Skip to content

P
Paddle

机器未来 / Paddle
与 Fork 源项目一致

Fork自 PaddlePaddle / Paddle

通知 1
Star 1
Fork 0
P
Paddle
提交 43f1c358 编写于 作者: T Travis CI
浏览文件
操作

Deploy to GitHub Pages: aa756a3d

上级 4e081a9f
展开全部 隐藏空白更改
内联 并排
Showing with 50 addition and 90 deletion
develop/doc/api/v2/config/layer.html
浏览文件 @ 43f1c358
...@@ -661,7 +661,7 @@ timestep to (t+k+1)-th timestep. Assumed that the hidden dim of input ...@@ -661,7 +661,7 @@ timestep to (t+k+1)-th timestep. Assumed that the hidden dim of input
activations are d, the activations r_t for the new layer at time-step t are:</p> activations are d, the activations r_t for the new layer at time-step t are:</p>
<div class="math"> <div class="math">
\[r_{t,r} = \sum_{j=1}^{k + 1} {w_{i,j}h_{t+j-1, i}} \[r_{t,r} = \sum_{j=1}^{k + 1} {w_{i,j}h_{t+j-1, i}}
\quad ext{for} \quad (1 \leq i \leq d)\]</div> \quad \text{for} \quad (1 \leq i \leq d)\]</div>
<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">The <cite>context_len</cite> is <cite>k + 1</cite>. That is to say, the lookahead step <p class="last">The <cite>context_len</cite> is <cite>k + 1</cite>. That is to say, the lookahead step
...@@ -3424,66 +3424,46 @@ details.</li> ...@@ -3424,66 +3424,46 @@ details.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">factorization_machine</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">factorization_machine</code></dt>
<dd><blockquote> <dd><p>The Factorization Machine models pairwise feature interactions as inner
<div><p>The Factorization Machine models pairwise feature interactions as inner
product of the learned latent vectors corresponding to each input feature. product of the learned latent vectors corresponding to each input feature.
The Factorization Machine can effectively capture feature interactions The Factorization Machine can effectively capture feature interactions
especially when the input is sparse.</p> especially when the input is sparse.</p>
<p>This implementation only consider the 2-order feature interactions using <p>This implementation only consider the 2-order feature interactions using
Factorization Machine with the formula:</p> Factorization Machine with the formula:</p>
<div class="math"> <div class="math">
\[y = \sum_{i=1}^{n-1}\sum_{j=i+1}^n\langle v_i, v_j\]</div> \[y = \sum_{i=1}^{n-1}\sum_{j=i+1}^n\langle v_i, v_j \rangle x_i x_j\]</div>
</div></blockquote> <div class="admonition note">
<p>angle x_i x_j</p> <p class="first admonition-title">Note</p>
<blockquote> <p class="last">X is the input vector with size n. V is the factor matrix. Each row of V
<div><dl class="docutils">
<dt>Note:</dt>
<dd>X is the input vector with size n. V is the factor matrix. Each row of V
is the latent vector corresponding to each input dimesion. The size of is the latent vector corresponding to each input dimesion. The size of
each latent vector is k.</dd> each latent vector is k.</p>
</dl> </div>
<p>For details of Factorization Machine, please refer to the paper: <p>For details of Factorization Machine, please refer to the paper:
Factorization machines.</p> Factorization machines.</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">param input:</th><td class="field-body">The input layer. Supported input types: all input data types <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
on CPU, and only dense input types on GPU.</td> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input layer. Supported input types: all input data types
</tr> on CPU, and only dense input types on GPU.</li>
<tr class="field-even field"><th class="field-name">type input:</th><td class="field-body">paddle.v2.config_base.Layer</td> <li><strong>factor_size</strong> &#8211; The hyperparameter that defines the dimensionality of
</tr> the latent vector size.</li>
<tr class="field-odd field"><th class="field-name" colspan="2">param factor_size:</th></tr> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. Default is linear activation.</li>
<tr class="field-odd field"><td>&#160;</td><td class="field-body">The hyperparameter that defines the dimensionality of <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
the latent vector size.</td> details.</li>
</tr> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Extra Layer config.</li>
<tr class="field-even field"><th class="field-name" colspan="2">type context_len:</th></tr> </ul>
<tr class="field-even field"><td>&#160;</td><td class="field-body">int</td> </td>
</tr>
