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 aa798ba1 编写于 作者: T Travis CI
浏览文件
操作

Deploy to GitHub Pages: c80af6ff

上级 175f359a
展开全部 隐藏空白更改
内联 并排
Showing with 78 addition and 6754 deletion
develop/doc/api/v2/fluid/evaluator.html
浏览文件 @ aa798ba1
......@@ -220,75 +220,6 @@
<h1>Evaluator<a class="headerlink" href="#evaluator" title="Permalink to this headline"></a></h1>
<div class="section" id="id1">
<h2>Evaluator<a class="headerlink" href="#id1" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.evaluator.</code><code class="descname">Evaluator</code><span class="sig-paren">(</span><em>name</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Base Class for all evaluators</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
<li><strong>name</strong> (<em>str</em>) &#8211; The name of evaluator. such as, &#8220;accuracy&#8221;. Used for generate
temporary variable name.</li>
<li><strong>main_program</strong> (<em>Program</em><em>, </em><em>optional</em>) &#8211; The evaluator should be added to this
main_program. Default default_main_program()</li>
<li><strong>startup_program</strong> (<em>Program</em><em>, </em><em>optional</em>) &#8211; The parameter should be added to this
startup_program. Default default_startup_program()</li>
</ul>
</td>
</tr>
</tbody>
</table>
<dl class="attribute">
<dt id="paddle.v2.fluid.evaluator.Evaluator.states">
<code class="descname">states</code><a class="headerlink" href="#paddle.v2.fluid.evaluator.Evaluator.states" title="Permalink to this definition"></a></dt>
<dd><p><em>list</em> &#8211; The list of state variables. states will be reset to zero
when <cite>reset</cite> is invoked.</p>
</dd></dl>
<dl class="attribute">
<dt id="paddle.v2.fluid.evaluator.Evaluator.metrics">
<code class="descname">metrics</code><a class="headerlink" href="#paddle.v2.fluid.evaluator.Evaluator.metrics" title="Permalink to this definition"></a></dt>
<dd><p><em>list</em> &#8211; The list of metrics variables. They will be calculate
every mini-batch</p>
</dd></dl>
<dl class="method">
<dt>
<code class="descname">reset</code><span class="sig-paren">(</span><em>executor</em>, <em>reset_program=None</em><span class="sig-paren">)</span></dt>
<dd><p>reset metric states at the begin of each pass/user specified batch</p>
</dd></dl>
<dl class="method">
<dt>
<code class="descname">eval</code><span class="sig-paren">(</span><em>executor</em>, <em>eval_program=None</em><span class="sig-paren">)</span></dt>
<dd><p>Evaluate the statistics merged by multiple mini-batches.</p>
</dd></dl>
<dl class="method">
<dt>
<code class="descname">create_state</code><span class="sig-paren">(</span><em>suffix</em>, <em>dtype</em>, <em>shape</em><span class="sig-paren">)</span></dt>
<dd><p>Create state variable.</p>
<p>NOTE: It is not a public API.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
<li><strong>suffix</strong> (<em>str</em>) &#8211; the state suffix.</li>
<li><strong>dtype</strong> (<em>str|core.DataType</em>) &#8211; the state data type</li>
<li><strong>shape</strong> (<em>tuple|list</em>) &#8211; the shape of state</li>
</ul>
</td>
</tr>
</tbody>
</table>
<p>Returns: State variable</p>
</dd></dl>
</dd></dl>
</div>
</div>
......
develop/doc/api/v2/fluid/initializer.html
浏览文件 @ aa798ba1
......@@ -220,90 +220,21 @@
<h1>Initializer<a class="headerlink" href="#initializer" title="Permalink to this headline"></a></h1>
<div class="section" id="id1">
<h2>Initializer<a class="headerlink" href="#id1" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">Initializer</code></dt>
<dd><p>Base class for variable initializers</p>
<p>Defines the common interface of variable initializers.
They add operations to the init program that are used
to initialize variables. Users should not use this class
directly, but need to use one of its implementations.</p>
</dd></dl>
</div>
<div class="section" id="constantinitializer">
<h2>ConstantInitializer<a class="headerlink" href="#constantinitializer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">ConstantInitializer</code><span class="sig-paren">(</span><em>value=0.0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the constant initializer</p>
</dd></dl>
</div>
<div class="section" id="uniforminitializer">
<h2>UniformInitializer<a class="headerlink" href="#uniforminitializer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">UniformInitializer</code><span class="sig-paren">(</span><em>low=-1.0</em>, <em>high=1.0</em>, <em>seed=0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the random uniform distribution initializer</p>
</dd></dl>
</div>
<div class="section" id="normalinitializer">
<h2>NormalInitializer<a class="headerlink" href="#normalinitializer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">NormalInitializer</code><span class="sig-paren">(</span><em>loc=0.0</em>, <em>scale=1.0</em>, <em>seed=0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the random Normal(Gaussian) distribution initializer</p>
</dd></dl>
</div>
<div class="section" id="xavierinitializer">
<h2>XavierInitializer<a class="headerlink" href="#xavierinitializer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">XavierInitializer</code><span class="sig-paren">(</span><em>uniform=True</em>, <em>fan_in=None</em>, <em>fan_out=None</em>, <em>seed=0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the Xavier initializer</p>
<p>This class implements the Xavier weight initializer from the paper
Understanding the difficulty of training deep feedforward neural
networks[1] by Xavier Glorot and Yoshua Bengio.</p>
<p>This initializer is designed to keep the scale of the gradients
approximately same in all the layers. In case of Uniform distribution,
the range is [-x, x], where x = sqrt(6 / (fan_in + fan_out)).
In case of Normal distribution, the mean is 0 and the standard deviation
is sqrt(2/ (fan_in + fan_out)).</p>
<p class="rubric">References</p>
<dl class="docutils">
<dt>[1] Understanding the difficulty of training deep feedforward neural</dt>
<dd>networks. International conference on artificial intelligence and
statistics.
