Deploy to GitHub Pages: df5a95dc

develop/doc/api/v1/trainer_config_helpers/layers.html

@@ -2016,6 +2016,10 @@ SumPooling, SquareRootNPooling.</li>
 <dt>
 <code class="descclassname">paddle.trainer_config_helpers.layers.</code><code class="descname">last_seq</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
 <dd><p>Get Last Timestamp Activation of a sequence.</p>
+<p>If stride &gt; 0, this layer slides a window whose size is determined by stride,
+and return the last value of the window as the output. Thus, a long sequence
+will be shorten. Note that for sequence with sub-sequence, the default value
+of stride is -1.</p>
 <p>The simple usage is:</p>
 <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">seq</span> <span class="o">=</span> <span class="n">last_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">)</span>
 </pre></div>
@@ -2028,6 +2032,7 @@ SumPooling, SquareRootNPooling.</li>
 <li><strong>agg_level</strong> &#8211; Aggregated level</li>
 <li><strong>name</strong> (<em>basestring</em>) &#8211; Layer name.</li>
 <li><strong>input</strong> (<em>LayerOutput</em>) &#8211; Input layer name.</li>
+<li><strong>stride</strong> (<em>Int</em>) &#8211; window size.</li>
 <li><strong>layer_attr</strong> (<em>ExtraLayerAttribute.</em>) &#8211; extra layer attributes.</li>
 </ul>
 </td>
@@ -2049,6 +2054,10 @@ SumPooling, SquareRootNPooling.</li>
 <dt>
 <code class="descclassname">paddle.trainer_config_helpers.layers.</code><code class="descname">first_seq</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
 <dd><p>Get First Timestamp Activation of a sequence.</p>
+<p>If stride &gt; 0, this layer slides a window whose size is determined by stride,
+and return the first value of the window as the output. Thus, a long sequence
+will be shorten. Note that for sequence with sub-sequence, the default value
+of stride is -1.</p>
 <p>The simple usage is:</p>
 <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">seq</span> <span class="o">=</span> <span class="n">first_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">)</span>
 </pre></div>
@@ -2061,6 +2070,7 @@ SumPooling, SquareRootNPooling.</li>
 <li><strong>agg_level</strong> &#8211; aggregation level</li>
 <li><strong>name</strong> (<em>basestring</em>) &#8211; Layer name.</li>
 <li><strong>input</strong> (<em>LayerOutput</em>) &#8211; Input layer name.</li>
+<li><strong>stride</strong> (<em>Int</em>) &#8211; window size.</li>
 <li><strong>layer_attr</strong> (<em>ExtraLayerAttribute.</em>) &#8211; extra layer attributes.</li>
 </ul>
 </td>

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

@@ -2252,6 +2252,10 @@ the way how to configure a neural network topology in Paddle Python code.</p>
 <dt>
 <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">last_seq</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
 <dd><p>Get Last Timestamp Activation of a sequence.</p>
+<p>If stride &gt; 0, this layer slides a window whose size is determined by stride,
+and return the last value of the window as the output. Thus, a long sequence
+will be shorten. Note that for sequence with sub-sequence, the default value
+of stride is -1.</p>
 <p>The simple usage is:</p>
 <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">seq</span> <span class="o">=</span> <span class="n">last_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">)</span>
 </pre></div>
@@ -2264,6 +2268,7 @@ the way how to configure a neural network topology in Paddle Python code.</p>
 <li><strong>agg_level</strong> &#8211; Aggregated level</li>
 <li><strong>name</strong> (<em>basestring</em>) &#8211; Layer name.</li>
 <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Input layer name.</li>
+<li><strong>stride</strong> (<em>Int</em>) &#8211; window size.</li>
 <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li>
 </ul>
 </td>
@@ -2300,6 +2305,10 @@ the way how to configure a neural network topology in Paddle Python code.</p>
 <dt>
 <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">first_seq</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
 <dd><p>Get First Timestamp Activation of a sequence.</p>
+<p>If stride &gt; 0, this layer slides a window whose size is determined by stride,
+and return the first value of the window as the output. Thus, a long sequence
+will be shorten. Note that for sequence with sub-sequence, the default value
+of stride is -1.</p>
 <p>The simple usage is:</p>
 <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">seq</span> <span class="o">=</span> <span class="n">first_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">)</span>
 </pre></div>
@@ -2312,6 +2321,7 @@ the way how to configure a neural network topology in Paddle Python code.</p>
 <li><strong>agg_level</strong> &#8211; aggregation level</li>
 <li><strong>name</strong> (<em>basestring</em>) &#8211; Layer name.</li>
 <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Input layer name.</li>
+<li><strong>stride</strong> (<em>Int</em>) &#8211; window size.</li>
 <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li>
 </ul>
 </td>