<tr class="field-odd field"><th class="field-name">param act:</th><td class="field-body">Activation Type. Default is linear activation.</td>
</tr>
<tr class="field-even field"><th class="field-name">type act:</th><td class="field-body">paddle.v2.activation.Base</td>
</tr>
<tr class="field-odd field"><th class="field-name" colspan="2">param param_attr:</th></tr>
<tr class="field-odd field"><td>&#160;</td><td class="field-body">The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</td>
</tr>
<tr class="field-even field"><th class="field-name" colspan="2">type param_attr:</th></tr>
<tr class="field-even field"><td>&#160;</td><td class="field-body">paddle.v2.attr.ParameterAttribute</td>
</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 config.</td>
</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.ExtraAttributeNone</td>
</tr> </tr>
<tr class="field-odd field"><th class="field-name">return:</th><td class="field-body">paddle.v2.config_base.Layer object.</td> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">paddle.v2.config_base.Layer object.</p>
</td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">rtype:</th><td class="field-body">paddle.v2.config_base.Layer</td> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">paddle.v2.config_base.Layer</p>
</td>
</tr> </tr>
</tbody> </tbody>
</table> </table>
</div></blockquote>
</dd></dl> </dd></dl>
</div> </div>
...@@ -4462,7 +4442,7 @@ details.</li> ...@@ -4462,7 +4442,7 @@ 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="#id5"><span class="problematic" id="id6">:match:`X&#8217;`</span></a> and <span class="math">\(\sigma\)</span> is finally returned.</p> product between <span class="math">\(X'\)</span> and <span class="math">\(\sigma\)</span> is finally returned.</p>
<dl class="docutils"> <dl class="docutils">
<dt>Reference:</dt> <dt>Reference:</dt>
<dd><a class="reference external" href="https://arxiv.org/abs/1612.08083">Language Modeling with Gated Convolutional Networks</a></dd> <dd><a class="reference external" href="https://arxiv.org/abs/1612.08083">Language Modeling with Gated Convolutional Networks</a></dd>
......
develop/doc/searchindex.js
浏览文件 @ 43f1c358
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 @ 43f1c358
...@@ -674,7 +674,7 @@ timestep to (t+k+1)-th timestep. Assumed that the hidden dim of input ...@@ -674,7 +674,7 @@ timestep to (t+k+1)-th timestep. Assumed that the hidden dim of input
activations are d, the activations r_t for the new layer at time-step t are:</p> activations are d, the activations r_t for the new layer at time-step t are:</p>
<div class="math"> <div class="math">
\[r_{t,r} = \sum_{j=1}^{k + 1} {w_{i,j}h_{t+j-1, i}} \[r_{t,r} = \sum_{j=1}^{k + 1} {w_{i,j}h_{t+j-1, i}}
\quad ext{for} \quad (1 \leq i \leq d)\]</div> \quad \text{for} \quad (1 \leq i \leq d)\]</div>
<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">The <cite>context_len</cite> is <cite>k + 1</cite>. That is to say, the lookahead step <p class="last">The <cite>context_len</cite> is <cite>k + 1</cite>. That is to say, the lookahead step
...@@ -3437,66 +3437,46 @@ details.</li> ...@@ -3437,66 +3437,46 @@ details.</li>
<dl class="class"> <dl class="class">
<dt> <dt>
<em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">factorization_machine</code></dt> <em class="property">class </em><code class="descclassname">paddle.v2.layer.</code><code class="descname">factorization_machine</code></dt>
<dd><blockquote> <dd><p>The Factorization Machine models pairwise feature interactions as inner
<div><p>The Factorization Machine models pairwise feature interactions as inner
product of the learned latent vectors corresponding to each input feature. product of the learned latent vectors corresponding to each input feature.
The Factorization Machine can effectively capture feature interactions The Factorization Machine can effectively capture feature interactions
especially when the input is sparse.</p> especially when the input is sparse.</p>
<p>This implementation only consider the 2-order feature interactions using <p>This implementation only consider the 2-order feature interactions using
Factorization Machine with the formula:</p> Factorization Machine with the formula:</p>
<div class="math"> <div class="math">
\[y = \sum_{i=1}^{n-1}\sum_{j=i+1}^n\langle v_i, v_j\]</div> \[y = \sum_{i=1}^{n-1}\sum_{j=i+1}^n\langle v_i, v_j \rangle x_i x_j\]</div>
</div></blockquote> <div class="admonition note">
<p>angle x_i x_j</p> <p class="first admonition-title">注解</p>