(<a class="reference external" href="http://proceedings.mlr.press/v9/glorot10a.html">http://proceedings.mlr.press/v9/glorot10a.html</a>)</dd>
</dl>
</dd></dl>
</div>
<div class="section" id="msrainitializer">
<h2>MSRAInitializer<a class="headerlink" href="#msrainitializer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">MSRAInitializer</code><span class="sig-paren">(</span><em>uniform=True</em>, <em>fan_in=None</em>, <em>seed=0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the MSRA initializer a.k.a. Kaiming Initializer</p>
<p>This class implements the weight initialization from the paper
Delving Deep into Rectifiers: Surpassing Human-Level Performance on
ImageNet Classification[1] by Kaiming He, Xiangyu Zhang, Shaoqing Ren
and Jian Sun. This is a robust initialization method that particularly
considers the rectifier nonlinearities. In case of Uniform distribution,
the range is [-x, x], where x = sqrt(6 / fan_in). In case of Normal
distribution, the mean is 0 and the standard deviation
is sqrt(2/ fan_in).</p>
<p class="rubric">References</p>
<dl class="docutils">
<dt>[1] Delving Deep into Rectifiers: Surpassing Human-Level Performance</dt>
<dd>on ImageNet Classification
(<a class="reference external" href="https://arxiv.org/abs/1502.01852">https://arxiv.org/abs/1502.01852</a>)</dd>
</dl>
</dd></dl>
</div>
</div>
......
develop/doc/api/v2/fluid/io.html
浏览文件 @ aa798ba1
......@@ -220,23 +220,6 @@
<h1>IO<a class="headerlink" href="#io" title="Permalink to this headline"></a></h1>
<div class="section" id="is-parameter">
<h2>is_parameter<a class="headerlink" href="#is-parameter" title="Permalink to this headline"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.io.</code><code class="descname">is_parameter</code><span class="sig-paren">(</span><em>var</em><span class="sig-paren">)</span></dt>
<dd><p>Check whether the variable is a Parameter.</p>
<p>This function checks whether the input variable is a Parameter.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>var</strong> &#8211; The input variable.</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">boolean result whether the variable is a Parameter.</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
</div>
......
develop/doc/api/v2/fluid/layers.html
浏览文件 @ aa798ba1
因为 它太大了无法显示 source diff 。你可以改为 查看blob。
develop/doc/api/v2/fluid/nets.html
浏览文件 @ aa798ba1
......@@ -220,118 +220,18 @@
<h1>Nets<a class="headerlink" href="#nets" title="Permalink to this headline"></a></h1>
<div class="section" id="simple-img-conv-pool">
<h2>simple_img_conv_pool<a class="headerlink" href="#simple-img-conv-pool" title="Permalink to this headline"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">simple_img_conv_pool</code><span class="sig-paren">(</span><em>input</em>, <em>num_filters</em>, <em>filter_size</em>, <em>pool_size</em>, <em>pool_stride</em>, <em>act</em>, <em>param_attr=None</em>, <em>pool_type='max'</em>, <em>use_cudnn=True</em><span class="sig-paren">)</span></dt>
<dd></dd></dl>
</div>
<div class="section" id="img-conv-group">
<h2>img_conv_group<a class="headerlink" href="#img-conv-group" title="Permalink to this headline"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">img_conv_group</code><span class="sig-paren">(</span><em>input</em>, <em>conv_num_filter</em>, <em>pool_size</em>, <em>conv_padding=1</em>, <em>conv_filter_size=3</em>, <em>conv_act=None</em>, <em>param_attr=None</em>, <em>conv_with_batchnorm=False</em>, <em>conv_batchnorm_drop_rate=None</em>, <em>pool_stride=1</em>, <em>pool_type=None</em>, <em>use_cudnn=True</em><span class="sig-paren">)</span></dt>
<dd><p>Image Convolution Group, Used for vgg net.</p>
</dd></dl>
</div>
<div class="section" id="sequence-conv-pool">
<h2>sequence_conv_pool<a class="headerlink" href="#sequence-conv-pool" title="Permalink to this headline"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">sequence_conv_pool</code><span class="sig-paren">(</span><em>input</em>, <em>num_filters</em>, <em>filter_size</em>, <em>param_attr=None</em>, <em>act='sigmoid'</em>, <em>pool_type='max'</em><span class="sig-paren">)</span></dt>
<dd></dd></dl>
</div>
<div class="section" id="glu">
<h2>glu<a class="headerlink" href="#glu" title="Permalink to this headline"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">glu</code><span class="sig-paren">(</span><em>input</em>, <em>dim=-1</em><span class="sig-paren">)</span></dt>
<dd><p>The gated linear unit composed by split, sigmoid activation and elementwise
multiplication. Specifically, Split the input into two equal sized parts
<span class="math">\(a\)</span> and <span class="math">\(b\)</span> along the given dimension and then compute as
following:</p>
<blockquote>
<div><div class="math">
\[{GLU}(a, b)= a \otimes \sigma(b)\]</div>
</div></blockquote>
<p>Refer to <a class="reference external" href="https://arxiv.org/pdf/1612.08083.pdf">Language Modeling with Gated Convolutional Networks</a>.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>input</strong> (<em>Variable</em>) &#8211; The input variable which is a Tensor or LoDTensor.</li>
<li><strong>dim</strong> (<em>int</em>) &#8211; The dimension along which to split. If <span class="math">\(dim &lt; 0\)</span>, the
dimension to split along is <span class="math">\(rank(input) + dim\)</span>.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">The Tensor variable with half the size of input.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">Variable</p>
</td>
</tr>
</tbody>
</table>
<p class="rubric">Examples</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="c1"># x is a Tensor variable with shape [3, 6, 9]</span>
<span class="n">fluid</span><span class="o">.</span><span class="n">nets</span><span class="o">.</span><span class="n">glu</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">x</span><span class="p">,</span> <span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> <span class="c1"># shape of output: [3, 3, 9]</span>
</pre></div>
</div>
</dd></dl>
</div>
<div class="section" id="dot-product-attention">
<h2>dot_product_attention<a class="headerlink" href="#dot-product-attention" title="Permalink to this headline"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">dot_product_attention</code><span class="sig-paren">(</span><em>querys</em>, <em>keys</em>, <em>values</em><span class="sig-paren">)</span></dt>
<dd><p>The dot-product attention.</p>
<p>Attention mechanism can be seen as mapping a query and a set of key-value
pairs to an output. The output is computed as a weighted sum of the values,
where the weight assigned to each value is computed by a compatibility
function (dot-product here) of the query with the corresponding key.</p>
<p>The dot-product attention can be implemented through (batch) matrix
multipication as follows:</p>
<blockquote>
<div><div class="math">
\[Attention(Q, K, V)= softmax(QK^\mathrm{T})V\]</div>
</div></blockquote>
<p>Refer to <a class="reference external" href="https://arxiv.org/pdf/1706.03762.pdf">Attention Is All You Need</a>.</p>
<p>Note that batch data containing sequences with different lengths is not
supported by this because of the (batch) matrix multipication.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>query</strong> (<em>Variable</em>) &#8211; The input variable which is a Tensor or LoDTensor.</li>
<li><strong>key</strong> (<em>Variable</em>) &#8211; The input variable which is a Tensor or LoDTensor.</li>
<li><strong>value</strong> (<em>Variable</em>) &#8211; The input variable which is a Tensor or LoDTensor.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">The Tensor variables representing the output and attention scores.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">tuple</p>
</td>
</tr>
</tbody>
</table>
<p class="rubric">Examples</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="c1"># Suppose q, k, v are tensor variables with the following shape:</span>
<span class="c1"># q: [3, 5, 9], k: [3, 6, 9], v: [3, 6, 10]</span>
<span class="n">out</span><span class="p">,</span> <span class="n">attn_scores</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">nets</span><span class="o">.</span><span class="n">dot_product_attention</span><span class="p">(</span><span class="n">q</span><span class="p">,</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span>
<span class="n">out</span><span class="o">.</span><span class="n">shape</span> <span class="c1"># [3, 5, 10]</span>
<span class="n">attn_scores</span><span class="o">.</span><span class="n">shape</span> <span class="c1"># [3, 5, 6]</span>
</pre></div>
</div>
</dd></dl>
</div>
</div>
......
