Skip to content

P
Paddle

迷途归一 / Paddle
与 Fork 源项目一致

Fork自 PaddlePaddle / Paddle

通知 1
Star 0
Fork 0
P
Paddle

体验新版 GitCode，发现更多精彩内容 >>

提交 517a2677 编写于 作者: T Travis CI
浏览文件
操作

Deploy to GitHub Pages: 82849ad1

上级 c622759a
隐藏空白更改
内联 并排
Showing with 178 addition and 160 deletion
develop/doc/api/v2/config/layer.html
浏览文件 @ 517a2677
...@@ -868,9 +868,12 @@ feature map.</p> ...@@ -868,9 +868,12 @@ feature map.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">img_cmrnorm</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">img_cmrnorm</code></dt>
<dd><p>Response normalization across feature maps. <dd><p>Response normalization across feature maps.</p>
The details please refer to <dl class="docutils">
<a class="reference external" href="http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf">Alex&#8217;s paper</a>.</p> <dt>Reference:</dt>
<dd>ImageNet Classification with Deep Convolutional Neural Networks
<a class="reference external" href="http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf">http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf</a></dd>
</dl>
<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">norm</span> <span class="o">=</span> <span class="n">img_cmrnorm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">net</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">norm</span> <span class="o">=</span> <span class="n">img_cmrnorm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">net</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -880,14 +883,16 @@ The details please refer to ...@@ -880,14 +883,16 @@ The details please refer to
<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>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>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; Normalize in number of <span class="math">\(size\)</span> feature maps.</li> <li><strong>size</strong> (<em>int</em>) &#8211; Normalize in number of <span class="math">\(size\)</span> feature maps.</li>
<li><strong>scale</strong> (<em>float</em>) &#8211; The hyper-parameter.</li> <li><strong>scale</strong> (<em>float</em>) &#8211; The hyper-parameter.</li>
<li><strong>power</strong> (<em>float</em>) &#8211; The hyper-parameter.</li> <li><strong>power</strong> (<em>float</em>) &#8211; The hyper-parameter.</li>
<li><strong>num_channels</strong> &#8211; input layer&#8217;s filers number or channels. If <li><strong>num_channels</strong> &#8211; The number of input channels. If the parameter is not set or
num_channels is None, it will be set automatically.</li> set to None, its actual value will be automatically set to
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> the channels number of the input.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attributes. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -907,7 +912,7 @@ num_channels is None, it will be set automatically.</li> ...@@ -907,7 +912,7 @@ num_channels is None, it will be set automatically.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">batch_norm</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">batch_norm</code></dt>
<dd><p>Batch Normalization Layer. The notation of this layer as follow.</p> <dd><p>Batch Normalization Layer. The notation of this layer is as follows.</p>
<p><span class="math">\(x\)</span> is the input features over a mini-batch.</p> <p><span class="math">\(x\)</span> is the input features over a mini-batch.</p>
<div class="math"> <div class="math">
\[\begin{split}\mu_{\beta} &amp;\gets \frac{1}{m} \sum_{i=1}^{m} x_i \qquad &amp;//\ \[\begin{split}\mu_{\beta} &amp;\gets \frac{1}{m} \sum_{i=1}^{m} x_i \qquad &amp;//\
...@@ -917,8 +922,12 @@ num_channels is None, it will be set automatically.</li> ...@@ -917,8 +922,12 @@ num_channels is None, it will be set automatically.</li>
\hat{x_i} &amp;\gets \frac{x_i - \mu_\beta} {\sqrt{\ \hat{x_i} &amp;\gets \frac{x_i - \mu_\beta} {\sqrt{\
\sigma_{\beta}^{2} + \epsilon}} \qquad &amp;//\ normalize \\ \sigma_{\beta}^{2} + \epsilon}} \qquad &amp;//\ normalize \\
y_i &amp;\gets \gamma \hat{x_i} + \beta \qquad &amp;//\ scale\ and\ shift\end{split}\]</div> y_i &amp;\gets \gamma \hat{x_i} + \beta \qquad &amp;//\ scale\ and\ shift\end{split}\]</div>
<p>The details of batch normalization please refer to this <dl class="docutils">
<a class="reference external" href="http://arxiv.org/abs/1502.03167">paper</a>.</p> <dt>Reference:</dt>
<dd>Batch Normalization: Accelerating Deep Network Training by Reducing
Internal Covariate Shift
<a class="reference external" href="http://arxiv.org/abs/1502.03167">http://arxiv.org/abs/1502.03167</a></dd>
</dl>
<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">norm</span> <span class="o">=</span> <span class="n">batch_norm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">net</span><span class="p">,</span> <span class="n">act</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">v2</span><span class="o">.</span><span class="n">activation</span><span class="o">.</span><span class="n">Relu</span><span class="p">())</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">norm</span> <span class="o">=</span> <span class="n">batch_norm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">net</span><span class="p">,</span> <span class="n">act</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">v2</span><span class="o">.</span><span class="n">activation</span><span class="o">.</span><span class="n">Relu</span><span class="p">())</span>
