>blank</strong> (<em>int</em>) &#8211; the &#8216;blank&#8217; label used in ctc</li> <li><strong>blank</strong> (<em>int</em>) &#8211; The &#8216;blank&#8217; label used in ctc.</li>
<li><strong>norm_by_times</strong> (<em>bool</em>) &#8211; Whether to normalization by times. False by default.</li> <li><strong>norm_by_times</strong> (<em>bool</em>) &#8211; Whether to do normalization by times. False is the default.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3880,8 +3943,7 @@ should be consistent as that used in your labels.</li> ...@@ -3880,8 +3943,7 @@ should be consistent as that used in your labels.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">nce</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">nce</code></dt>
<dd><p>Noise-contrastive estimation. This layer implements the method in the <dd><p>Noise-contrastive estimation.</p>
following paper:</p>
<dl class="docutils"> <dl class="docutils">
<dt>Reference:</dt> <dt>Reference:</dt>
<dd>A fast and simple algorithm for training neural probabilistic language <dd>A fast and simple algorithm for training neural probabilistic language
...@@ -3899,19 +3961,20 @@ models. <a class="reference external" href="https://www.cs.toronto.edu/~amnih/pa ...@@ -3899,19 +3961,20 @@ models. <a class="reference external" href="https://www.cs.toronto.edu/~amnih/pa
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple | collections.Sequence</em>) &#8211; The input layers. It should be a paddle.v2.config_base.Layer or a list/tuple <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple | collections.Sequence</em>) &#8211; The first input of this layer.</li>
of paddle.v2.config_base.Layer.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The ground truth.</li>
<li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the <li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the
mini-batch. The default value is None.</li> mini-batch. It is optional.</li>
<li><strong>num_classes</strong> (<em>int</em>) &#8211; The class number.</li> <li><strong>num_classes</strong> (<em>int</em>) &#8211; The number of classes.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|list</em>) &#8211; The parameter attributes.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Sigmoid is the default activation.</li>
<li><strong>num_neg_samples</strong> (<em>int</em>) &#8211; The number of sampled negative labels. The default <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
value is 10.</li> details.</li>
<li><strong>num_neg_samples</strong> (<em>int</em>) &#8211; The number of sampled negative labels. 10 is the
default value.</li>
<li><strong>neg_distribution</strong> (<em>list | tuple | collections.Sequence | None</em>) &#8211; The discrete noisy distribution over the output <li><strong>neg_distribution</strong> (<em>list | tuple | collections.Sequence | None</em>) &#8211; The discrete noisy distribution over the output
space from which num_neg_samples negative labels space from which num_neg_samples negative labels
are sampled. If this parameter is not set, a are sampled. If this parameter is not set, a
uniform distribution will be used. A user defined uniform distribution will be used. A user-defined
distribution is a list whose length must be equal distribution is a list whose length must be equal
to the num_classes. Each member of the list defines to the num_classes. Each member of the list defines
the probability of a class given input x.</li> the probability of a class given input x.</li>
...@@ -3919,11 +3982,12 @@ the probability of a class given input x.</li> ...@@ -3919,11 +3982,12 @@ the probability of a class given input x.</li>
False or an object whose type is not paddle.v2.attr.ParameterAttribute, False or an object whose type is not paddle.v2.attr.ParameterAttribute,
no bias is defined. If this parameter is set to True, no bias is defined. If this parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">The paddle.v2.config_base.Layer object.</p> <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> </td>
</tr> </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> <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>
...@@ -4007,7 +4071,7 @@ sizes of input and label are equal. The formula is as follows,</p> ...@@ -4007,7 +4071,7 @@ sizes of input and label are equal. The formula is as follows,</p>
<li><strong>label</strong> &#8211; The input label.</li> <li><strong>label</strong> &#8211; The input label.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation. <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default.</li> 1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
</ul> </ul>
...@@ -4079,8 +4143,9 @@ It is used by recurrent layer group.</p> ...@@ -4079,8 +4143,9 @@ It is used by recurrent layer group.</p>
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>eos_id</strong> (<em>int</em>) &#8211; end id of sequence</li> <li><strong>eos_id</strong> (<em>int</em>) &#8211; End id of sequence</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -4189,7 +4254,7 @@ details.</li> ...@@ -4189,7 +4254,7 @@ details.</li>
<dd><p>The gated unit layer implements a simple gating mechanism over the input. <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 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 it is also used to produce a gate weight <span class="math">\(\sigma\)</span>. Element-wise
product between <a href="#id11"><span class="problematic" id="id12">:match:`X&#8217;`</span></a> and <span class="math">\(\sigma\)</span> is finally returned.</p> product between <a href="#id10"><span class="problematic" id="id11">:match:`X&#8217;`</span></a> and <span class="math">\(\sigma\)</span> is finally returned.</p>
<dl class="docutils"> <dl class="docutils">
<dt>Reference:</dt> <dt>Reference:</dt>
<dd>Language Modeling with Gated Convolutional Networks <dd>Language Modeling with Gated Convolutional Networks
...@@ -4205,7 +4270,8 @@ product between <a href="#id11"><span class="problematic" id="id12">:match:`X&#8 ...@@ -4205,7 +4270,8 @@ product between <a href="#id11"><span class="problematic" id="id12">:match:`X&#8
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer&#8217;s output.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer&#8217;s output.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of the projection. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of the projection. paddle.v2.activation.Linear is the default
activation.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>gate_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute of the gate. See paddle.v2.attr.ExtraAttribute for <li><strong>gate_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute of the gate. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
......
develop/doc/searchindex.js
浏览文件 @ bf265015
因为 它太大了无法显示 source diff 。你可以改为 查看blob。
develop/doc_cn/api/v2/config/layer.html
浏览文件 @ bf265015
...@@ -251,7 +251,7 @@ ...@@ -251,7 +251,7 @@
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; The input of this layer.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; The layer dimension.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The layer dimension.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Tanh is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The Parameter Attribute|list.</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The Parameter Attribute|list.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
...@@ -277,7 +277,7 @@ parameter is set to True, the bias is initialized to zero.</li> ...@@ -277,7 +277,7 @@ parameter is set to True, the bias is initialized to zero.</li>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">selective_fc</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">selective_fc</code></dt>
<dd><p>Selectived fully connected layer. Different from fc, the output <dd><p>Selectived fully connected layer. Different from fc, the output
of this layer maybe sparse. It requires an additional input to indicate of this layer can be sparse. It requires an additional input to indicate
several selected columns for output. If the selected columns is not several selected columns for output. If the selected columns is not
specified, selective_fc acts exactly like fc.</p> specified, selective_fc acts exactly like fc.</p>
<p>The simple usage is:</p> <p>The simple usage is:</p>
...@@ -291,17 +291,26 @@ specified, selective_fc acts exactly like fc.</p> ...@@ -291,17 +291,26 @@ specified, selective_fc acts exactly like fc.</p>
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; The input of this layer.</li>
<li><strong>select</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The select layer. The output of select layer should be a <li><strong>select</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The layer to select columns to output. It should be a sparse
sparse binary matrix, and treat as the mask of selective fc. binary matrix, and is treated as the mask of selective fc. If
If is None, acts exactly like fc.</li> it is not set or set to None, selective_fc acts exactly
<li><strong>size</strong> (<em>int</em>) &#8211; The layer dimension.</li> like fc.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer, which should be equal to that of
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The Parameter Attribute.</li> the layer &#8216;select&#8217;.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>pass_generation</strong> (<em>bool</em>) &#8211; The flag which indicates whether it is during generation.</li>
<li><strong>has_selected_colums</strong> (<em>bool</em>) &#8211; The flag which indicates whether the parameter &#8216;select&#8217;
has been set. True is the default.</li>
<li><strong>mul_ratio</strong> (<em>float</em>) &#8211; A ratio helps to judge how sparse the output is and determine
the computation method for speed consideration.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to
False or an object whose type is not paddle.v2.attr.ParameterAttribute, False or an object whose type is not paddle.v2.attr.ParameterAttribute,
no bias is defined. If this parameter is set to True, no bias is defined. If this parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -327,7 +336,7 @@ the bias is initialized to zero.</li> ...@@ -327,7 +336,7 @@ the bias is initialized to zero.</li>
<dd><p>Different from img_conv, conv_op is an Operator, which can be used <dd><p>Different from img_conv, conv_op is an Operator, which can be used
in mixed. And conv_op takes two inputs to perform convolution. in mixed. And conv_op takes two inputs to perform convolution.