develop/doc/api/v2/fluid/optimizer.html
浏览文件 @ aa798ba1
......@@ -220,105 +220,24 @@
<h1>Optimizer<a class="headerlink" href="#optimizer" title="Permalink to this headline"></a></h1>
<div class="section" id="id1">
<h2>Optimizer<a class="headerlink" href="#id1" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">Optimizer</code><span class="sig-paren">(</span><em>global_step=None</em>, <em>regularization=None</em><span class="sig-paren">)</span></dt>
<dd><p>Optimizer Base class.</p>
<p>Define the common interface of an optimizer.
User should not use this class directly,
but need to use one of it&#8217;s implementation.</p>
<dl class="method">
<dt>
<code class="descname">create_optimization_pass</code><span class="sig-paren">(</span><em>parameters_and_grads</em>, <em>loss</em>, <em>startup_program=None</em><span class="sig-paren">)</span></dt>
<dd><p>Add optimization operators to update gradients to variables.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>loss</strong> &#8211; the target that this optimization is for.</li>
<li><strong>parameters_and_grads</strong> &#8211; a list of (variable, gradient) pair to update.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">a list of operators that will complete one step of
optimization. This will include parameter update ops, global step
update ops and any other custom ops required by subclasses to manage
their internal state.
:param startup_program:</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">return_op_list</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="method">
<dt>
<code class="descname">minimize</code><span class="sig-paren">(</span><em>loss</em>, <em>startup_program=None</em>, <em>parameter_list=None</em>, <em>no_grad_set=None</em><span class="sig-paren">)</span></dt>
<dd><p>Add operations to minimize <cite>loss</cite> by updating <cite>parameter_list</cite>.</p>
<p>This method combines interface <cite>append_backward()</cite> and
<cite>create_optimization_pass()</cite> into one.</p>
</dd></dl>
</dd></dl>
</div>
<div class="section" id="sgdoptimizer">
<h2>SGDOptimizer<a class="headerlink" href="#sgdoptimizer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">SGDOptimizer</code><span class="sig-paren">(</span><em>learning_rate</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Simple SGD optimizer without any state.</p>
</dd></dl>
</div>
<div class="section" id="momentumoptimizer">
<h2>MomentumOptimizer<a class="headerlink" href="#momentumoptimizer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">MomentumOptimizer</code><span class="sig-paren">(</span><em>learning_rate</em>, <em>momentum</em>, <em>use_nesterov=False</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Simple Momentum optimizer with velocity state</p>
</dd></dl>
</div>
<div class="section" id="adagradoptimizer">
<h2>AdagradOptimizer<a class="headerlink" href="#adagradoptimizer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">AdagradOptimizer</code><span class="sig-paren">(</span><em>learning_rate</em>, <em>epsilon=1e-06</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Simple Adagrad optimizer with moment state</p>
</dd></dl>
</div>
<div class="section" id="adamoptimizer">
<h2>AdamOptimizer<a class="headerlink" href="#adamoptimizer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">AdamOptimizer</code><span class="sig-paren">(</span><em>learning_rate=0.001</em>, <em>beta1=0.9</em>, <em>beta2=0.999</em>, <em>epsilon=1e-08</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the Adam Optimizer</p>
</dd></dl>
</div>
<div class="section" id="adamaxoptimizer">
<h2>AdamaxOptimizer<a class="headerlink" href="#adamaxoptimizer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">AdamaxOptimizer</code><span class="sig-paren">(</span><em>learning_rate=0.001</em>, <em>beta1=0.9</em>, <em>beta2=0.999</em>, <em>epsilon=1e-08</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the Adamax Optimizer</p>
</dd></dl>
</div>
<div class="section" id="decayedadagradoptimizer">
<h2>DecayedAdagradOptimizer<a class="headerlink" href="#decayedadagradoptimizer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">DecayedAdagradOptimizer</code><span class="sig-paren">(</span><em>learning_rate</em>, <em>decay=0.95</em>, <em>epsilon=1e-06</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Simple Decayed Adagrad optimizer with moment state</p>
</dd></dl>
</div>
</div>
......
develop/doc/api/v2/fluid/profiler.html
浏览文件 @ aa798ba1
......@@ -220,35 +220,6 @@
<h1>Profiler<a class="headerlink" href="#profiler" title="Permalink to this headline"></a></h1>
<div class="section" id="id1">
<h2>Profiler<a class="headerlink" href="#id1" title="Permalink to this headline"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.profiler.</code><code class="descname">cuda_profiler</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwds</em><span class="sig-paren">)</span></dt>
<dd><p>The CUDA profiler.
This fuctions is used to profile CUDA program by CUDA runtime application
programming interface. The profiling result will be written into
<cite>output_file</cite> with Key-Value pair format or Comma separated values format.
The user can set the output mode by <cite>output_mode</cite> argument and set the
counters/options for profiling by <cite>config</cite> argument. The default config
is [&#8216;gpustarttimestamp&#8217;, &#8216;gpustarttimestamp&#8217;, &#8216;gridsize3d&#8217;,
&#8216;threadblocksize&#8217;, &#8216;streamid&#8217;, &#8216;enableonstart 0&#8217;, &#8216;conckerneltrace&#8217;].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
<li><strong>output_file</strong> (<em>string</em>) &#8211; The output file name, the result will be
written into this file.</li>
<li><strong>output_mode</strong> (<em>string</em>) &#8211; The output mode has Key-Value pair format and
Comma separated values format. It should be &#8216;kvp&#8217; or &#8216;csv&#8217;.</li>
<li><strong>config</strong> (<em>list of string</em>) &#8211; The profiler options and counters can refer
to &#8220;Compute Command Line Profiler User Guide&#8221;.</li>
</ul>
</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
</div>
......
develop/doc/api/v2/fluid/regularizer.html
浏览文件 @ aa798ba1
......@@ -220,36 +220,12 @@
<h1>Regularizer<a class="headerlink" href="#regularizer" title="Permalink to this headline"></a></h1>
<div class="section" id="weightdecayregularizer">
<h2>WeightDecayRegularizer<a class="headerlink" href="#weightdecayregularizer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.regularizer.</code><code class="descname">WeightDecayRegularizer</code></dt>
<dd><p>Base class for weight decay regularizers</p>
<p>Defines the common interface of weight-decay regularizers.