</pre></div> </pre></div>
...@@ -929,40 +938,39 @@ y_i &amp;\gets \gamma \hat{x_i} + \beta \qquad &amp;//\ scale\ and\ shift\end{sp ...@@ -929,40 +938,39 @@ y_i &amp;\gets \gamma \hat{x_i} + \beta \qquad &amp;//\ scale\ and\ shift\end{sp
<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; batch normalization input. Better be linear activation. <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; This layer&#8217;s input which is to be performed batch normalization on.</li>
Because there is an activation inside batch_normalization.</li>
<li><strong>batch_norm_type</strong> (<em>None | string</em><em>, </em><em>None</em><em> or </em><em>&quot;batch_norm&quot;</em><em> or </em><em>&quot;cudnn_batch_norm&quot;</em><em> <li><strong>batch_norm_type</strong> (<em>None | string</em><em>, </em><em>None</em><em> or </em><em>&quot;batch_norm&quot;</em><em> or </em><em>&quot;cudnn_batch_norm&quot;</em><em>
or </em><em>&quot;mkldnn_batch_norm&quot;</em>) &#8211; We have batch_norm, mkldnn_batch_norm and cudnn_batch_norm. or </em><em>&quot;mkldnn_batch_norm&quot;</em>) &#8211; We have batch_norm, mkldnn_batch_norm and cudnn_batch_norm.
batch_norm supports CPU, MKLDNN and GPU. cudnn_batch_norm batch_norm supports CPU, MKLDNN and GPU. cudnn_batch_norm
requires cuDNN version greater or equal to v4 (&gt;=v4). requires cuDNN version greater or equal to v4 (&gt;=v4).
But cudnn_batch_norm is faster and needs less But cudnn_batch_norm is faster and needs less
memory than batch_norm. mkldnn_batch_norm requires memory than batch_norm. mkldnn_batch_norm requires
enable use_mkldnn. By default (None), we will use_mkldnn is enabled. By default (None), we will
automaticly select cudnn_batch_norm for GPU, automatically select cudnn_batch_norm for GPU,
mkldnn_batch_norm for MKLDNN and batch_norm for CPU. mkldnn_batch_norm for MKLDNN and batch_norm for CPU.
Otherwise, select batch norm type based on the Users can specify the batch norm type. If you use
specified type. If you use cudnn_batch_norm, cudnn_batch_norm, we suggested you use latest version,
we suggested you use latest version, such as v5.1.</li> such as v5.1.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. Better be relu. Because batch <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Relu is the default activation.</li>
normalization will normalize input near zero.</li> <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of input channels. If the parameter is not set or
<li><strong>num_channels</strong> (<em>int</em>) &#8211; num of image channels or previous layer&#8217;s number of set to None, its actual value will be automatically set to
filters. None will automatically get from layer&#8217;s the channels number of the input.</li>
input.</li> <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; <span class="math">\(\beta\)</span>. The bias attribute. If the parameter is set to
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; <span class="math">\(\beta\)</span>, better be zero when initialize. So the False or an object whose type is not paddle.v2.attr.ParameterAttribute, no
initial_std=0, initial_mean=1 is best practice.</li> bias is defined. If the parameter is set to True, the bias is
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; <span class="math">\(\gamma\)</span>, better be one when initialize. So the initialized to zero.</li>
initial_std=0, initial_mean=1 is best practice.</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; <span class="math">\(\gamma\)</span>. The parameter attribute. See paddle.v2.attr.ParameterAttribute
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> for details.</li>
<li><strong>use_global_stats</strong> (<em>bool | None.</em>) &#8211; whether use moving mean/variance statistics <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
during testing peroid. If None or True, details.</li>
it will use moving mean/variance statistics during <li><strong>use_global_stats</strong> (<em>bool | None.</em>) &#8211; Whether use moving mean/variance statistics during
testing. If False, it will use the mean testing peroid. If the parameter is set to None or
and variance of current batch of test data for True, it will use moving mean/variance statistics
testing.</li> during testing. If the parameter is set to False, it
<li><strong>moving_average_fraction</strong> (<em>float.</em>) &#8211; Factor used in the moving average will use the mean and variance of the current batch
computation, referred to as facotr, of test data.</li>
<span class="math">\(runningMean = newMean*(1-factor) <li><strong>moving_average_fraction</strong> (<em>float.</em>) &#8211; Factor used in the moving average computation.