The first input is the image and the second is filter kernel. It only The first input is the image and the second is filter kernel. It only
support GPU mode.</p> supports GPU mode.</p>
<p>The example usage is:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">op</span> <span class="o">=</span> <span class="n">conv_operator</span><span class="p">(</span><span class="n">img</span><span class="o">=</span><span class="n">input1</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">op</span> <span class="o">=</span> <span class="n">conv_operator</span><span class="p">(</span><span class="n">img</span><span class="o">=</span><span class="n">input1</span><span class="p">,</span>
<span class="nb">filter</span><span class="o">=</span><span class="n">input2</span><span class="p">,</span> <span class="nb">filter</span><span class="o">=</span><span class="n">input2</span><span class="p">,</span>
...@@ -341,18 +350,22 @@ support GPU mode.</p> ...@@ -341,18 +350,22 @@ support GPU mode.</p>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>img</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input image</li> <li><strong>img</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input image.</li>
<li><strong>filter</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input filter</li> <li><strong>filter</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input filter.</li>
<li><strong>filter_size</strong> (<em>int</em>) &#8211; The x dimension of a filter kernel.</li> <li><strong>filter_size</strong> (<em>int</em>) &#8211; The dimension of the filter kernel on the x axis.</li>
<li><strong>filter_size_y</strong> (<em>int</em>) &#8211; The y dimension of a filter kernel. Since <li><strong>filter_size_y</strong> (<em>int</em>) &#8211; The dimension of the filter kernel on the y axis.
PaddlePaddle now supports rectangular filters, If the parameter is not set or set to None, it will
the filter&#8217;s shape can be (filter_size, filter_size_y).</li> set to &#8216;filter_size&#8217; automatically.</li>
<li><strong>num_filters</strong> (<em>int</em>) &#8211; channel of output data.</li> <li><strong>num_filters</strong> (<em>int</em>) &#8211; The number of the output channels.</li>
<li><strong>num_channels</strong> (<em>int</em>) &#8211; channel of input data.</li> <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of the input channels. If the parameter is not set
<li><strong>stride</strong> (<em>int</em>) &#8211; The x dimension of the stride.</li> or set to None, it will be automatically set to the channel
<li><strong>stride_y</strong> (<em>int</em>) &#8211; The y dimension of the stride.</li> number of the &#8216;img&#8217;.</li>
<li><strong>padding</strong> (<em>int</em>) &#8211; The x dimension of padding.</li> <li><strong>stride</strong> (<em>int</em>) &#8211; The stride on the x axis.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The y dimension of padding.</li> <li><strong>stride_y</strong> (<em>int</em>) &#8211; The stride on the y axis. If the parameter is not set or
set to None, it will be set to &#8216;stride&#8217; automatically.</li>
<li><strong>padding</strong> (<em>int</em>) &#8211; The padding size on the x axis.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The padding size on the y axis. If the parameter is not set
or set to None, it will be set to &#8216;padding&#8217; automatically.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -372,9 +385,9 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li> ...@@ -372,9 +385,9 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">conv_projection</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">conv_projection</code></dt>
<dd><p>Different from img_conv and conv_op, conv_projection is an Projection, <dd><p>Different from img_conv and conv_op, conv_projection is a Projection,
which can be used in mixed and conat. It use cudnn to implement which can be used in mixed and concat. It uses cudnn to implement
conv and only support GPU mode.</p> convolution and only supports GPU mode.</p>
<p>The example usage is:</p> <p>The example usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">proj</span> <span class="o">=</span> <span class="n">conv_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">input1</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">proj</span> <span class="o">=</span> <span class="n">conv_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">input1</span><span class="p">,</span>
<span class="n">filter_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">filter_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span>
...@@ -388,26 +401,39 @@ conv and only support GPU mode.</p> ...@@ -388,26 +401,39 @@ conv and only support GPU mode.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>filter_size</strong> (<em>int</em>) &#8211; The x dimension of a filter kernel.</li> <li><strong>filter_size</strong> (<em>int | tuple | list</em>) &#8211; The dimensions of the filter kernel. If the parameter is
<li><strong>filter_size_y</strong> (<em>int</em>) &#8211; The y dimension of a filter kernel. Since set to one integer, the two dimensions on x and y axises
PaddlePaddle now supports rectangular filters, will be same when filter_size_y is not set. If it is set
the filter&#8217;s shape can be (filter_size, filter_size_y).</li> to a list, the first element indicates the dimension on
<li><strong>num_filters</strong> (<em>int</em>) &#8211; channel of output data.</li> the x axis, and the second is used to specify the dimension
<li><strong>num_channels</strong> (<em>int</em>) &#8211; channel of input data.</li> on the y axis when filter_size is not provided.</li>
<li><strong>stride</strong> (<em>int</em>) &#8211; The x dimension of the stride.</li> <li><strong>filter_size_y</strong> (<em>int</em>) &#8211; The dimension of the filter kernel on the y axis. If the parameter
<li><strong>stride_y</strong> (<em>int</em>) &#8211; The y dimension of the stride.</li> is not set, it will be set automatically according to filter_size.</li>
<li><strong>padding</strong> (<em>int</em>) &#8211; The x dimension of padding.</li> <li><strong>num_filters</strong> (<em>int</em>) &#8211; The number of filters.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The y dimension of padding.</li> <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of the input channels.</li>
<li><strong>stride</strong> (<em>int | tuple | list</em>) &#8211; The strides. If the parameter is set to one integer, the strides
on x and y axises will be same when stride_y is not set. If it is
set to a list, the first element indicates the stride on the x axis,
and the second is used to specify the stride on the y axis when
stride_y is not provided.</li>
<li><strong>stride_y</strong> (<em>int</em>) &#8211; The stride on the y axis.</li>
<li><strong>padding</strong> (<em>int | tuple | list</em>) &#8211; The padding sizes. If the parameter is set to one integer, the padding
sizes on x and y axises will be same when padding_y is not set. If it
is set to a list, the first element indicates the padding size on the
x axis, and the second is used to specify the padding size on the y axis
when padding_y is not provided.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The padding size on the y axis.</li>
<li><strong>groups</strong> (<em>int</em>) &#8211; The group number.</li> <li><strong>groups</strong> (<em>int</em>) &#8211; The group number.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; Convolution param attribute. None means default attribute</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute of the convolution. See paddle.v2.attr.ParameterAttribute for
<li><strong>trans</strong> (<em>bool</em>) &#8211; whether it is convTrans or conv</li> details.</li>
<li><strong>trans</strong> (<em>bool</em>) &#8211; Whether it is ConvTransProjection or ConvProjection</li>
</ul> </ul>
</td> </td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">A DotMulProjection Object.</p> <tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">A Projection Object.</p>
</td> </td>
</tr> </tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">DotMulProjection</p> <tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">ConvTransProjection | ConvProjection</p>
</td> </td>
</tr> </tr>
</tbody> </tbody>
...@@ -421,7 +447,7 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li> ...@@ -421,7 +447,7 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">conv_shift</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">conv_shift</code></dt>
<dd><dl class="docutils"> <dd><dl class="docutils">
<dt>This layer performs cyclic convolution for two input. For example:</dt> <dt>This layer performs cyclic convolution on two inputs. For example:</dt>
<dd><ul class="first last simple"> <dd><ul class="first last simple">
<li>a[in]: contains M elements.</li> <li>a[in]: contains M elements.</li>
<li>b[in]: contains N elements (N should be odd).</li> <li>b[in]: contains N elements (N should be odd).</li>
...@@ -432,7 +458,7 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li> ...@@ -432,7 +458,7 @@ the filter&#8217;s shape can be (filter_size, filter_size_y).</li>
<div class="math"> <div class="math">
\[c[i] = \sum_{j=-(N-1)/2}^{(N-1)/2}a_{i+j} * b_{j}\]</div> \[c[i] = \sum_{j=-(N-1)/2}^{(N-1)/2}a_{i+j} * b_{j}\]</div>
<dl class="docutils"> <dl class="docutils">
<dt>In this formular:</dt> <dt>In this formula:</dt>
<dd><ul class="first last simple"> <dd><ul class="first last simple">
<li>a&#8217;s index is computed modulo M. When it is negative, then get item from <li>a&#8217;s index is computed modulo M. When it is negative, then get item from
the right side (which is the end of array) to the left.</li> the right side (which is the end of array) to the left.</li>
...@@ -451,9 +477,10 @@ the right size (which is the end of array) to the left.</li> ...@@ -451,9 +477,10 @@ the right size (which is the end of array) to the left.</li>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Input layer a.</li> <li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input of this layer.</li>