Weight-decay regularizers are added only during the backward
pass for faster regularization. They add operations to the network
that correspond to gradient of the regularization function.
Users should not use this class directly, but need to use one
of its implementations</p>
</dd></dl>
</div>
<div class="section" id="l2decayregularizer">
<h2>L2DecayRegularizer<a class="headerlink" href="#l2decayregularizer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.regularizer.</code><code class="descname">L2DecayRegularizer</code><span class="sig-paren">(</span><em>regularization_coeff=0.0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the L2 Weight Decay Regularization</p>
</dd></dl>
</div>
<div class="section" id="module-paddle.v2.fluid.regularizer">
<span id="l1decayregularizer"></span><h2>L1DecayRegularizer<a class="headerlink" href="#module-paddle.v2.fluid.regularizer" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="paddle.v2.fluid.regularizer.L1DecayRegularizer">
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.regularizer.</code><code class="descname">L1DecayRegularizer</code><span class="sig-paren">(</span><em>regularization_coeff=0.0</em><span class="sig-paren">)</span><a class="headerlink" href="#paddle.v2.fluid.regularizer.L1DecayRegularizer" title="Permalink to this definition"></a></dt>
<dd><p>Implements the L1 Weight Decay Regularization</p>
</dd></dl>
<div class="section" id="l1decayregularizer">
<h2>L1DecayRegularizer<a class="headerlink" href="#l1decayregularizer" title="Permalink to this headline"></a></h2>
</div>
</div>
......
develop/doc/genindex.html
浏览文件 @ aa798ba1
......@@ -217,7 +217,6 @@
<a href="#B"><strong>B</strong></a>
| <a href="#C"><strong>C</strong></a>
| <a href="#L"><strong>L</strong></a>
| <a href="#M"><strong>M</strong></a>
| <a href="#P"><strong>P</strong></a>
| <a href="#R"><strong>R</strong></a>
| <a href="#S"><strong>S</strong></a>
......@@ -243,14 +242,12 @@
<h2 id="L">L</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/fluid/regularizer.html#paddle.v2.fluid.regularizer.L1DecayRegularizer">L1DecayRegularizer (class in paddle.v2.fluid.regularizer)</a>
</li>
<li><a href="api/v2/data/image.html#paddle.v2.image.left_right_flip">left_right_flip() (in module paddle.v2.image)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/data/image.html#paddle.v2.image.load_and_transform">load_and_transform() (in module paddle.v2.image)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/data/image.html#paddle.v2.image.load_image">load_image() (in module paddle.v2.image)</a>
</li>
<li><a href="api/v2/data/image.html#paddle.v2.image.load_image_bytes">load_image_bytes() (in module paddle.v2.image)</a>
......@@ -258,23 +255,13 @@
</ul></td>
</tr></table>
<h2 id="M">M</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/fluid/evaluator.html#paddle.v2.fluid.evaluator.Evaluator.metrics">metrics (paddle.v2.fluid.evaluator.Evaluator attribute)</a>
</li>
</ul></td>
</tr></table>
<h2 id="P">P</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/fluid/regularizer.html#module-paddle.v2.fluid.regularizer">paddle.v2.fluid.regularizer (module)</a>
<li><a href="api/v2/data/image.html#module-paddle.v2.image">paddle.v2.image (module)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/data/image.html#module-paddle.v2.image">paddle.v2.image (module)</a>
</li>
<li><a href="api/v1/data_provider/pydataprovider2_en.html#paddle.trainer.PyDataProvider2.provider">provider() (in module paddle.trainer.PyDataProvider2)</a>
</li>
</ul></td>
......@@ -296,10 +283,6 @@
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/data/image.html#paddle.v2.image.simple_transform">simple_transform() (in module paddle.v2.image)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/fluid/evaluator.html#paddle.v2.fluid.evaluator.Evaluator.states">states (paddle.v2.fluid.evaluator.Evaluator attribute)</a>
</li>
</ul></td>
</tr></table>
......
develop/doc/operators.json
浏览文件 @ aa798ba1
......@@ -1140,24 +1140,6 @@
"intermediate" : 0
} ],
"attrs" : [ ]
},{
"type" : "log",
"comment" : "\nLog Activation Operator.\n\n$out = \\ln(x)$\n\nNatural logarithm of x.\n\n",
"inputs" : [
{
"name" : "X",
"comment" : "Input of Log operator",
"duplicable" : 0,
"intermediate" : 0
} ],
"outputs" : [
{
"name" : "Out",
"comment" : "Output of Log operator",
"duplicable" : 0,
"intermediate" : 0
} ],
"attrs" : [ ]
},{
"type" : "softmax",
"comment" : "\nSoftmax Operator.\n\nThe input of the softmax operator is a 2-D tensor with shape N x K (N is the\nbatch_size, K is the dimension of input feature). The output tensor has the\nsame shape as the input tensor.\n\nFor each row of the input tensor, the softmax operator squashes the\nK-dimensional vector of arbitrary real values to a K-dimensional vector of real\nvalues in the range [0, 1] that add up to 1.\nIt computes the exponential of the given dimension and the sum of exponential\nvalues of all the other dimensions in the K-dimensional vector input.\nThen the ratio of the exponential of the given dimension and the sum of\nexponential values of all the other dimensions is the output of the softmax\noperator.\n\nFor each row $i$ and each column $j$ in Input(X), we have:\n $$Out[i, j] = \\frac{\\exp(X[i, j])}{\\sum_j(exp(X[i, j])}$$\n\n",