+ runningMean*factor\)</span></li> <span class="math">\(runningMean = newMean*(1-factor) + runningMean*factor\)</span></li>
<li><strong>mean_var_names</strong> (<em>string list</em>) &#8211; [mean name, variance name]</li> <li><strong>mean_var_names</strong> (<em>string list</em>) &#8211; [mean name, variance name]</li>
</ul> </ul>
</td> </td>
...@@ -1000,7 +1008,8 @@ and <span class="math">\(out\)</span> is a (batchSize x dataDim) output vector.< ...@@ -1000,7 +1008,8 @@ and <span class="math">\(out\)</span> is a (batchSize x dataDim) output vector.<
<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>
...@@ -1074,7 +1083,8 @@ and the size of <span class="math">\(out\)</span> is a (batchSize x dataDim) .</ ...@@ -1074,7 +1083,8 @@ and the size of <span class="math">\(out\)</span> is a (batchSize x dataDim) .</
<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" colspan="2">param layer_attr:</th></tr> <tr class="field-odd field"><th class="field-name" colspan="2">param layer_attr:</th></tr>
<tr class="field-odd field"><td>&#160;</td><td class="field-body">extra layer attributes.</td> <tr class="field-odd field"><td>&#160;</td><td class="field-body">The extra layer attribute. See paddle.v2.attr.ExtraAttribute
for details.</td>
</tr> </tr>
<tr class="field-even field"><th class="field-name" colspan="2">type layer_attr:</th></tr> <tr class="field-even field"><th class="field-name" colspan="2">type layer_attr:</th></tr>
<tr class="field-even field"><td>&#160;</td><td class="field-body">paddle.v2.attr.ExtraAttribute</td> <tr class="field-even field"><td>&#160;</td><td class="field-body">paddle.v2.attr.ExtraAttribute</td>
...@@ -1265,24 +1275,19 @@ parameter is set to True, the bias is initialized to zero.</li> ...@@ -1265,24 +1275,19 @@ parameter is set to True, the bias is initialized to zero.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">memory</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">memory</code></dt>
<dd><p>The memory layers is a layer cross each time step. Reference this output <dd><p>The memory takes a layer&#8217;s output at previous time step as its own output.</p>
as previous time step layer <code class="code docutils literal"><span class="pre">name</span></code> &#8216;s output.</p> <p>If boot_bias, the activation of the bias is the initial value of the memory.</p>
<p>The default memory is zero in first time step, previous time step&#8217;s <p>If boot_with_const_id is set, then the memory&#8217;s output at the first time step
output in the rest time steps.</p> is a IndexSlot, the Arguments.ids()[0] is this <code class="code docutils literal"><span class="pre">cost_id</span></code>.</p>
<p>If boot_bias, the first time step value is this bias and <p>If boot is specified, the memory&#8217;s output at the first time step will
with activation.</p> be the boot&#8217;s output.</p>
<p>If boot_with_const_id, then the first time stop is a IndexSlot, the <p>In other case, the default memory&#8217;s output at the first time step is zero.</p>
Arguments.ids()[0] is this <code class="code docutils literal"><span class="pre">cost_id</span></code>.</p>
<p>If boot is not null, the memory is just the boot&#8217;s output.
Set <code class="code docutils literal"><span class="pre">is_seq</span></code> is true boot layer is sequence.</p>
<p>The same name layer in recurrent group will set memory on each time
step.</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;state&#39;</span><span class="p">)</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;state&#39;</span><span class="p">)</span>
<span class="n">state</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">mem</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;state&#39;</span><span class="p">)</span> <span class="n">state</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">mem</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;state&#39;</span><span class="p">)</span>
</pre></div> </pre></div>
</div> </div>
<p>If you do not want to specify the name, you can equivalently use set_input() <p>If you do not want to specify the name, you can also use set_input()
to specify the layer needs to be remembered as the following:</p> to specify the layer to be remembered as the following:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">)</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">)</span>
<span class="n">state</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">mem</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">)</span> <span class="n">state</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">mem</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">)</span>
<span class="n">mem</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="n">mem</span><span class="p">)</span> <span class="n">mem</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="n">mem</span><span class="p">)</span>
...@@ -1293,21 +1298,26 @@ to specify the layer needs to be remembered as the following:</p> ...@@ -1293,21 +1298,26 @@ to specify the layer needs to be remembered as the following:</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>basestring</em>) &#8211; the name of the layer which this memory remembers. <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of the layer which this memory remembers.