develop/doc_cn/api/v1/trainer_config_helpers/layers.html

@@ -2023,6 +2023,10 @@ SumPooling, SquareRootNPooling.</li>
 <dt>
 <code class="descclassname">paddle.trainer_config_helpers.layers.</code><code class="descname">last_seq</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
 <dd><p>Get Last Timestamp Activation of a sequence.</p>
+<p>If stride &gt; 0, this layer slides a window whose size is determined by stride,
+and return the last value of the window as the output. Thus, a long sequence
+will be shorten. Note that for sequence with sub-sequence, the default value
+of stride is -1.</p>
 <p>The simple usage is:</p>
 <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">seq</span> <span class="o">=</span> <span class="n">last_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">)</span>
 </pre></div>
@@ -2035,6 +2039,7 @@ SumPooling, SquareRootNPooling.</li>
 <li><strong>agg_level</strong> &#8211; Aggregated level</li>
 <li><strong>name</strong> (<em>basestring</em>) &#8211; Layer name.</li>
 <li><strong>input</strong> (<em>LayerOutput</em>) &#8211; Input layer name.</li>
+<li><strong>stride</strong> (<em>Int</em>) &#8211; window size.</li>
 <li><strong>layer_attr</strong> (<em>ExtraLayerAttribute.</em>) &#8211; extra layer attributes.</li>
 </ul>
 </td>
@@ -2056,6 +2061,10 @@ SumPooling, SquareRootNPooling.</li>
 <dt>
 <code class="descclassname">paddle.trainer_config_helpers.layers.</code><code class="descname">first_seq</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
 <dd><p>Get First Timestamp Activation of a sequence.</p>
+<p>If stride &gt; 0, this layer slides a window whose size is determined by stride,
+and return the first value of the window as the output. Thus, a long sequence
+will be shorten. Note that for sequence with sub-sequence, the default value
+of stride is -1.</p>
 <p>The simple usage is:</p>
 <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">seq</span> <span class="o">=</span> <span class="n">first_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">)</span>
 </pre></div>
@@ -2068,6 +2077,7 @@ SumPooling, SquareRootNPooling.</li>
 <li><strong>agg_level</strong> &#8211; aggregation level</li>
 <li><strong>name</strong> (<em>basestring</em>) &#8211; Layer name.</li>
 <li><strong>input</strong> (<em>LayerOutput</em>) &#8211; Input layer name.</li>
+<li><strong>stride</strong> (<em>Int</em>) &#8211; window size.</li>
 <li><strong>layer_attr</strong> (<em>ExtraLayerAttribute.</em>) &#8211; extra layer attributes.</li>
 </ul>
 </td>

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

@@ -2259,6 +2259,10 @@ the way how to configure a neural network topology in Paddle Python code.</p>
 <dt>
 <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">last_seq</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
 <dd><p>Get Last Timestamp Activation of a sequence.</p>
+<p>If stride &gt; 0, this layer slides a window whose size is determined by stride,
+and return the last value of the window as the output. Thus, a long sequence
+will be shorten. Note that for sequence with sub-sequence, the default value
+of stride is -1.</p>
 <p>The simple usage is:</p>
 <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">seq</span> <span class="o">=</span> <span class="n">last_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">)</span>
 </pre></div>
@@ -2271,6 +2275,7 @@ the way how to configure a neural network topology in Paddle Python code.</p>
 <li><strong>agg_level</strong> &#8211; Aggregated level</li>
 <li><strong>name</strong> (<em>basestring</em>) &#8211; Layer name.</li>
 <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Input layer name.</li>
+<li><strong>stride</strong> (<em>Int</em>) &#8211; window size.</li>
 <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li>
 </ul>
 </td>
@@ -2307,6 +2312,10 @@ the way how to configure a neural network topology in Paddle Python code.</p>
 <dt>
 <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">first_seq</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
 <dd><p>Get First Timestamp Activation of a sequence.</p>
+<p>If stride &gt; 0, this layer slides a window whose size is determined by stride,
+and return the first value of the window as the output. Thus, a long sequence
+will be shorten. Note that for sequence with sub-sequence, the default value
+of stride is -1.</p>
 <p>The simple usage is:</p>
 <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">seq</span> <span class="o">=</span> <span class="n">first_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">)</span>
 </pre></div>
@@ -2319,6 +2328,7 @@ the way how to configure a neural network topology in Paddle Python code.</p>
 <li><strong>agg_level</strong> &#8211; aggregation level</li>
 <li><strong>name</strong> (<em>basestring</em>) &#8211; Layer name.</li>
 <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; Input layer name.</li>
+<li><strong>stride</strong> (<em>Int</em>) &#8211; window size.</li>
 <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttribute</em>) &#8211; extra layer attributes.</li>
 </ul>
 </td>