<li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input layer b.</li> <li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The second input of this layer.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; layer&#8217;s extra attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -512,7 +539,7 @@ two image dimension.</li> ...@@ -512,7 +539,7 @@ two image dimension.</li>
currently supports rectangular filters, the filter&#8217;s currently supports rectangular filters, the filter&#8217;s
shape will be (filter_size, filter_size_y).</li> shape will be (filter_size, filter_size_y).</li>
<li><strong>num_filters</strong> &#8211; Each filter group&#8217;s number of filter</li> <li><strong>num_filters</strong> &#8211; Each filter group&#8217;s number of filter</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Relu is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Relu is the default activation.</li>
<li><strong>groups</strong> (<em>int</em>) &#8211; Group size of filters.</li> <li><strong>groups</strong> (<em>int</em>) &#8211; Group size of filters.</li>
<li><strong>stride</strong> (<em>int | tuple | list</em>) &#8211; The x dimension of the stride. Or input a tuple for two image <li><strong>stride</strong> (<em>int | tuple | list</em>) &#8211; The x dimension of the stride. Or input a tuple for two image
dimension.</li> dimension.</li>
...@@ -628,7 +655,7 @@ number plus one equals context_len.</p> ...@@ -628,7 +655,7 @@ number plus one equals context_len.</p>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>context_len</strong> (<em>int</em>) &#8211; The context length equals the lookahead step number <li><strong>context_len</strong> (<em>int</em>) &#8211; The context length equals the lookahead step number
plus one.</li> plus one.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</li> details.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
...@@ -760,15 +787,23 @@ The details please refer to ...@@ -760,15 +787,23 @@ The details please refer to
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">maxout</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">maxout</code></dt>
<dd><dl class="docutils"> <dd><dl class="docutils">
<dt>A layer to do max out on conv layer output.</dt> <dt>A layer to do max out on convolutional layer output.</dt>
<dd><ul class="first last simple"> <dd><ul class="first last simple">
<li>Input: output of a conv layer.</li> <li>Input: the output of a convolutional layer.</li>
<li>Output: feature map size same as input. Channel is (input channel) / groups.</li> <li>Output: feature map size same as the input&#8217;s, and its channel number is
(input channel) / groups.</li>
</ul> </ul>
</dd> </dd>
</dl> </dl>
<p>So groups should be larger than 1, and the num of channels should be able <p>So groups should be larger than 1, and the num of channels should be able
to devided by groups.</p> to be devided by groups.</p>
<dl class="docutils">
<dt>Reference:</dt>
<dd>Maxout Networks
<a class="reference external" href="http://www.jmlr.org/proceedings/papers/v28/goodfellow13.pdf">http://www.jmlr.org/proceedings/papers/v28/goodfellow13.pdf</a>
Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
<a class="reference external" href="https://arxiv.org/pdf/1312.6082v4.pdf">https://arxiv.org/pdf/1312.6082v4.pdf</a></dd>
</dl>
<div class="math"> <div class="math">
\[y_{si+j} = \max_k x_{gsi + sk + j} \[y_{si+j} = \max_k x_{gsi + sk + j}
g = groups g = groups
...@@ -776,14 +811,6 @@ s = input.size / num_channels ...@@ -776,14 +811,6 @@ s = input.size / num_channels
0 \le i &lt; num_channels / groups 0 \le i &lt; num_channels / groups
0 \le j &lt; s 0 \le j &lt; s
0 \le k &lt; groups\]</div> 0 \le k &lt; groups\]</div>
<dl class="docutils">
<dt>Please refer to Paper:</dt>
<dd><ul class="first last simple">
<li>Maxout Networks: <a class="reference external" href="http://www.jmlr.org/proceedings/papers/v28/goodfellow13.pdf">http://www.jmlr.org/proceedings/papers/v28/goodfellow13.pdf</a></li>
<li>Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks: <a class="reference external" href="https://arxiv.org/pdf/1312.6082v4.pdf">https://arxiv.org/pdf/1312.6082v4.pdf</a></li>
</ul>
</dd>
</dl>
<p>The simple usage is:</p> <p>The simple usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">maxout</span> <span class="o">=</span> <span class="n">maxout</span><span class="p">(</span><span class="nb">input</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">maxout</span> <span class="o">=</span> <span class="n">maxout</span><span class="p">(</span><span class="nb">input</span><span class="p">,</span>
<span class="n">num_channels</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span> <span class="n">num_channels</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span>
...@@ -796,11 +823,13 @@ s = input.size / num_channels ...@@ -796,11 +823,13 @@ s = input.size / num_channels
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>num_channels</strong> (<em>int | None</em>) &#8211; The channel number of input layer. If None will be set <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of input channels. If the parameter is not set or
automatically from previous output.</li> set to None, its actual value will be automatically set to
the channels number of the input.</li>
<li><strong>groups</strong> (<em>int</em>) &#8211; The group number of input layer.</li> <li><strong>groups</strong> (<em>int</em>) &#8211; The group number of input layer.</li>
<li><strong>name</strong> (<em>None | basestring.</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1098,14 +1127,16 @@ out_{i} = act(in_{i} + out_{i+1} * W) \ \ \text{for} \ start &lt;= i &lt; end\en ...@@ -1098,14 +1127,16 @@ out_{i} = act(in_{i} + out_{i+1} * W) \ \ \text{for} \ start &lt;= i &lt; end\en
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to
False or an object whose type is not paddle.v2.attr.ParameterAttribute, False or an object whose type is not paddle.v2.attr.ParameterAttribute,
no bias is defined. If the parameter is set to True, no bias is defined. If the parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; parameter attribute.</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1149,7 +1180,7 @@ more details about LSTM.</p> ...@@ -1149,7 +1180,7 @@ more details about LSTM.</p>
<li><strong>size</strong> (<em>int</em>) &#8211; DEPRECATED. size of the lstm cell</li> <li><strong>size</strong> (<em>int</em>) &#8211; DEPRECATED. size of the lstm cell</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>reverse</strong> (<em>bool</em>) &#8211; is sequence process reversed or not.</li> <li><strong>reverse</strong> (<em>bool</em>) &#8211; is sequence process reversed or not.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default. <span class="math">\(h_t\)</span></li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; gate activation type, paddle.v2.activation.Sigmoid by default.</li> <li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; gate activation type, paddle.v2.activation.Sigmoid by default.</li>
<li><strong>state_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; state activation type, paddle.v2.activation.Tanh by default.</li> <li><strong>state_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; state activation type, paddle.v2.activation.Tanh by default.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
...@@ -1309,8 +1340,8 @@ It is ignored when name is provided.</li> ...@@ -1309,8 +1340,8 @@ It is ignored when name is provided.</li>
<dd><p>Recurrent layer group is an extremely flexible recurrent unit in <dd><p>Recurrent layer group is an extremely flexible recurrent unit in
PaddlePaddle. As long as the user defines the calculation done within a PaddlePaddle. As long as the user defines the calculation done within a
time step, PaddlePaddle will iterate such a recurrent calculation over time step, PaddlePaddle will iterate such a recurrent calculation over
sequence input. This is extremely usefull for attention based model, or sequence input. This is useful for attention-based models, or Neural
Neural Turning Machine like models.</p> Turning Machine like models.</p>
<p>The basic usage (time steps) is:</p> <p>The basic usage (time steps) is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="nb">input</span><span class="p">):</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="nb">input</span><span class="p">):</span>
<span class="n">output</span> <span class="o">=</span> <span class="n">fc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span> <span class="n">output</span> <span class="o">=</span> <span class="n">fc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span>
...@@ -1333,22 +1364,21 @@ Neural Turning Machine like models.</p> ...@@ -1333,22 +1364,21 @@ Neural Turning Machine like models.</p>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>step</strong> (<em>callable</em>) &#8211; <p>recurrent one time step function.The input of this function is <li><strong>step</strong> (<em>callable</em>) &#8211; <p>A step function which takes the input of recurrent_group as its own
input of the group. The return of this function will be input and returns values as recurrent_group&#8217;s output every time step.</p>
recurrent group&#8217;s return value.</p> <p>The recurrent group scatters a sequence into time steps. And
<p>The recurrent group scatter a sequence into time steps. And for each time step, it will invoke step function, and return
for each time step, will invoke step function, and return a time step result. Then gather outputs of each time step into
a time step result. Then gather each time step of output into
layer group&#8217;s output.</p> layer group&#8217;s output.</p>
</li> </li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; recurrent_group&#8217;s name.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The recurrent_group&#8217;s name. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | StaticInput | SubsequenceInput | list | tuple</em>) &#8211; <p>Input links array.</p> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | StaticInput | SubsequenceInput | list | tuple</em>) &#8211; <p>Input links array.</p>
<p>paddle.v2.config_base.Layer will be scattered into time steps. <p>paddle.v2.config_base.Layer will be scattered into time steps.