If name is None, user should call set_input() to specify the If name is None, user should call set_input() to specify the
name of the layer which this memory remembers.</li> name of the layer which this memory remembers.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; size of memory.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimensionality of memory.</li>
<li><strong>memory_name</strong> (<em>basestring</em>) &#8211; the name of the memory. <li><strong>memory_name</strong> (<em>basestring</em>) &#8211; The name of the memory. It is ignored when name is provided.</li>
It is ignored when name is provided.</li>
<li><strong>is_seq</strong> (<em>bool</em>) &#8211; DEPRECATED. is sequence for boot</li> <li><strong>is_seq</strong> (<em>bool</em>) &#8211; DEPRECATED. is sequence for boot</li>
<li><strong>boot</strong> (<em>paddle.v2.config_base.Layer | None</em>) &#8211; boot layer of memory.</li> <li><strong>boot</strong> (<em>paddle.v2.config_base.Layer | None</em>) &#8211; This parameter specifies memory&#8217;s output at the first time
<li><strong>boot_bias</strong> (<em>paddle.v2.attr.ParameterAttribute | None</em>) &#8211; boot layer&#8217;s bias</li> step and the output is boot&#8217;s output.</li>
<li><strong>boot_bias_active_type</strong> (<em>paddle.v2.activation.Base</em>) &#8211; boot layer&#8217;s active type.</li> <li><strong>boot_bias</strong> (<em>paddle.v2.attr.ParameterAttribute | None</em>) &#8211; The bias attribute of memory&#8217;s output at the first time step.
<li><strong>boot_with_const_id</strong> (<em>int</em>) &#8211; boot layer&#8217;s id.</li> If the parameter is set to False or an object 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>boot_bias_active_type</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type for memory&#8217;s bias at the first time
step. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>boot_with_const_id</strong> (<em>int</em>) &#8211; This parameter specifies memory&#8217;s output at the first
time step and the output is an index.</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">paddle.v2.config_base.Layer object which is a memory.</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>
...@@ -2162,8 +2172,8 @@ of stride is -1.</p> ...@@ -2162,8 +2172,8 @@ of stride is -1.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">concat</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">concat</code></dt>
<dd><p>Concat all input vector into one huge vector. <dd><p>Concatenate all input vectors to one vector.
Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p> Inputs can be a list of paddle.v2.config_base.Layer or a list of projection.</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">concat</span> <span class="o">=</span> <span class="n">concat</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">layer1</span><span class="p">,</span> <span class="n">layer2</span><span class="p">])</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">concat</span> <span class="o">=</span> <span class="n">concat</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">layer1</span><span class="p">,</span> <span class="n">layer2</span><span class="p">])</span>
</pre></div> </pre></div>
...@@ -2174,9 +2184,10 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p> ...@@ -2174,9 +2184,10 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</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>list | tuple | collections.Sequence</em>) &#8211; input layers or projections</li> <li><strong>input</strong> (<em>list | tuple | collections.Sequence</em>) &#8211; The 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 activation.</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; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -2196,7 +2207,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p> ...@@ -2196,7 +2207,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">seq_concat</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">seq_concat</code></dt>
<dd><p>Concat sequence a with sequence b.</p> <dd><p>Concatenate sequence a and sequence b.</p>
<dl class="docutils"> <dl class="docutils">
<dt>Inputs:</dt> <dt>Inputs:</dt>
<dd><ul class="first last simple"> <dd><ul class="first last simple">
...@@ -2218,10 +2229,11 @@ processed in one batch.</p> ...@@ -2218,10 +2229,11 @@ processed in one batch.</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 sequence layer</li> <li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first 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; The second input sequence layer</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>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; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</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>
...@@ -2595,29 +2607,26 @@ and <span class="math">\(f\)</span> is activation function.</p> ...@@ -2595,29 +2607,26 @@ and <span class="math">\(f\)</span> is activation function.</p>
<span class="n">bias_attr</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span> <span class="n">bias_attr</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>
</pre></div> </pre></div>
</div> </div>
<p>This layer just simply add all input layers together, then activate the sum <p>This layer just simply adds all input layers together, then activates the
inputs. Each input of this layer should be the same size, which is also the sum. All inputs should share the same dimension, which is also the dimension
output size of this layer.</p> of this layer&#8217;s output.</p>
<p>There is no weight matrix for each input, because it just a simple add <p>There is no weight matrix for each input, because it just a simple add
operation. If you want a complicated operation before add, please use operation. If you want a complicated operation before add, please use
mixed.</p> mixed.</p>
<p>It is a very good way to set dropout outside the layers. Since not all
PaddlePaddle layer support dropout, you can add an add_to layer, set
dropout here.