......@@ -1546,6 +1528,34 @@
"comment" : "(float, default 0.0) L2 regularization strength.",
"generated" : 0
} ]
},{
"type" : "rank_loss",
"comment" : "\nRankLoss Operator.\n\nRankLoss operator for RankNet\n(http://icml.cc/2015/wp-content/uploads/2015/06/icml_ranking.pdf). \nRankNet is a pairwise ranking model with\none training sample consisting of a pair of doc A and B, and the label P\nindicating that A is ranked higher than B or not:\n\nP = {0, 1} or {0, 0.5, 1}, where 0.5 means no information about the rank of\nthe input pair.\n\nThe RankLoss operator takes three inputs: Left (o_i), Right (o_j) and Label\n(P_{i,j}), which represent the output score of RankNet for the two docs and \nthe label respectively, and yields the rank loss C_{i,j} using the following \nequation:\n\n$$\n C_{i,j} = -\\tilde{P_{ij}} * o_{i,j} + \\log(1 + e^{o_{i,j}}) \\\\\n o_{i,j} = o_i - o_j \\\\\n \\tilde{P_{i,j}} = \\left \\{0, 0.5, 1 \\right \\} \\ or \\ \\left \\{0, 1 \\right \\}\n$$\n\nThe operator can take batch inputs with size batch_size (batch_size >= 1).\n\n",
"inputs" : [
{
"name" : "Label",
"comment" : "(2-D Tensor with shape [batch_size x 1]) The label indicating A ranked higher than B or not.",
"duplicable" : 0,
"intermediate" : 0
}, {
"name" : "Left",
"comment" : "(2-D Tensor with shape [batch_size x 1]) The output of RankNet for doc A.",
"duplicable" : 0,
"intermediate" : 0
}, {
"name" : "Right",
"comment" : "(2-D Tensor with shape [batch_size x 1]) The output of RankNet for doc B.",
"duplicable" : 0,
"intermediate" : 0
} ],
"outputs" : [
{
"name" : "Out",
"comment" : "(2-D Tensor with shape [batch_size x 1]) The output loss of RankLoss operator.",
"duplicable" : 0,
"intermediate" : 0
} ],
"attrs" : [ ]
},{
"type" : "reciprocal",
"comment" : "\nReciprocal Activation Operator.\n\n$$out = \\frac{1}{x}$$\n\n",
......@@ -2389,7 +2399,13 @@
"duplicable" : 0,
"intermediate" : 0
} ],
"attrs" : [ ]
"attrs" : [
{
"name" : "axis",
"type" : "int",
"comment" : "(int, default -1). The start dimension index for broadcasting Y onto X.",
"generated" : 0
} ]
},{
"type" : "sequence_pool",
"comment" : "\nSequence Pool Operator.\n\nThe SequencePoolOp pools features of all time-steps of each instance.\nIt supports six pooling types:\n1. AVERAGE: $$Out[i] = \\frac{\\sum_i X_i}{N}$$\n2. SUM: $$Out[i] = \\sum_jX_{ij}$$\n3. SQRT: $$Out[i] = \\frac{\\sum_jX_{ij}}{\\sqrt{len(X_i)}}$$\n4. LAST: Out[i] = last instance in i-th sequence X[i]\n5. FIRST: Out[i] = first instance in i-th sequence X[i]\n6. MAX: $$Out[i] = max(X_i)$$\n\nThe following example explains how this works:\nFor a mini-batch of 3 variable-length sentences,\ncontaining 2, 3, and 2 time-steps:\n\nAssume X is a [7,M,N] LoDTensor, and X->lod()[0] = [0, 2, 5, 7], 7=2+3+2.\nBesides, for the sake of simplicity, we assume M=1 and N=1,\nand the value of X = [[1, 3], [2, 4, 6], [5, 1]].\n\nThus, Out is a [3,1,1] Tensor without LoD infomation.\nAnd for different pooltype, the value of Out is as follows:\n\n- AVERAGE: [2, 4, 3], where 2=(1+3)/2, 4=(2+4+6)/3, 3=(5+1)/2\n- SUM: [4, 12, 6], where 4=1+3, 12=2+4+6, 6=5+1\n- SQRT: [2.82, 6.93, 4.24], where 2.82=(1+3)/sqrt(2),\n 6.93=(2+4+6)/sqrt(3), 4.24=(5+1)/sqrt(2)\n- MAX: [3, 6, 5], where 3=max(1,3), 6=max(2,4,6), 5=max(5,1)\n- LAST: [3, 6, 1], where 3=last(1,3), 6=last(2,4,6), 1=last(5,1)\n- FIRST: [1, 2, 5], where 1=first(1,3), 2=first(2,4,6), 5=first(5,1)\n\n ",
......@@ -3197,57 +3213,6 @@
"comment" : "Hyper parameter in huber loss.",
"generated" : 0
} ]
},{
"type" : "rank_loss",
"comment" : "\nRankLoss Operator.\n\nRankLoss operator for RankNet\n(http://icml.cc/2015/wp-content/uploads/2015/06/icml_ranking.pdf). \nRankNet is a pairwise ranking model with\none training sample consisting of a pair of doc A and B, and the label P\nindicating that A is ranked higher than B or not:\n\nP = {0, 1} or {0, 0.5, 1}, where 0.5 means no information about the rank of\nthe input pair.\n\nThe RankLoss operator takes three inputs: Left (o_i), Right (o_j) and Label\n(P_{i,j}), which represent the output score of RankNet for the two docs and \nthe label respectively, and yields the rank loss C_{i,j} using the following \nequation:\n\n$$\n C_{i,j} = -\\tilde{P_{ij}} * o_{i,j} + \\log(1 + e^{o_{i,j}}) \\\\\n o_{i,j} = o_i - o_j \\\\\n \\tilde{P_{i,j}} = \\left \\{0, 0.5, 1 \\right \\} \\ or \\ \\left \\{0, 1 \\right \\}\n$$\n\nThe operator can take batch inputs with size batch_size (batch_size >= 1).\n\n",
"inputs" : [
{
"name" : "Label",
"comment" : "(2-D Tensor with shape [batch_size x 1]) The label indicating A ranked higher than B or not.",
"duplicable" : 0,
"intermediate" : 0
}, {
"name" : "Left",
"comment" : "(2-D Tensor with shape [batch_size x 1]) The output of RankNet for doc A.",
"duplicable" : 0,
"intermediate" : 0
}, {
"name" : "Right",
"comment" : "(2-D Tensor with shape [batch_size x 1]) The output of RankNet for doc B.",
"duplicable" : 0,
"intermediate" : 0
} ],
"outputs" : [
{
"name" : "Out",
"comment" : "(2-D Tensor with shape [batch_size x 1]) The output loss of RankLoss operator.",
"duplicable" : 0,
"intermediate" : 0
} ],
"attrs" : [ ]
},{
"type" : "greater_than",
"comment" : "greater_than Operator\n\nIt operates element-wise on X and Y, and returns the Out. Each of them is a\nN-dim tensor. X and Y could be any type. The each element of the Out tensor is\ncalculated by Out = X > Y\n",