SubsequenceInput will be scattered into sequence steps. SubsequenceInput will be scattered into sequence steps.
StaticInput will be imported to each time step, and doesn&#8217;t change StaticInput will be imported to each time step, and doesn&#8217;t change
through time. It&#8217;s a mechanism to access layer outside step function.</p> over time. It&#8217;s a mechanism to access layer outside step function.</p>
</li> </li>
<li><strong>reverse</strong> (<em>bool</em>) &#8211; If reverse is set true, the recurrent unit will process the <li><strong>reverse</strong> (<em>bool</em>) &#8211; If reverse is set to True, the recurrent unit will process the
input sequence in a reverse order.</li> input sequence in a reverse order.</li>
<li><strong>targetInlink</strong> (<em>paddle.v2.config_base.Layer | SubsequenceInput</em>) &#8211; <p>DEPRECATED. <li><strong>targetInlink</strong> (<em>paddle.v2.config_base.Layer | SubsequenceInput</em>) &#8211; <p>DEPRECATED.
The input layer which share info with layer group&#8217;s output</p> The input layer which share info with layer group&#8217;s output</p>
...@@ -1387,8 +1417,8 @@ input vectors.</p> ...@@ -1387,8 +1417,8 @@ input vectors.</p>
<p>The state of lstm step is <span class="math">\(c_{t-1}\)</span>. And lstm step layer will do</p> <p>The state of lstm step is <span class="math">\(c_{t-1}\)</span>. And lstm step layer will do</p>
<div class="math"> <div class="math">
\[ \begin{align}\begin{aligned}i_t = \sigma(input + W_{ci}c_{t-1} + b_i)\\...\end{aligned}\end{align} \]</div> \[ \begin{align}\begin{aligned}i_t = \sigma(input + W_{ci}c_{t-1} + b_i)\\...\end{aligned}\end{align} \]</div>
<p>This layer has two outputs. Default output is <span class="math">\(h_t\)</span>. The other <p>This layer has two outputs. The default output is <span class="math">\(h_t\)</span>. The other
output is <span class="math">\(o_t\)</span>, whose name is &#8216;state&#8217; and can use output is <span class="math">\(o_t\)</span>, whose name is &#8216;state&#8217; and users can use
<code class="code docutils literal"><span class="pre">get_output</span></code> to extract this output.</p> <code class="code docutils literal"><span class="pre">get_output</span></code> to extract this output.</p>
<table class="docutils field-list" frame="void" rules="none"> <table class="docutils field-list" frame="void" rules="none">
<col class="field-name" /> <col class="field-name" />
...@@ -1396,17 +1426,19 @@ output is <span class="math">\(o_t\)</span>, whose name is &#8216;state&#8217; a ...@@ -1396,17 +1426,19 @@ output is <span class="math">\(o_t\)</span>, whose name is &#8216;state&#8217; a
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; Layer&#8217;s size. NOTE: lstm layer&#8217;s size, should be equal to <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer&#8217;s output, which must be
<code class="code docutils literal"><span class="pre">input.size/4</span></code>, and should be equal to equal to the dimension of the state.</li>
<code class="code docutils literal"><span class="pre">state.size</span></code>.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input layer. <span class="math">\(Wx_t + Wh_{t-1}\)</span></li> <li><strong>state</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The state of the LSTM unit.</li>
<li><strong>state</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; State Layer. <span class="math">\(c_{t-1}\)</span></li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default activation.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Tanh is the default.</li> <li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of the gate. paddle.v2.activation.Sigmoid is the
<li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Gate Activation Type. paddle.v2.activation.Sigmoid is the default.</li> default activation.</li>
<li><strong>state_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; State Activation Type. paddle.v2.activation.Tanh is the default.</li> <li><strong>state_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of the state. paddle.v2.activation.Tanh is the
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | True</em>) &#8211; The parameter attribute for bias. If this parameter is default activation.</li>
set to True or None, the bias is initialized to zero.</li> <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; layer&#8217;s extra attribute.</li> whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1431,19 +1463,22 @@ set to True or None, the bias is initialized to zero.</li> ...@@ -1431,19 +1463,22 @@ set to True or None, the bias is initialized to zero.</li>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; </li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer, whose dimension can be divided by 3.</li>
<li><strong>output_mem</strong> &#8211; </li> <li><strong>output_mem</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; A memory which memorizes the output of this layer at previous
<li><strong>size</strong> &#8211; </li> time step.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; </li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer&#8217;s output. If it is not set or set to None,
<li><strong>name</strong> &#8211; The name of this layer. It is optional.</li> it will be set to one-third of the dimension of the input automatically.</li>
<li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of this layer&#8217;s two gates. Default is Sigmoid.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of this layer&#8217;s output. paddle.v2.activation.Tanh
is the default activation.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>gate_act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of this layer&#8217;s two gates. paddle.v2.activation.Sigmoid is
the default activation.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to
False or an object whose type is not paddle.v2.attr.ParameterAttribute, no bias False or an object whose type is not paddle.v2.attr.ParameterAttribute, no bias
is defined. If this parameter is set to True, is defined. If this parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>param_attr</strong> &#8211; the parameter_attribute for transforming the output_mem <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for details.</li>
from previous step.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for details.</li>
<li><strong>layer_attr</strong> &#8211; </li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1497,7 +1532,8 @@ to maintain tractability.</p> ...@@ -1497,7 +1532,8 @@ to maintain tractability.</p>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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>base string</em>) &#8211; Name of the recurrent unit that generates sequences.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of the recurrent unit that is responsible for
generating sequences. It is optional.</li>
<li><strong>step</strong> (<em>callable</em>) &#8211; <p>A callable function that defines the calculation in a time <li><strong>step</strong> (<em>callable</em>) &#8211; <p>A callable function that defines the calculation in a time
step, and it is applied to sequences with arbitrary length by step, and it is applied to sequences with arbitrary length by
sharing a same set of weights.</p> sharing a same set of weights.</p>
...@@ -1555,10 +1591,11 @@ the output from input.</p> ...@@ -1555,10 +1591,11 @@ the output from input.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; get output layer&#8217;s input. And this layer should contains <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input layer. And this layer should contain
multiple outputs.</li> multiple outputs.</li>
<li><strong>arg_name</strong> (<em>basestring</em>) &#8211; Output name from input.</li> <li><strong>arg_name</strong> (<em>basestring</em>) &#8211; The name of the output to be extracted from the input layer.</li>
<li><strong>layer_attr</strong> &#8211; Layer&#8217;s extra attribute.</li> <li><strong>layer_attr</strong> &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -1609,7 +1646,7 @@ Each inputs is a projection or operator.</p> ...@@ -1609,7 +1646,7 @@ Each inputs is a projection or operator.</p>
<li><strong>size</strong> (<em>int</em>) &#8211; layer size.</li> <li><strong>size</strong> (<em>int</em>) &#8211; layer size.</li>
<li><strong>input</strong> &#8211; The input of this layer. It is an optional parameter. If set, <li><strong>input</strong> &#8211; The input of this layer. It is an optional parameter. If set,
then this function will just return layer&#8217;s name.</li> then this function will just return layer&#8217;s name.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.</li> parameter is set to True, the bias is initialized to zero.</li>
...@@ -2152,7 +2189,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p> ...@@ -2152,7 +2189,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p>
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>list | tuple | collections.Sequence</em>) &#8211; input layers or projections</li> <li><strong>input</strong> (<em>list | tuple | collections.Sequence</em>) &#8211; input layers or projections</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default activation.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li>
</ul> </ul>
</td> </td>
...@@ -2197,7 +2234,7 @@ processed in one batch.</p> ...@@ -2197,7 +2234,7 @@ processed in one batch.</p>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input sequence layer</li> <li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input sequence layer</li>
<li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input sequence layer</li> <li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input sequence layer</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default activation.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
...@@ -2321,11 +2358,11 @@ beam training.</p> ...@@ -2321,11 +2358,11 @@ beam training.</p>
</dl> </dl>
<div class="math"> <div class="math">
\[ \begin{align}\begin{aligned}outputH = 1 + (2 * padding_y + imgSizeH - block_y + stride_y - 1) / stride_y\\outputW = 1 + (2 * padding_x + imgSizeW - block_x + stride_x - 1) / stride_x\end{aligned}\end{align} \]</div> \[ \begin{align}\begin{aligned}outputH = 1 + (2 * padding_y + imgSizeH - block_y + stride_y - 1) / stride_y\\outputW = 1 + (2 * padding_x + imgSizeW - block_x + stride_x - 1) / stride_x\end{aligned}\end{align} \]</div>
<p>The expand method is the same with ExpandConvLayer, but saved the transposed <p>The expanding method is the same with ExpandConvLayer, but saved the transposed
value. After expanding, output.sequenceStartPositions will store timeline. value. After expanding, output.sequenceStartPositions will store timeline.