Please refer to dropout for details.</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" />
<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>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; The 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 activation.</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>
<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>
......
develop/doc/searchindex.js
浏览文件 @ 517a2677
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 @ 517a2677
...@@ -882,9 +882,12 @@ feature map.</p> ...@@ -882,9 +882,12 @@ feature map.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">img_cmrnorm</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">img_cmrnorm</code></dt>
<dd><p>Response normalization across feature maps. <dd><p>Response normalization across feature maps.</p>
The details please refer to <dl class="docutils">
<a class="reference external" href="http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf">Alex&#8217;s paper</a>.</p> <dt>Reference:</dt>
<dd>ImageNet Classification with Deep Convolutional Neural Networks
<a class="reference external" href="http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf">http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf</a></dd>
</dl>
<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">norm</span> <span class="o">=</span> <span class="n">img_cmrnorm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">net</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">norm</span> <span class="o">=</span> <span class="n">img_cmrnorm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">net</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
</pre></div> </pre></div>
...@@ -894,14 +897,16 @@ The details please refer to ...@@ -894,14 +897,16 @@ The details please refer to
<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>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>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; Normalize in number of <span class="math">\(size\)</span> feature maps.</li> <li><strong>size</strong> (<em>int</em>) &#8211; Normalize in number of <span class="math">\(size\)</span> feature maps.</li>
<li><strong>scale</strong> (<em>float</em>) &#8211; The hyper-parameter.</li> <li><strong>scale</strong> (<em>float</em>) &#8211; The hyper-parameter.</li>
<li><strong>power</strong> (<em>float</em>) &#8211; The hyper-parameter.</li> <li><strong>power</strong> (<em>float</em>) &#8211; The hyper-parameter.</li>
<li><strong>num_channels</strong> &#8211; input layer&#8217;s filers number or channels. If <li><strong>num_channels</strong> &#8211; The number of input channels. If the parameter is not set or
num_channels is None, it will be set automatically.</li> set to None, its actual value will be automatically set to
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> the channels number of the input.</li>
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attributes. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -921,7 +926,7 @@ num_channels is None, it will be set automatically.</li> ...@@ -921,7 +926,7 @@ num_channels is None, it will be set automatically.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">batch_norm</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">batch_norm</code></dt>
<dd><p>Batch Normalization Layer. The notation of this layer as follow.</p> <dd><p>Batch Normalization Layer. The notation of this layer is as follows.</p>
<p><span class="math">\(x\)</span> is the input features over a mini-batch.</p> <p><span class="math">\(x\)</span> is the input features over a mini-batch.</p>
<div class="math"> <div class="math">
\[\begin{split}\mu_{\beta} &amp;\gets \frac{1}{m} \sum_{i=1}^{m} x_i \qquad &amp;//\ \[\begin{split}\mu_{\beta} &amp;\gets \frac{1}{m} \sum_{i=1}^{m} x_i \qquad &amp;//\
...@@ -931,8 +936,12 @@ num_channels is None, it will be set automatically.</li> ...@@ -931,8 +936,12 @@ num_channels is None, it will be set automatically.</li>
\hat{x_i} &amp;\gets \frac{x_i - \mu_\beta} {\sqrt{\ \hat{x_i} &amp;\gets \frac{x_i - \mu_\beta} {\sqrt{\
\sigma_{\beta}^{2} + \epsilon}} \qquad &amp;//\ normalize \\ \sigma_{\beta}^{2} + \epsilon}} \qquad &amp;//\ normalize \\
y_i &amp;\gets \gamma \hat{x_i} + \beta \qquad &amp;//\ scale\ and\ shift\end{split}\]</div> y_i &amp;\gets \gamma \hat{x_i} + \beta \qquad &amp;//\ scale\ and\ shift\end{split}\]</div>
<p>The details of batch normalization please refer to this <dl class="docutils">
<a class="reference external" href="http://arxiv.org/abs/1502.03167">paper</a>.</p> <dt>Reference:</dt>
<dd>Batch Normalization: Accelerating Deep Network Training by Reducing
Internal Covariate Shift
<a class="reference external" href="http://arxiv.org/abs/1502.03167">http://arxiv.org/abs/1502.03167</a></dd>
</dl>
<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">norm</span> <span class="o">=</span> <span class="n">batch_norm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">net</span><span class="p">,</span> <span class="n">act</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">v2</span><span class="o">.</span><span class="n">activation</span><span class="o">.</span><span class="n">Relu</span><span class="p">())</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">norm</span> <span class="o">=</span> <span class="n">batch_norm</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">net</span><span class="p">,</span> <span class="n">act</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">v2</span><span class="o">.</span><span class="n">activation</span><span class="o">.</span><span class="n">Relu</span><span class="p">())</span>
</pre></div> </pre></div>
...@@ -943,40 +952,39 @@ y_i &amp;\gets \gamma \hat{x_i} + \beta \qquad &amp;//\ scale\ and\ shift\end{sp ...@@ -943,40 +952,39 @@ y_i &amp;\gets \gamma \hat{x_i} + \beta \qquad &amp;//\ scale\ and\ shift\end{sp
<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; batch normalization input. Better be linear activation. <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; This layer&#8217;s input which is to be performed batch normalization on.</li>
Because there is an activation inside batch_normalization.</li>
<li><strong>batch_norm_type</strong> (<em>None | string</em><em>, </em><em>None</em><em> or </em><em>&quot;batch_norm&quot;</em><em> or </em><em>&quot;cudnn_batch_norm&quot;</em><em> <li><strong>batch_norm_type</strong> (<em>None | string</em><em>, </em><em>None</em><em> or </em><em>&quot;batch_norm&quot;</em><em> or </em><em>&quot;cudnn_batch_norm&quot;</em><em>
or </em><em>&quot;mkldnn_batch_norm&quot;</em>) &#8211; We have batch_norm, mkldnn_batch_norm and cudnn_batch_norm. or </em><em>&quot;mkldnn_batch_norm&quot;</em>) &#8211; We have batch_norm, mkldnn_batch_norm and cudnn_batch_norm.