"inputs" : [
{
"name" : "X",
"comment" : "(LoDTensor) the left hand operand of greater_than operator",
"duplicable" : 0,
"intermediate" : 0
}, {
"name" : "Y",
"comment" : "(LoDTensor) the right hand operand of greater_than operator",
"duplicable" : 0,
"intermediate" : 0
} ],
"outputs" : [
{
"name" : "Out",
"comment" : "(LoDTensor) n-dim bool tensor. Each element is Out = X > Y",
"duplicable" : 0,
"intermediate" : 0
} ],
"attrs" : [ ]
},{
"type" : "sequence_softmax",
"comment" : "\nSequence Softmax Operator.\n\nSequenceSoftmaxOp computes the softmax activation among all time-steps for each\nsequence. The dimension of each time-step should be 1. Thus, the shape of\ninput Tensor can be either [N, 1] or [N], where N is the sum of the length\nof all sequences.\n\nThe algorithm works as follows:\n\n for i-th sequence in a mini-batch:\n\n$$\nOut(X[lod[i]:lod[i+1]], :) = \\\n\\frac{\\exp(X[lod[i]:lod[i+1], :])} \\\n{\\sum(\\exp(X[lod[i]:lod[i+1], :]))}\n$$\n\nFor example, for a mini-batch of 3 sequences with variable-length,\neach containing 2, 3, 2 time-steps, the lod of which is [0, 2, 5, 7],\nthen softmax will be computed among X[0:2, :], X[2:5, :], X[5:7, :]\nand N turns out to be 7.\n\n",
......@@ -4515,29 +4480,6 @@
"comment" : "(int) the specific lod level to split.",
"generated" : 0
} ]
},{
"type" : "greater_equal",
"comment" : "greater_equal Operator\n\nIt operates element-wise on X and Y, and returns the Out. Each of them is a\nN-dim tensor. X and Y could be any type. The each element of the Out tensor is\ncalculated by Out = X >= Y\n",
"inputs" : [
{
"name" : "X",
"comment" : "(LoDTensor) the left hand operand of greater_equal operator",
"duplicable" : 0,
"intermediate" : 0
}, {
"name" : "Y",
"comment" : "(LoDTensor) the right hand operand of greater_equal operator",
"duplicable" : 0,
"intermediate" : 0
} ],
"outputs" : [
{
"name" : "Out",
"comment" : "(LoDTensor) n-dim bool tensor. Each element is Out = X >= Y",
"duplicable" : 0,
"intermediate" : 0
} ],
"attrs" : [ ]
},{
"type" : "crop",
"comment" : "\nCrop Operator.\n\nCrop input into output, as specified by offsets and shape.\n\nThere are two ways to set shape:\n1. reference input: crop input X into the same shape as reference input.\n The dimension of reference input should\n be the same as the dimension of input X.\n2. shape list: crop input X into the shape described by a list<int>.\n The size of shape list should be the same as\n the dimension size of input X.\n\nThe input should be a k-D tensor(k > 0 and k < 7). As an example:\n\nCase 1:\nGiven\n\n X = [[0, 1, 2, 0, 0]\n [0, 3, 4, 0, 0]\n [0, 0, 0, 0, 0]],\n\nand\n\n offsets = [0, 1],\n\nand\n\n shape = [2, 2],\n\nwe get:\n\n Out = [[1, 2],\n [3, 4]].\n\n\nCase 2:\nGiven\n\n X = [[0, 1, 2, 5, 0]\n [0, 3, 4, 6, 0]\n [0, 0, 0, 0, 0]],\n\nand\n\n offsets = [0, 1],\n\nand\n\n Y = [[0, 0, 0]\n [0, 0, 0]],\n\nwe get:\n\n Out = [[1, 2, 5],\n [3, 4, 6]].\n",
......@@ -4750,7 +4692,13 @@
"duplicable" : 0,
"intermediate" : 0
} ],
"attrs" : [ ]
"attrs" : [
{
"name" : "axis",
"type" : "int",
"comment" : "(int, default -1). The start dimension index for broadcasting Y onto X.",
"generated" : 0
} ]
},{
"type" : "equal",
"comment" : "equal Operator\n\nIt operates element-wise on X and Y, and returns the Out. Each of them is a\nN-dim tensor. X and Y could be any type. The each element of the Out tensor is\ncalculated by Out = X == Y\n",
......@@ -4773,7 +4721,13 @@
"duplicable" : 0,
"intermediate" : 0
} ],
"attrs" : [ ]
"attrs" : [
{
"name" : "axis",
"type" : "int",
"comment" : "(int, default -1). The start dimension index for broadcasting Y onto X.",
"generated" : 0
} ]
},{
"type" : "gather",
"comment" : "\nGather Operator.\n\n$Out = X[Index]$\n\nOut is obtained by gathering entries of the outer-most dimension \nof X indexed by Index and concatenate them together.\n\nExample:\n\nX = [[1, 2],\n [3, 4],\n [5, 6]]\n\nIndex = [[1, 2]]\n\nThen:\n\nOut = [[3, 4],\n [5, 6]]\n\n",
......@@ -5359,6 +5313,24 @@
"comment" : "(float, default 1.0e-6) Constant for numerical stability",
"generated" : 0
} ]
},{
"type" : "log",
"comment" : "\nLog Activation Operator.\n\n$out = \\ln(x)$\n\nNatural logarithm of x.\n\n",
"inputs" : [
{
"name" : "X",
"comment" : "Input of Log operator",
"duplicable" : 0,
"intermediate" : 0
} ],
"outputs" : [
{
"name" : "Out",
"comment" : "Output of Log operator",
"duplicable" : 0,
"intermediate" : 0
} ],
"attrs" : [ ]
},{
"type" : "nce",
"comment" : "\nCompute and return the noise-contrastive estimation training loss.\nSee [Noise-contrastive estimation: A new estimation principle for unnormalized statistical models](http://www.jmlr.org/proceedings/papers/v9/gutmann10a/gutmann10a.pdf).\nBy default this operator uses a uniform distribution for sampling.\n",
......
develop/doc/py-modindex.html
浏览文件 @ aa798ba1
......@@ -229,11 +229,6 @@
<td>
<code class="xref">paddle</code></td><td>
<em></em></td></tr>
<tr class="cg-1">
<td></td>
<td>&#160;&#160;&#160;
<a href="api/v2/fluid/regularizer.html#module-paddle.v2.fluid.regularizer"><code class="xref">paddle.v2.fluid.regularizer</code></a></td><td>
<em></em></td></tr>
<tr class="cg-1">
<td></td>
<td>&#160;&#160;&#160;
......