The number of time steps are outputH * outputW and the dimension of each The number of time steps is outputH * outputW and the dimension of each
time step is block_y * block_x * num_channels. This layer can be used after time step is block_y * block_x * num_channels. This layer can be used after
convolution neural network, and before recurrent neural network.</p> convolutional neural network, and before recurrent neural network.</p>
<p>The simple usage is:</p> <p>The simple usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">block_expand</span> <span class="o">=</span> <span class="n">block_expand</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">block_expand</span> <span class="o">=</span> <span class="n">block_expand</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span>
<span class="n">num_channels</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span> <span class="n">num_channels</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span>
...@@ -2341,15 +2378,18 @@ convolution neural network, and before recurrent neural network.</p> ...@@ -2341,15 +2378,18 @@ convolution neural network, and before recurrent neural network.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>num_channels</strong> (<em>int | None</em>) &#8211; The channel number of input layer.</li> <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of input channels. If the parameter is not set or
set to None, its actual value will be automatically set to
the channels number of the input.</li>
<li><strong>block_x</strong> (<em>int</em>) &#8211; The width of sub block.</li> <li><strong>block_x</strong> (<em>int</em>) &#8211; The width of sub block.</li>
<li><strong>block_y</strong> (<em>int</em>) &#8211; The width of sub block.</li> <li><strong>block_y</strong> (<em>int</em>) &#8211; The width of sub block.</li>
<li><strong>stride_x</strong> (<em>int</em>) &#8211; The stride size in horizontal direction.</li> <li><strong>stride_x</strong> (<em>int</em>) &#8211; The stride size in horizontal direction.</li>
<li><strong>stride_y</strong> (<em>int</em>) &#8211; The stride size in vertical direction.</li> <li><strong>stride_y</strong> (<em>int</em>) &#8211; The stride size in vertical direction.</li>
<li><strong>padding_x</strong> (<em>int</em>) &#8211; The padding size in horizontal direction.</li> <li><strong>padding_x</strong> (<em>int</em>) &#8211; The padding size in horizontal direction.</li>
<li><strong>padding_y</strong> (<em>int</em>) &#8211; The padding size in vertical direction.</li> <li><strong>padding_y</strong> (<em>int</em>) &#8211; The padding size in vertical direction.</li>
<li><strong>name</strong> (<em>None | basestring.</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring.</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -2455,7 +2495,7 @@ in the column direction. This is equivalent to apply ...@@ -2455,7 +2495,7 @@ in the column direction. This is equivalent to apply
concat() with num_repeats same input. concat() with num_repeats same input.
False for treating input as column vector and repeating False for treating input as column vector and repeating
in the row direction.</li> in the row direction.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default activation.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li>
</ul> </ul>
</td> </td>
...@@ -2531,7 +2571,7 @@ output sequence has T*M/N instances, the dimension of each instance is N.</p> ...@@ -2531,7 +2571,7 @@ output sequence has T*M/N instances, the dimension of each instance is N.</p>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>reshape_size</strong> (<em>int</em>) &#8211; the size of reshaped sequence.</li> <li><strong>reshape_size</strong> (<em>int</em>) &#8211; the size of reshaped sequence.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Identity is the default activation.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
...@@ -2587,7 +2627,7 @@ Please refer to dropout for details.</p> ...@@ -2587,7 +2627,7 @@ Please refer to dropout for details.</p>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; Input layers. It could be a paddle.v2.config_base.Layer or list/tuple of <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple</em>) &#8211; Input layers. It could be a paddle.v2.config_base.Layer or list/tuple of
paddle.v2.config_base.Layer.</li> paddle.v2.config_base.Layer.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The bias attribute. If the parameter is set to False or an object
whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the whose type is not paddle.v2.attr.ParameterAttribute, no bias is defined. If the
parameter is set to True, the bias is initialized to zero.</li> parameter is set to True, the bias is initialized to zero.</li>
...@@ -2652,9 +2692,10 @@ processed in one batch.</p> ...@@ -2652,9 +2692,10 @@ processed in one batch.</p>
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>weights</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer.</li> <li><strong>weights</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer.</li>
<li><strong>vectors</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The vector layer.</li> <li><strong>vectors</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The vector layer.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; the dimension of this layer.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -2901,8 +2942,7 @@ where size is the parameter of this layer indicating the output dimension.</p> ...@@ -2901,8 +2942,7 @@ where size is the parameter of this layer indicating the output dimension.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">slope_intercept</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">slope_intercept</code></dt>
<dd><p>This layer for applying a slope and an intercept to the input <dd><p>This layer for applying a slope and an intercept to the input.</p>
element-wise. There is no activation and weight.</p>
<div class="math"> <div class="math">
\[y = slope * x + intercept\]</div> \[y = slope * x + intercept\]</div>
<p>The simple usage is:</p> <p>The simple usage is:</p>
...@@ -2916,9 +2956,10 @@ element-wise. There is no activation and weight.</p> ...@@ -2916,9 +2956,10 @@ element-wise. There is no activation and weight.</p>
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>slope</strong> (<em>float.</em>) &#8211; the scale factor.</li> <li><strong>slope</strong> (<em>float</em>) &#8211; The scale factor.</li>
<li><strong>intercept</strong> (<em>float.</em>) &#8211; the offset.</li> <li><strong>intercept</strong> (<em>float</em>) &#8211; The offset.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -2938,8 +2979,8 @@ element-wise. There is no activation and weight.</p> ...@@ -2938,8 +2979,8 @@ element-wise. There is no activation and weight.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">tensor</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">tensor</code></dt>
<dd><p>This layer performs tensor operation for two input. <dd><p>This layer performs tensor operation on two inputs.
For example, each sample:</p> For example:</p>
<div class="math"> <div class="math">
\[y_{i} = a * W_{i} * {b^\mathrm{T}}, i=0,1,...,K-1\]</div> \[y_{i} = a * W_{i} * {b^\mathrm{T}}, i=0,1,...,K-1\]</div>
<dl class="docutils"> <dl class="docutils">
...@@ -2963,16 +3004,18 @@ For example, each sample:</p> ...@@ -2963,16 +3004,18 @@ For example, each sample:</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Input layer a.</li> <li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input of this layer.</li>
<li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; input layer b.</li> <li><strong>b</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The second input of this layer.</li>
<li><strong>size</strong> (<em>int.</em>) &#8211; the layer dimension.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The Parameter Attribute.</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</li>
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; The parameter attribute for bias. If this parameter is set to
False or an object whose type is not paddle.v2.attr.ParameterAttribute, False or an object whose type is not paddle.v2.attr.ParameterAttribute,
no bias is defined. If this parameter is set to True, no bias is defined. If this parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3127,7 +3170,8 @@ The result is stored in output.ids.</p> ...@@ -3127,7 +3170,8 @@ The result is stored in output.ids.</p>
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3147,7 +3191,7 @@ The result is stored in output.ids.</p> ...@@ -3147,7 +3191,7 @@ The result is stored in output.ids.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">sampling_id</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">sampling_id</code></dt>
<dd><p>A layer for sampling id from multinomial distribution from the input layer. <dd><p>A layer for sampling id from a multinomial distribution from the input layer.