batch_norm supports CPU, MKLDNN and GPU. cudnn_batch_norm batch_norm supports CPU, MKLDNN and GPU. cudnn_batch_norm
requires cuDNN version greater or equal to v4 (&gt;=v4). requires cuDNN version greater or equal to v4 (&gt;=v4).
But cudnn_batch_norm is faster and needs less But cudnn_batch_norm is faster and needs less
memory than batch_norm. mkldnn_batch_norm requires memory than batch_norm. mkldnn_batch_norm requires
enable use_mkldnn. By default (None), we will use_mkldnn is enabled. By default (None), we will
automaticly select cudnn_batch_norm for GPU, automatically select cudnn_batch_norm for GPU,
mkldnn_batch_norm for MKLDNN and batch_norm for CPU. mkldnn_batch_norm for MKLDNN and batch_norm for CPU.
Otherwise, select batch norm type based on the Users can specify the batch norm type. If you use
specified type. If you use cudnn_batch_norm, cudnn_batch_norm, we suggested you use latest version,
we suggested you use latest version, such as v5.1.</li> such as v5.1.</li>
<li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. Better be relu. Because batch <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type. paddle.v2.activation.Relu is the default activation.</li>
normalization will normalize input near zero.</li> <li><strong>num_channels</strong> (<em>int</em>) &#8211; The number of input channels. If the parameter is not set or
<li><strong>num_channels</strong> (<em>int</em>) &#8211; num of image channels or previous layer&#8217;s number of set to None, its actual value will be automatically set to
filters. None will automatically get from layer&#8217;s the channels number of the input.</li>
input.</li> <li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; <span class="math">\(\beta\)</span>. The bias attribute. If the parameter is set to
<li><strong>bias_attr</strong> (<em>paddle.v2.attr.ParameterAttribute | None | bool | Any</em>) &#8211; <span class="math">\(\beta\)</span>, better be zero when initialize. So the False or an object whose type is not paddle.v2.attr.ParameterAttribute, no
initial_std=0, initial_mean=1 is best practice.</li> bias is defined. If the parameter is set to True, the bias is
<li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; <span class="math">\(\gamma\)</span>, better be one when initialize. So the initialized to zero.</li>
initial_std=0, initial_mean=1 is best practice.</li> <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; <span class="math">\(\gamma\)</span>. The parameter attribute. See paddle.v2.attr.ParameterAttribute
<li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; Extra Layer Attribute.</li> for details.</li>
<li><strong>use_global_stats</strong> (<em>bool | None.</em>) &#8211; whether use moving mean/variance statistics <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
during testing peroid. If None or True, details.</li>
it will use moving mean/variance statistics during <li><strong>use_global_stats</strong> (<em>bool | None.</em>) &#8211; Whether use moving mean/variance statistics during
testing. If False, it will use the mean testing peroid. If the parameter is set to None or
and variance of current batch of test data for True, it will use moving mean/variance statistics
testing.</li> during testing. If the parameter is set to False, it
<li><strong>moving_average_fraction</strong> (<em>float.</em>) &#8211; Factor used in the moving average will use the mean and variance of the current batch
computation, referred to as facotr, of test data.</li>
<span class="math">\(runningMean = newMean*(1-factor) <li><strong>moving_average_fraction</strong> (<em>float.</em>) &#8211; Factor used in the moving average computation.