develop/doc/searchindex.js
浏览文件 @ aa798ba1
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/fluid/evaluator.html
浏览文件 @ aa798ba1
......@@ -239,75 +239,6 @@
<h1>Evaluator<a class="headerlink" href="#evaluator" title="永久链接至标题"></a></h1>
<div class="section" id="id1">
<h2>Evaluator<a class="headerlink" href="#id1" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.evaluator.</code><code class="descname">Evaluator</code><span class="sig-paren">(</span><em>name</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Base Class for all evaluators</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple">
<li><strong>name</strong> (<em>str</em>) &#8211; The name of evaluator. such as, &#8220;accuracy&#8221;. Used for generate
temporary variable name.</li>
<li><strong>main_program</strong> (<em>Program</em><em>, </em><em>optional</em>) &#8211; The evaluator should be added to this
main_program. Default default_main_program()</li>
<li><strong>startup_program</strong> (<em>Program</em><em>, </em><em>optional</em>) &#8211; The parameter should be added to this
startup_program. Default default_startup_program()</li>
</ul>
</td>
</tr>
</tbody>
</table>
<dl class="attribute">
<dt id="paddle.v2.fluid.evaluator.Evaluator.states">
<code class="descname">states</code><a class="headerlink" href="#paddle.v2.fluid.evaluator.Evaluator.states" title="永久链接至目标"></a></dt>
<dd><p><em>list</em> &#8211; The list of state variables. states will be reset to zero
when <cite>reset</cite> is invoked.</p>
</dd></dl>
<dl class="attribute">
<dt id="paddle.v2.fluid.evaluator.Evaluator.metrics">
<code class="descname">metrics</code><a class="headerlink" href="#paddle.v2.fluid.evaluator.Evaluator.metrics" title="永久链接至目标"></a></dt>
<dd><p><em>list</em> &#8211; The list of metrics variables. They will be calculate
every mini-batch</p>
</dd></dl>
<dl class="method">
<dt>
<code class="descname">reset</code><span class="sig-paren">(</span><em>executor</em>, <em>reset_program=None</em><span class="sig-paren">)</span></dt>
<dd><p>reset metric states at the begin of each pass/user specified batch</p>
</dd></dl>
<dl class="method">
<dt>
<code class="descname">eval</code><span class="sig-paren">(</span><em>executor</em>, <em>eval_program=None</em><span class="sig-paren">)</span></dt>
<dd><p>Evaluate the statistics merged by multiple mini-batches.</p>
</dd></dl>
<dl class="method">
<dt>
<code class="descname">create_state</code><span class="sig-paren">(</span><em>suffix</em>, <em>dtype</em>, <em>shape</em><span class="sig-paren">)</span></dt>
<dd><p>Create state variable.</p>
<p>NOTE: It is not a public API.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple">
<li><strong>suffix</strong> (<em>str</em>) &#8211; the state suffix.</li>
<li><strong>dtype</strong> (<em>str|core.DataType</em>) &#8211; the state data type</li>
<li><strong>shape</strong> (<em>tuple|list</em>) &#8211; the shape of state</li>
</ul>
</td>
</tr>
</tbody>
</table>
<p>Returns: State variable</p>
</dd></dl>
</dd></dl>
</div>
</div>
......
develop/doc_cn/api/v2/fluid/initializer.html
浏览文件 @ aa798ba1
......@@ -239,90 +239,21 @@
<h1>Initializer<a class="headerlink" href="#initializer" title="永久链接至标题"></a></h1>
<div class="section" id="id1">
<h2>Initializer<a class="headerlink" href="#id1" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">Initializer</code></dt>
<dd><p>Base class for variable initializers</p>
<p>Defines the common interface of variable initializers.
They add operations to the init program that are used
to initialize variables. Users should not use this class
directly, but need to use one of its implementations.</p>
</dd></dl>
</div>
<div class="section" id="constantinitializer">
<h2>ConstantInitializer<a class="headerlink" href="#constantinitializer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">ConstantInitializer</code><span class="sig-paren">(</span><em>value=0.0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the constant initializer</p>
</dd></dl>
</div>
<div class="section" id="uniforminitializer">
<h2>UniformInitializer<a class="headerlink" href="#uniforminitializer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">UniformInitializer</code><span class="sig-paren">(</span><em>low=-1.0</em>, <em>high=1.0</em>, <em>seed=0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the random uniform distribution initializer</p>
</dd></dl>
</div>
<div class="section" id="normalinitializer">
<h2>NormalInitializer<a class="headerlink" href="#normalinitializer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">NormalInitializer</code><span class="sig-paren">(</span><em>loc=0.0</em>, <em>scale=1.0</em>, <em>seed=0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the random Normal(Gaussian) distribution initializer</p>
</dd></dl>
</div>
<div class="section" id="xavierinitializer">
<h2>XavierInitializer<a class="headerlink" href="#xavierinitializer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">XavierInitializer</code><span class="sig-paren">(</span><em>uniform=True</em>, <em>fan_in=None</em>, <em>fan_out=None</em>, <em>seed=0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the Xavier initializer</p>
<p>This class implements the Xavier weight initializer from the paper
Understanding the difficulty of training deep feedforward neural
networks[1] by Xavier Glorot and Yoshua Bengio.</p>
<p>This initializer is designed to keep the scale of the gradients
approximately same in all the layers. In case of Uniform distribution,
the range is [-x, x], where x = sqrt(6 / (fan_in + fan_out)).
In case of Normal distribution, the mean is 0 and the standard deviation
is sqrt(2/ (fan_in + fan_out)).</p>
<p class="rubric">References</p>
<dl class="docutils">
<dt>[1] Understanding the difficulty of training deep feedforward neural</dt>
<dd>networks. International conference on artificial intelligence and
statistics.
(<a class="reference external" href="http://proceedings.mlr.press/v9/glorot10a.html">http://proceedings.mlr.press/v9/glorot10a.html</a>)</dd>
</dl>
</dd></dl>
</div>
<div class="section" id="msrainitializer">
<h2>MSRAInitializer<a class="headerlink" href="#msrainitializer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.initializer.</code><code class="descname">MSRAInitializer</code><span class="sig-paren">(</span><em>uniform=True</em>, <em>fan_in=None</em>, <em>seed=0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the MSRA initializer a.k.a. Kaiming Initializer</p>
<p>This class implements the weight initialization from the paper
Delving Deep into Rectifiers: Surpassing Human-Level Performance on
ImageNet Classification[1] by Kaiming He, Xiangyu Zhang, Shaoqing Ren
and Jian Sun. This is a robust initialization method that particularly
considers the rectifier nonlinearities. In case of Uniform distribution,
the range is [-x, x], where x = sqrt(6 / fan_in). In case of Normal
distribution, the mean is 0 and the standard deviation
is sqrt(2/ fan_in).</p>
<p class="rubric">References</p>
<dl class="docutils">
<dt>[1] Delving Deep into Rectifiers: Surpassing Human-Level Performance</dt>
<dd>on ImageNet Classification
(<a class="reference external" href="https://arxiv.org/abs/1502.01852">https://arxiv.org/abs/1502.01852</a>)</dd>
</dl>
</dd></dl>
</div>
</div>
......