Sampling one id for one sample.</p> Sampling one id for one sample.</p>
<p>The simple usage is:</p> <p>The simple usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">samping_id</span> <span class="o">=</span> <span class="n">sampling_id</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">samping_id</span> <span class="o">=</span> <span class="n">sampling_id</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span>
...@@ -3160,7 +3204,8 @@ Sampling one id for one sample.</p> ...@@ -3160,7 +3204,8 @@ Sampling one id for one sample.</p>
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3229,12 +3274,12 @@ details.</li> ...@@ -3229,12 +3274,12 @@ details.</li>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">pad</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">pad</code></dt>
<dd><p>This operation pads zeros to the input data according to pad_c,pad_h <dd><p>This operation pads zeros to the input data according to pad_c,pad_h
and pad_w. pad_c, pad_h, pad_w specifies the which dimension and size and pad_w. pad_c, pad_h, pad_w specify the size in the corresponding
of padding. And the input data shape is NCHW.</p> dimension. And the input data shape is NCHW.</p>
<p>For example, pad_c=[2,3] means padding 2 zeros before the <p>For example, pad_c=[2,3] means padding 2 zeros before the input data
input data and 3 zeros after the input data in channel dimension. and 3 zeros after the input data in the channel dimension. pad_h means
pad_h means padding zeros in height dimension. pad_w means padding zeros padding zeros in the height dimension. pad_w means padding zeros in the
in width dimension.</p> width dimension.</p>
<p>For example,</p> <p>For example,</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="nb">input</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">)</span> <span class="o">=</span> <span class="p">[</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="nb">input</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">)</span> <span class="o">=</span> <span class="p">[</span>
<span class="p">[</span> <span class="p">[[</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">],</span> <span class="p">[</span><span class="mi">3</span><span class="p">,</span><span class="mi">4</span><span class="p">,</span><span class="mi">5</span><span class="p">]],</span> <span class="p">[</span> <span class="p">[[</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">3</span><span class="p">],</span> <span class="p">[</span><span class="mi">3</span><span class="p">,</span><span class="mi">4</span><span class="p">,</span><span class="mi">5</span><span class="p">]],</span>
...@@ -3270,10 +3315,11 @@ in width dimension.</p> ...@@ -3270,10 +3315,11 @@ in width dimension.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>pad_c</strong> (<em>list | None</em>) &#8211; padding size in channel dimension.</li> <li><strong>pad_c</strong> (<em>list | None</em>) &#8211; The padding size in the channel dimension.</li>
<li><strong>pad_h</strong> (<em>list | None</em>) &#8211; padding size in height dimension.</li> <li><strong>pad_h</strong> (<em>list | None</em>) &#8211; The padding size in the height dimension.</li>
<li><strong>pad_w</strong> (<em>list | None</em>) &#8211; padding size in width dimension.</li> <li><strong>pad_w</strong> (<em>list | None</em>) &#8211; The padding size in the width dimension.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
</ul> </ul>
</td> </td>
...@@ -3312,10 +3358,9 @@ in width dimension.</p> ...@@ -3312,10 +3358,9 @@ in width dimension.</p>
<li><strong>label</strong> &#8211; The input label.</li> <li><strong>label</strong> &#8211; The input label.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation. <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default.</li> 1.0 is the default value.</li>
<li><strong>weight</strong> (<em>LayerOutout</em>) &#8211; The cost of each sample is multiplied with each weight. <li><strong>weight</strong> (<em>LayerOutout</em>) &#8211; The weight layer defines a weight for each sample in the
The weight should be a layer with size=1. Note that gradient mini-batch. It is optional.</li>
will not be calculated for weight.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
</ul> </ul>
...@@ -3353,7 +3398,7 @@ Input should be a vector of positive numbers, without normalization.</p> ...@@ -3353,7 +3398,7 @@ Input should be a vector of positive numbers, without normalization.</p>
<li><strong>label</strong> &#8211; The input label.</li> <li><strong>label</strong> &#8211; The input label.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation. <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default.</li> 1.0 is the default value.</li>
<li><strong>softmax_selfnorm_alpha</strong> (<em>float</em>) &#8211; The scale factor affects the cost.</li> <li><strong>softmax_selfnorm_alpha</strong> (<em>float</em>) &#8211; The scale factor affects the cost.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
...@@ -3391,7 +3436,7 @@ details.</li> ...@@ -3391,7 +3436,7 @@ details.</li>
<li><strong>label</strong> &#8211; The input label.</li> <li><strong>label</strong> &#8211; The input label.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation. <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default.</li> 1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
</ul> </ul>
...@@ -3449,7 +3494,7 @@ ight <a href="#id2"><span class="problematic" id="id3">|</span></a>leq delta</p> ...@@ -3449,7 +3494,7 @@ ight <a href="#id2"><span class="problematic" id="id3">|</span></a>leq delta</p>
<tr class="field-even field"><th class="field-name">type delta:</th><td class="field-body">float</td> <tr class="field-even field"><th class="field-name">type delta:</th><td class="field-body">float</td>
</tr> </tr>
<tr class="field-odd field"><th class="field-name">param coeff:</th><td class="field-body">The weight of the gradient in the back propagation. <tr class="field-odd field"><th class="field-name">param coeff:</th><td class="field-body">The weight of the gradient in the back propagation.
1.0 is the default.</td> 1.0 is the default value.</td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">type coeff:</th><td class="field-body">float</td> <tr class="field-even field"><th class="field-name">type coeff:</th><td class="field-body">float</td>
</tr> </tr>
...@@ -3506,7 +3551,7 @@ a true binary class label :math:<a href="#id6"><span class="problematic" id="id7 ...@@ -3506,7 +3551,7 @@ a true binary class label :math:<a href="#id6"><span class="problematic" id="id7
<tr class="field-even field"><th class="field-name">type name:</th><td class="field-body">basestring</td> <tr class="field-even field"><th class="field-name">type name:</th><td class="field-body">basestring</td>
</tr> </tr>
<tr class="field-odd field"><th class="field-name">param coeff:</th><td class="field-body">The weight of the gradient in the back propagation. <tr class="field-odd field"><th class="field-name">param coeff:</th><td class="field-body">The weight of the gradient in the back propagation.