+ runningMean*factor\)</span></li> <span class="math">\(runningMean = newMean*(1-factor) + runningMean*factor\)</span></li>
<li><strong>mean_var_names</strong> (<em>string list</em>) &#8211; [mean name, variance name]</li> <li><strong>mean_var_names</strong> (<em>string list</em>) &#8211; [mean name, variance name]</li>
</ul> </ul>
</td> </td>
...@@ -1014,7 +1022,8 @@ and <span class="math">\(out\)</span> is a (batchSize x dataDim) output vector.< ...@@ -1014,7 +1022,8 @@ and <span class="math">\(out\)</span> is a (batchSize x dataDim) output vector.<
<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>
...@@ -1088,7 +1097,8 @@ and the size of <span class="math">\(out\)</span> is a (batchSize x dataDim) .</ ...@@ -1088,7 +1097,8 @@ and the size of <span class="math">\(out\)</span> is a (batchSize x dataDim) .</
<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" colspan="2">param layer_attr:</th></tr> <tr class="field-odd field"><th class="field-name" colspan="2">param layer_attr:</th></tr>
<tr class="field-odd field"><td>&#160;</td><td class="field-body">extra layer attributes.</td> <tr class="field-odd field"><td>&#160;</td><td class="field-body">The extra layer attribute. See paddle.v2.attr.ExtraAttribute
for details.</td>
</tr> </tr>
<tr class="field-even field"><th class="field-name" colspan="2">type layer_attr:</th></tr> <tr class="field-even field"><th class="field-name" colspan="2">type layer_attr:</th></tr>
<tr class="field-even field"><td>&#160;</td><td class="field-body">paddle.v2.attr.ExtraAttribute</td> <tr class="field-even field"><td>&#160;</td><td class="field-body">paddle.v2.attr.ExtraAttribute</td>
...@@ -1279,24 +1289,19 @@ parameter is set to True, the bias is initialized to zero.</li> ...@@ -1279,24 +1289,19 @@ parameter is set to True, the bias is initialized to zero.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">memory</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">memory</code></dt>
<dd><p>The memory layers is a layer cross each time step. Reference this output <dd><p>The memory takes a layer&#8217;s output at previous time step as its own output.</p>
as previous time step layer <code class="code docutils literal"><span class="pre">name</span></code> &#8216;s output.</p> <p>If boot_bias, the activation of the bias is the initial value of the memory.</p>
<p>The default memory is zero in first time step, previous time step&#8217;s <p>If boot_with_const_id is set, then the memory&#8217;s output at the first time step
output in the rest time steps.</p> is a IndexSlot, the Arguments.ids()[0] is this <code class="code docutils literal"><span class="pre">cost_id</span></code>.</p>
<p>If boot_bias, the first time step value is this bias and <p>If boot is specified, the memory&#8217;s output at the first time step will
with activation.</p> be the boot&#8217;s output.</p>
<p>If boot_with_const_id, then the first time stop is a IndexSlot, the <p>In other case, the default memory&#8217;s output at the first time step is zero.</p>
Arguments.ids()[0] is this <code class="code docutils literal"><span class="pre">cost_id</span></code>.</p>
<p>If boot is not null, the memory is just the boot&#8217;s output.
Set <code class="code docutils literal"><span class="pre">is_seq</span></code> is true boot layer is sequence.</p>
<p>The same name layer in recurrent group will set memory on each time
step.</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;state&#39;</span><span class="p">)</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;state&#39;</span><span class="p">)</span>
<span class="n">state</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">mem</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;state&#39;</span><span class="p">)</span> <span class="n">state</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">mem</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;state&#39;</span><span class="p">)</span>
</pre></div> </pre></div>
</div> </div>
<p>If you do not want to specify the name, you can equivalently use set_input() <p>If you do not want to specify the name, you can also use set_input()
to specify the layer needs to be remembered as the following:</p> to specify the layer to be remembered as the following:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">)</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">)</span>
<span class="n">state</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">mem</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">)</span> <span class="n">state</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">mem</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">)</span>
<span class="n">mem</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="n">mem</span><span class="p">)</span> <span class="n">mem</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="n">mem</span><span class="p">)</span>
...@@ -1307,21 +1312,26 @@ to specify the layer needs to be remembered as the following:</p> ...@@ -1307,21 +1312,26 @@ to specify the layer needs to be remembered as the following:</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>basestring</em>) &#8211; the name of the layer which this memory remembers. <li><strong>name</strong> (<em>basestring</em>) &#8211; The name of the layer which this memory remembers.