<blockquote> <p class="last">X is the input vector with size n. V is the factor matrix. Each row of V
<div><dl class="docutils">
<dt>Note:</dt>
<dd>X is the input vector with size n. V is the factor matrix. Each row of V
is the latent vector corresponding to each input dimesion. The size of is the latent vector corresponding to each input dimesion. The size of
each latent vector is k.</dd> each latent vector is k.</p>
</dl> </div>
<p>For details of Factorization Machine, please refer to the paper: <p>For details of Factorization Machine, please refer to the paper:
Factorization machines.</p> Factorization machines.</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">param input:</th><td class="field-body">The input layer. Supported input types: all input data types <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
on CPU, and only dense input types on GPU.</td> <li><strong>input</strong> (<em>paddle.v2.config_base.Layer</em>) &#8211; The input layer. Supported input types: all input data types
</tr> on CPU, and only dense input types on GPU.</li>
<tr class="field-even field"><th class="field-name">type input:</th><td class="field-body">paddle.v2.config_base.Layer</td> <li><strong>factor_size</strong> &#8211; The hyperparameter that defines the dimensionality of
</tr> the latent vector size.</li>
<tr class="field-odd field"><th class="field-name" colspan="2">param factor_size:</th></tr> <li><strong>act</strong> (<em>paddle.v2.activation.Base</em>) &#8211; Activation Type. Default is linear activation.</li>
<tr class="field-odd field"><td>&#160;</td><td class="field-body">The hyperparameter that defines the dimensionality of <li><strong>param_attr</strong> (<em>paddle.v2.attr.ParameterAttribute</em>) &#8211; The parameter attribute. See paddle.v2.attr.ParameterAttribute for
the latent vector size.</td> details.</li>
</tr> <li><strong>layer_attr</strong> (<em>paddle.v2.attr.ExtraAttributeNone</em>) &#8211; Extra Layer config.</li>
<tr class="field-even field"><th class="field-name" colspan="2">type context_len:</th></tr> </ul>
<tr class="field-even field"><td>&#160;</td><td class="field-body">int</td> </td>
</tr>
<tr class="field-odd field"><th class="field-name">param act:</th><td class="field-body">Activation Type. Default is linear activation.</td>
</tr>
<tr class="field-even field"><th class="field-name">type act:</th><td class="field-body">paddle.v2.activation.Base</td>
</tr>
<tr class="field-odd field"><th class="field-name" colspan="2">param param_attr:</th></tr>
<tr class="field-odd field"><td>&#160;</td><td class="field-body">The parameter attribute. See paddle.v2.attr.ParameterAttribute for
details.</td>
</tr>
<tr class="field-even field"><th class="field-name" colspan="2">type param_attr:</th></tr>
<tr class="field-even field"><td>&#160;</td><td class="field-body">paddle.v2.attr.ParameterAttribute</td>
</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 config.</td>
</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.ExtraAttributeNone</td>
</tr> </tr>
<tr class="field-odd field"><th class="field-name">return:</th><td class="field-body">paddle.v2.config_base.Layer object.</td> <tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">paddle.v2.config_base.Layer object.</p>
</td>
</tr> </tr>
<tr class="field-even field"><th class="field-name">rtype:</th><td class="field-body">paddle.v2.config_base.Layer</td> <tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">paddle.v2.config_base.Layer</p>
</td>
</tr> </tr>
</tbody> </tbody>
</table> </table>
</div></blockquote>
</dd></dl> </dd></dl>
</div> </div>
...@@ -4475,7 +4455,7 @@ details.</li> ...@@ -4475,7 +4455,7 @@ 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="#id5"><span class="problematic" id="id6">:match:`X&#8217;`</span></a> and <span class="math">\(\sigma\)</span> is finally returned.</p> product between <span class="math">\(X'\)</span> and <span class="math">\(\sigma\)</span> is finally returned.</p>
<dl class="docutils"> <dl class="docutils">
<dt>Reference:</dt> <dt>Reference:</dt>
<dd><a class="reference external" href="https://arxiv.org/abs/1612.08083">Language Modeling with Gated Convolutional Networks</a></dd> <dd><a class="reference external" href="https://arxiv.org/abs/1612.08083">Language Modeling with Gated Convolutional Networks</a></dd>
......
develop/doc_cn/searchindex.js
浏览文件 @ 43f1c358
此差异已折叠。
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或