1.0 is the default.</td> 1.0 is the default value.</td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">type coeff:</th><td class="field-body">float</td> <tr class="field-even field"><th class="field-name">type coeff:</th><td class="field-body">float</td>
</tr> </tr>
...@@ -3546,20 +3591,20 @@ details.</td> ...@@ -3546,20 +3591,20 @@ details.</td>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; Samples of the same query should be loaded as sequence.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input of this layer, which is often a document
<li><strong>score</strong> &#8211; The 2nd input. Score of each sample.</li> samples list of the same query and whose type must be sequence.</li>
<li><strong>score</strong> &#8211; The scores of the samples.</li>
<li><strong>NDCG_num</strong> (<em>int</em>) &#8211; The size of NDCG (Normalized Discounted Cumulative Gain), <li><strong>NDCG_num</strong> (<em>int</em>) &#8211; The size of NDCG (Normalized Discounted Cumulative Gain),
e.g., 5 for NDCG&#64;5. It must be less than or equal to the e.g., 5 for NDCG&#64;5. It must be less than or equal to the
minimum size of lists.</li> minimum size of the list.</li>
<li><strong>max_sort_size</strong> (<em>int</em>) &#8211; The size of partial sorting in calculating gradient. <li><strong>max_sort_size</strong> (<em>int</em>) &#8211; The size of partial sorting in calculating gradient. If
If max_sort_size = -1, then for each list, the max_sort_size is equal to -1 or greater than the number
algorithm will sort the entire list to get gradient. of the samples in the list, then the algorithm will sort
In other cases, max_sort_size must be greater than or the entire list to compute the gradient. In other cases,
equal to NDCG_num. And if max_sort_size is greater max_sort_size must be greater than or equal to NDCG_num.</li>
than the size of a list, the algorithm will sort the <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
entire list of get gradient.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
<li><strong>name</strong> (<em>None | basestring</em>) &#8211; The name of this layer. It is optional.</li> details.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3588,12 +3633,14 @@ entire list of get gradient.</li> ...@@ -3588,12 +3633,14 @@ entire list of get gradient.</li>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Network prediction.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Data label.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight affects the cost, namely the scale of cost. <li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the
It is an optional argument.</li> mini-batch. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The coefficient affects the gradient in the backward.</li> <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; layer&#8217;s extra attribute.</li> 1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3613,10 +3660,12 @@ It is an optional argument.</li> ...@@ -3613,10 +3660,12 @@ It is an optional argument.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">rank_cost</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">rank_cost</code></dt>
<dd><p>A cost Layer for learning to rank using gradient descent. Details can refer <dd><p>A cost Layer for learning to rank using gradient descent.</p>
to <a class="reference external" href="http://research.microsoft.com/en-us/um/people/cburges/papers/ICML_ranking.pdf">papers</a>. <dl class="docutils">
This layer contains at least three inputs. The weight is an optional <dt>Reference:</dt>
argument, which affects the cost.</p> <dd>Learning to Rank using Gradient Descent
<a class="reference external" href="http://research.microsoft.com/en-us/um/people/cburges/papers/ICML_ranking.pdf">http://research.microsoft.com/en-us/um/people/cburges/papers/ICML_ranking.pdf</a></dd>
</dl>
<div class="math"> <div class="math">
\[ \begin{align}\begin{aligned}C_{i,j} &amp; = -\tilde{P_{ij}} * o_{i,j} + log(1 + e^{o_{i,j}})\\o_{i,j} &amp; = o_i - o_j\\\tilde{P_{i,j}} &amp; = \{0, 0.5, 1\} \ or \ \{0, 1\}\end{aligned}\end{align} \]</div> \[ \begin{align}\begin{aligned}C_{i,j} &amp; = -\tilde{P_{ij}} * o_{i,j} + log(1 + e^{o_{i,j}})\\o_{i,j} &amp; = o_i - o_j\\\tilde{P_{i,j}} &amp; = \{0, 0.5, 1\} \ or \ \{0, 1\}\end{aligned}\end{align} \]</div>
<dl class="docutils"> <dl class="docutils">
...@@ -3644,11 +3693,13 @@ Their dimension is one.</li> ...@@ -3644,11 +3693,13 @@ Their dimension is one.</li>
<li><strong>left</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input, the size of this layer is 1.</li> <li><strong>left</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input, the size of this layer is 1.</li>
<li><strong>right</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The right input, the size of this layer is 1.</li> <li><strong>right</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The right input, the size of this layer is 1.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Label is 1 or 0, means positive order and reverse order.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Label is 1 or 0, means positive order and reverse order.</li>
<li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight affects the cost, namely the scale of cost. <li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the
It is an optional argument.</li> mini-batch. It is optional.</li>
<li><strong>name</strong> (<em>None | basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The coefficient affects the gradient in the backward.</li> <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> 1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3714,15 +3765,18 @@ field model.</p> ...@@ -3714,15 +3765,18 @@ field model.</p>
<col class="field-body" /> <col class="field-body" />
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The first input layer is the feature.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The second input layer is label.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; The category number.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The category number.</li>
<li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The third layer is &#8220;weight&#8221; of each sample, which is an <li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the
optional argument.</li> mini-batch. It is optional.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; Parameter attribute. None means default attribute</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
<li><strong>name</strong> (<em>None | basestring</em>) &#8211; The name of this layer. It is optional.</li> details.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The coefficient affects the gradient in the backward.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3744,9 +3798,9 @@ optional argument.</li> ...@@ -3744,9 +3798,9 @@ optional argument.</li>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">crf_decoding</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">crf_decoding</code></dt>
<dd><p>A layer for calculating the decoding sequence of sequential conditional <dd><p>A layer for calculating the decoding sequence of sequential conditional
random field model. The decoding sequence is stored in output.ids. 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 the input &#8216;label&#8217; 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 an incorrect
decoding or 0 for correct decoding.</p> decoding and 0 for the correct.</p>
<p>The example usage is:</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>
...@@ -3758,11 +3812,13 @@ decoding or 0 for correct decoding.</p> ...@@ -3758,11 +3812,13 @@ decoding or 0 for correct decoding.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The first input layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first input layer.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; size of this layer.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em><em> or </em><em>None</em>) &#8211; None or ground-truth label.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer | None</em>) &#8211; The input label.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; Parameter attribute. None means default attribute</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
<li><strong>name</strong> (<em>None | basestring</em>) &#8211; The name of this layer. It is optional.</li> details.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3783,18 +3839,21 @@ decoding or 0 for correct decoding.</p> ...@@ -3783,18 +3839,21 @@ decoding or 0 for correct decoding.</p>
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">ctc</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">ctc</code></dt>
<dd><p>Connectionist Temporal Classification (CTC) is designed for temporal <dd><p>Connectionist Temporal Classification (CTC) is designed for temporal
classication task. That is, for sequence labeling problems where the classication task. e.g. sequence labeling problems where the
alignment between the inputs and the target labels is unknown.</p> alignment between the inputs and the target labels is unknown.</p>
<p>More details can be found by referring to <a class="reference external" href="http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf">Connectionist Temporal <dl class="docutils">
Classification: Labelling Unsegmented Sequence Data with Recurrent <dt>Reference:</dt>
Neural Networks</a></p> <dd>Connectionist Temporal Classification: Labelling Unsegmented Sequence Data
with Recurrent Neural Networks
<a class="reference external" href="http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf">http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf</a></dd>
</dl>
<div class="admonition note"> <div class="admonition note">
<p class="first admonition-title">注解</p> <p class="first admonition-title">注解</p>
<p class="last">Considering the &#8216;blank&#8217; label needed by CTC, you need to use <p class="last">Considering the &#8216;blank&#8217; label needed by CTC, you need to use (num_classes + 1)
(num_classes + 1) as the input size. num_classes is the category number. as the size of the input, where num_classes is the category number.
And the &#8216;blank&#8217; is the last category index. So the size of &#8216;input&#8217; layer, such as And the &#8216;blank&#8217; is the last category index. So the size of &#8216;input&#8217; layer (e.g.