If name is None, user should call set_input() to specify the If name is None, user should call set_input() to specify the
name of the layer which this memory remembers.</li> name of the layer which this memory remembers.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; size of memory.</li> <li><strong>size</strong> (<em>int</em>) &#8211; The dimensionality of memory.</li>
<li><strong>memory_name</strong> (<em>basestring</em>) &#8211; the name of the memory. <li><strong>memory_name</strong> (<em>basestring</em>) &#8211; The name of the memory. It is ignored when name is provided.</li>
It is ignored when name is provided.</li>
<li><strong>is_seq</strong> (<em>bool</em>) &#8211; DEPRECATED. is sequence for boot</li> <li><strong>is_seq</strong> (<em>bool</em>) &#8211; DEPRECATED. is sequence for boot</li>
<li><strong>boot</strong> (<em>paddle.v2.config_base.Layer | None</em>) &#8211; boot layer of memory.</li> <li><strong>boot</strong> (<em>paddle.v2.config_base.Layer | None</em>) &#8211; This parameter specifies memory&#8217;s output at the first time
<li><strong>boot_bias</strong> (<em>paddle.v2.attr.ParameterAttribute | None</em>) &#8211; boot layer&#8217;s bias</li> step and the output is boot&#8217;s output.</li>
<li><strong>boot_bias_active_type</strong> (<em>paddle.v2.activation.Base</em>) &#8211; boot layer&#8217;s active type.</li> <li><strong>boot_bias</strong> (<em>paddle.v2.attr.ParameterAttribute | None</em>) &#8211; The bias attribute of memory&#8217;s output at the first time step.
<li><strong>boot_with_const_id</strong> (<em>int</em>) &#8211; boot layer&#8217;s id.</li> If the parameter is set to False or an object 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>boot_bias_active_type</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation type for memory&#8217;s bias at the first time
step. paddle.v2.activation.Linear is the default activation.</li>
<li><strong>boot_with_const_id</strong> (<em>int</em>) &#8211; This parameter specifies memory&#8217;s output at the first
time step and the output is an index.</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">paddle.v2.config_base.Layer object which is a memory.</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>
...@@ -2176,8 +2186,8 @@ of stride is -1.</p> ...@@ -2176,8 +2186,8 @@ of stride is -1.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">concat</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">concat</code></dt>
<dd><p>Concat all input vector into one huge vector. <dd><p>Concatenate all input vectors to one vector.
Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p> Inputs can be a list of paddle.v2.config_base.Layer or a list of projection.</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">concat</span> <span class="o">=</span> <span class="n">concat</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">layer1</span><span class="p">,</span> <span class="n">layer2</span><span class="p">])</span> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">concat</span> <span class="o">=</span> <span class="n">concat</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">layer1</span><span class="p">,</span> <span class="n">layer2</span><span class="p">])</span>
</pre></div> </pre></div>
...@@ -2188,9 +2198,10 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p> ...@@ -2188,9 +2198,10 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</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>list | tuple | collections.Sequence</em>) &#8211; input layers or projections</li> <li><strong>input</strong> (<em>list | tuple | collections.Sequence</em>) &#8211; The 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 activation.</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; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</li>
</ul> </ul>
</td> </td>
</tr> </tr>
...@@ -2210,7 +2221,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p> ...@@ -2210,7 +2221,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.</p>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">seq_concat</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">seq_concat</code></dt>
<dd><p>Concat sequence a with sequence b.</p> <dd><p>Concatenate sequence a and sequence b.</p>
<dl class="docutils"> <dl class="docutils">
<dt>Inputs:</dt> <dt>Inputs:</dt>
<dd><ul class="first last simple"> <dd><ul class="first last simple">
...@@ -2232,10 +2243,11 @@ processed in one batch.</p> ...@@ -2232,10 +2243,11 @@ processed in one batch.</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 sequence layer</li> <li><strong>a</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The first 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; The second input sequence layer</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>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; The extra layer attribute. See paddle.v2.attr.ExtraAttribute for
details.</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>
...@@ -2609,29 +2621,26 @@ and <span class="math">\(f\)</span> is activation function.</p> ...@@ -2609,29 +2621,26 @@ and <span class="math">\(f\)</span> is activation function.</p>
<span class="n">bias_attr</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span> <span class="n">bias_attr</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>
</pre></div> </pre></div>
</div> </div>
<p>This layer just simply add all input layers together, then activate the sum <p>This layer just simply adds all input layers together, then activates the
inputs. Each input of this layer should be the same size, which is also the sum. All inputs should share the same dimension, which is also the dimension
output size of this layer.</p> of this layer&#8217;s output.</p>
<p>There is no weight matrix for each input, because it just a simple add <p>There is no weight matrix for each input, because it just a simple add
operation. If you want a complicated operation before add, please use operation. If you want a complicated operation before add, please use
mixed.</p> mixed.</p>
<p>It is a very good way to set dropout outside the layers. Since not all
PaddlePaddle layer support dropout, you can add an add_to layer, set
dropout here.
Please refer to dropout for details.</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" />
<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>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; The 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 activation.</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>
<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>
......
develop/doc_cn/searchindex.js
浏览文件 @ 517a2677
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