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
should also be num_classes + 1.</p> ctc should also be (num_classes + 1).</p>
</div> </div>
<p>The example usage is:</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>
...@@ -3809,11 +3868,12 @@ should also be num_classes + 1.</p> ...@@ -3809,11 +3868,12 @@ should also be num_classes + 1.</p>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The data layer of label with variable length.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; category numbers + 1.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer, which must be equal to (category number + 1).</li>
<li><strong>name</strong> (<em>basestring | None</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>norm_by_times</strong> (<em>bool</em>) &#8211; Whether to normalization by times. False by default.</li> <li><strong>norm_by_times</strong> (<em>bool</em>) &#8211; Whether to do normalization by times. False is the default.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3839,20 +3899,22 @@ Classification (CTC) loss. Besides, another <a class="reference external" href=" ...@@ -3839,20 +3899,22 @@ Classification (CTC) loss. Besides, another <a class="reference external" href="
the official one, is maintained to enable more compiling options. During the the official one, is maintained to enable more compiling options. During the
building process, PaddlePaddle will clone the source codes, build and building process, PaddlePaddle will clone the source codes, build and
install it to <code class="code docutils literal"><span class="pre">third_party/install/warpctc</span></code> directory.</p> install it to <code class="code docutils literal"><span class="pre">third_party/install/warpctc</span></code> directory.</p>
<p>More details of CTC can be found by referring to <a class="reference external" href="http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf">Connectionist Temporal <dl class="docutils">
Classification: Labelling Unsegmented Sequence Data with Recurrent <dt>Reference:</dt>
Neural Networks</a>.</p> <dd>Connectionist Temporal Classification: Labelling Unsegmented Sequence Data
with Recurrent Neural Networks
<a class="reference external" href="http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf">http://machinelearning.wustl.edu/mlpapers/paper_files/icml2006_GravesFGS06.pdf</a></dd>
</dl>
<div class="admonition note"> <div class="admonition note">
<p class="first admonition-title">注解</p> <p class="first admonition-title">注解</p>
<ul class="last simple"> <ul class="last simple">
<li>Let num_classes represent the category number. Considering the &#8216;blank&#8217; <li>Let num_classes represents the category number. Considering the &#8216;blank&#8217;
label needed by CTC, you need to use (num_classes + 1) as the input size. label needed by CTC, you need to use (num_classes + 1) as the size of
Thus, the size of both warp_ctc layer and &#8216;input&#8217; layer should be set to warp_ctc layer.</li>
num_classes + 1.</li>
<li>You can set &#8216;blank&#8217; to any value ranged in [0, num_classes], which <li>You can set &#8216;blank&#8217; to any value ranged in [0, num_classes], which
should be consistent as that used in your labels.</li> should be consistent with those used in your labels.</li>
<li>As a native &#8216;softmax&#8217; activation is interated to the warp-ctc library, <li>As a native &#8216;softmax&#8217; activation is interated to the warp-ctc library,
&#8216;linear&#8217; activation is expected instead in the &#8216;input&#8217; layer.</li> &#8216;linear&#8217; activation is expected to be used instead in the &#8216;input&#8217; layer.</li>
</ul> </ul>
</div> </div>
<p>The example usage is:</p> <p>The example usage is:</p>
...@@ -3869,12 +3931,13 @@ should be consistent as that used in your labels.</li> ...@@ -3869,12 +3931,13 @@ should be consistent as that used in your labels.</li>
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The data layer of label with variable length.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; category numbers + 1.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer, which must be equal to (category number + 1).</li>
<li><strong>name</strong> (<em>basestring | None</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>blank</strong> (<em>int</em>) &#8211; the &#8216;blank&#8217; label used in ctc</li> <li><strong>blank</strong> (<em>int</em>) &#8211; The &#8216;blank&#8217; label used in ctc.</li>
<li><strong>norm_by_times</strong> (<em>bool</em>) &#8211; Whether to normalization by times. False by default.</li> <li><strong>norm_by_times</strong> (<em>bool</em>) &#8211; Whether to do normalization by times. False is the default.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; Extra Layer config.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -3894,8 +3957,7 @@ should be consistent as that used in your labels.</li> ...@@ -3894,8 +3957,7 @@ should be consistent as that used in your labels.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">nce</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">nce</code></dt>
<dd><p>Noise-contrastive estimation. This layer implements the method in the <dd><p>Noise-contrastive estimation.</p>
following paper:</p>
<dl class="docutils"> <dl class="docutils">
<dt>Reference:</dt> <dt>Reference:</dt>
<dd>A fast and simple algorithm for training neural probabilistic language <dd>A fast and simple algorithm for training neural probabilistic language
...@@ -3913,19 +3975,20 @@ models. <a class="reference external" href="https://www.cs.toronto.edu/~amnih/pa ...@@ -3913,19 +3975,20 @@ models. <a class="reference external" href="https://www.cs.toronto.edu/~amnih/pa
<tbody valign="top"> <tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple | collections.Sequence</em>) &#8211; The input layers. It should be a paddle.v2.config_base.Layer or a list/tuple <li><strong>input</strong> (<em>paddle.v2.config_base.Layer | list | tuple | collections.Sequence</em>) &#8211; The first input of this layer.</li>
of paddle.v2.config_base.Layer.</li> <li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input label.</li>
<li><strong>label</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The ground truth.</li>
<li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the <li><strong>weight</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The weight layer defines a weight for each sample in the
mini-batch. The default value is None.</li> mini-batch. It is optional.</li>
<li><strong>num_classes</strong> (<em>int</em>) &#8211; The class number.</li> <li><strong>num_classes</strong> (<em>int</em>) &#8211; The number of classes.</li>
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute|list</em>) &#8211; The parameter attributes.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Sigmoid is the default activation.</li>
<li><strong>num_neg_samples</strong> (<em>int</em>) &#8211; The number of sampled negative labels. The default <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
value is 10.</li> details.</li>
<li><strong>num_neg_samples</strong> (<em>int</em>) &#8211; The number of sampled negative labels. 10 is the
default value.</li>
<li><strong>neg_distribution</strong> (<em>list | tuple | collections.Sequence | None</em>) &#8211; The discrete noisy distribution over the output <li><strong>neg_distribution</strong> (<em>list | tuple | collections.Sequence | None</em>) &#8211; The discrete noisy distribution over the output
space from which num_neg_samples negative labels space from which num_neg_samples negative labels
are sampled. If this parameter is not set, a are sampled. If this parameter is not set, a
uniform distribution will be used. A user defined uniform distribution will be used. A user-defined
distribution is a list whose length must be equal distribution is a list whose length must be equal
to the num_classes. Each member of the list defines to the num_classes. Each member of the list defines
the probability of a class given input x.</li> the probability of a class given input x.</li>
...@@ -3933,11 +3996,12 @@ the probability of a class given input x.</li> ...@@ -3933,11 +3996,12 @@ the probability of a class given input x.</li>
False or an object whose type is not paddle.v2.attr.ParameterAttribute, False or an object whose type is not paddle.v2.attr.ParameterAttribute,
no bias is defined. If this parameter is set to True, no bias is defined. If this parameter is set to True,
the bias is initialized to zero.</li> the bias is initialized to zero.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">The paddle.v2.config_base.Layer object.</p> <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> </td>
</tr> </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> <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>
...@@ -4021,7 +4085,7 @@ sizes of input and label are equal. The formula is as follows,</p> ...@@ -4021,7 +4085,7 @@ sizes of input and label are equal. The formula is as follows,</p>
<li><strong>label</strong> &#8211; The input label.</li> <li><strong>label</strong> &#8211; The input label.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation. <li><strong>coeff</strong> (<em>float</em>) &#8211; The weight of the gradient in the back propagation.
1.0 is the default.</li> 1.0 is the default value.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
</ul> </ul>
...@@ -4093,8 +4157,9 @@ It is used by recurrent layer group.</p> ...@@ -4093,8 +4157,9 @@ It is used by recurrent layer group.</p>
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>eos_id</strong> (<em>int</em>) &#8211; end id of sequence</li> <li><strong>eos_id</strong> (<em>int</em>) &#8211; End id of sequence</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -4203,7 +4268,7 @@ details.</li> ...@@ -4203,7 +4268,7 @@ details.</li>
<dd><p>The gated unit layer implements a simple gating mechanism over the input. <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 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 it is also used to produce a gate weight <span class="math">\(\sigma\)</span>. Element-wise
product between <a href="#id11"><span class="problematic" id="id12">:match:`X&#8217;`</span></a> and <span class="math">\(\sigma\)</span> is finally returned.</p> product between <a href="#id10"><span class="problematic" id="id11">:match:`X&#8217;`</span></a> and <span class="math">\(\sigma\)</span> is finally returned.</p>
<dl class="docutils"> <dl class="docutils">
<dt>Reference:</dt> <dt>Reference:</dt>
<dd>Language Modeling with Gated Convolutional Networks <dd>Language Modeling with Gated Convolutional Networks
...@@ -4219,7 +4284,8 @@ product between <a href="#id11"><span class="problematic" id="id12">:match:`X&#8 ...@@ -4219,7 +4284,8 @@ product between <a href="#id11"><span class="problematic" id="id12">:match:`X&#8
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple"> <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; The input of this layer.</li> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input of this layer.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer&#8217;s output.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimension of this layer&#8217;s output.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of the projection. paddle.v2.activation.Linear is the default.</li> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type of the projection. paddle.v2.activation.Linear is the default
activation.</li>
<li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li> <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of this layer. It is optional.</li>
<li><strong>gate_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute of the gate. See paddle.v2.attr.ExtraAttribute for <li><strong>gate_attr</strong> (<em>paddle.v2.attr.ExtraAttribute | None</em>) &#8211; The extra layer attribute of the gate. See paddle.v2.attr.ExtraAttribute for
details.</li> details.</li>
......
develop/doc_cn/searchindex.js
浏览文件 @ bf265015
因为 它太大了无法显示 source diff 。你可以改为 查看blob。
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