develop/doc_cn/api/v2/fluid/io.html
浏览文件 @ aa798ba1
......@@ -239,23 +239,6 @@
<h1>IO<a class="headerlink" href="#io" title="永久链接至标题"></a></h1>
<div class="section" id="is-parameter">
<h2>is_parameter<a class="headerlink" href="#is-parameter" title="永久链接至标题"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.io.</code><code class="descname">is_parameter</code><span class="sig-paren">(</span><em>var</em><span class="sig-paren">)</span></dt>
<dd><p>Check whether the variable is a Parameter.</p>
<p>This function checks whether the input variable is a Parameter.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><strong>var</strong> &#8211; The input variable.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body">boolean result whether the variable is a Parameter.</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
</div>
......
develop/doc_cn/api/v2/fluid/layers.html
浏览文件 @ aa798ba1
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/fluid/nets.html
浏览文件 @ aa798ba1
......@@ -239,118 +239,18 @@
<h1>Nets<a class="headerlink" href="#nets" title="永久链接至标题"></a></h1>
<div class="section" id="simple-img-conv-pool">
<h2>simple_img_conv_pool<a class="headerlink" href="#simple-img-conv-pool" title="永久链接至标题"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">simple_img_conv_pool</code><span class="sig-paren">(</span><em>input</em>, <em>num_filters</em>, <em>filter_size</em>, <em>pool_size</em>, <em>pool_stride</em>, <em>act</em>, <em>param_attr=None</em>, <em>pool_type='max'</em>, <em>use_cudnn=True</em><span class="sig-paren">)</span></dt>
<dd></dd></dl>
</div>
<div class="section" id="img-conv-group">
<h2>img_conv_group<a class="headerlink" href="#img-conv-group" title="永久链接至标题"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">img_conv_group</code><span class="sig-paren">(</span><em>input</em>, <em>conv_num_filter</em>, <em>pool_size</em>, <em>conv_padding=1</em>, <em>conv_filter_size=3</em>, <em>conv_act=None</em>, <em>param_attr=None</em>, <em>conv_with_batchnorm=False</em>, <em>conv_batchnorm_drop_rate=None</em>, <em>pool_stride=1</em>, <em>pool_type=None</em>, <em>use_cudnn=True</em><span class="sig-paren">)</span></dt>
<dd><p>Image Convolution Group, Used for vgg net.</p>
</dd></dl>
</div>
<div class="section" id="sequence-conv-pool">
<h2>sequence_conv_pool<a class="headerlink" href="#sequence-conv-pool" title="永久链接至标题"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">sequence_conv_pool</code><span class="sig-paren">(</span><em>input</em>, <em>num_filters</em>, <em>filter_size</em>, <em>param_attr=None</em>, <em>act='sigmoid'</em>, <em>pool_type='max'</em><span class="sig-paren">)</span></dt>
<dd></dd></dl>
</div>
<div class="section" id="glu">
<h2>glu<a class="headerlink" href="#glu" title="永久链接至标题"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">glu</code><span class="sig-paren">(</span><em>input</em>, <em>dim=-1</em><span class="sig-paren">)</span></dt>
<dd><p>The gated linear unit composed by split, sigmoid activation and elementwise
multiplication. Specifically, Split the input into two equal sized parts
<span class="math">\(a\)</span> and <span class="math">\(b\)</span> along the given dimension and then compute as
following:</p>
<blockquote>
<div><div class="math">
\[{GLU}(a, b)= a \otimes \sigma(b)\]</div>
</div></blockquote>
<p>Refer to <a class="reference external" href="https://arxiv.org/pdf/1612.08083.pdf">Language Modeling with Gated Convolutional Networks</a>.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>input</strong> (<em>Variable</em>) &#8211; The input variable which is a Tensor or LoDTensor.</li>
<li><strong>dim</strong> (<em>int</em>) &#8211; The dimension along which to split. If <span class="math">\(dim &lt; 0\)</span>, the
dimension to split along is <span class="math">\(rank(input) + dim\)</span>.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">The Tensor variable with half the size of input.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">Variable</p>
</td>
</tr>
</tbody>
</table>
<p class="rubric">Examples</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="c1"># x is a Tensor variable with shape [3, 6, 9]</span>
<span class="n">fluid</span><span class="o">.</span><span class="n">nets</span><span class="o">.</span><span class="n">glu</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">x</span><span class="p">,</span> <span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> <span class="c1"># shape of output: [3, 3, 9]</span>
</pre></div>
</div>
</dd></dl>
</div>
<div class="section" id="dot-product-attention">
<h2>dot_product_attention<a class="headerlink" href="#dot-product-attention" title="永久链接至标题"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.nets.</code><code class="descname">dot_product_attention</code><span class="sig-paren">(</span><em>querys</em>, <em>keys</em>, <em>values</em><span class="sig-paren">)</span></dt>
<dd><p>The dot-product attention.</p>
<p>Attention mechanism can be seen as mapping a query and a set of key-value
pairs to an output. The output is computed as a weighted sum of the values,
where the weight assigned to each value is computed by a compatibility
function (dot-product here) of the query with the corresponding key.</p>
<p>The dot-product attention can be implemented through (batch) matrix
multipication as follows:</p>
<blockquote>
<div><div class="math">
\[Attention(Q, K, V)= softmax(QK^\mathrm{T})V\]</div>
</div></blockquote>
<p>Refer to <a class="reference external" href="https://arxiv.org/pdf/1706.03762.pdf">Attention Is All You Need</a>.</p>
<p>Note that batch data containing sequences with different lengths is not
supported by this because of the (batch) matrix multipication.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>query</strong> (<em>Variable</em>) &#8211; The input variable which is a Tensor or LoDTensor.</li>
<li><strong>key</strong> (<em>Variable</em>) &#8211; The input variable which is a Tensor or LoDTensor.</li>
<li><strong>value</strong> (<em>Variable</em>) &#8211; The input variable which is a Tensor or LoDTensor.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">The Tensor variables representing the output and attention scores.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">tuple</p>
</td>
</tr>
</tbody>
</table>
<p class="rubric">Examples</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="c1"># Suppose q, k, v are tensor variables with the following shape:</span>
<span class="c1"># q: [3, 5, 9], k: [3, 6, 9], v: [3, 6, 10]</span>
<span class="n">out</span><span class="p">,</span> <span class="n">attn_scores</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">nets</span><span class="o">.</span><span class="n">dot_product_attention</span><span class="p">(</span><span class="n">q</span><span class="p">,</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span>
<span class="n">out</span><span class="o">.</span><span class="n">shape</span> <span class="c1"># [3, 5, 10]</span>
<span class="n">attn_scores</span><span class="o">.</span><span class="n">shape</span> <span class="c1"># [3, 5, 6]</span>
</pre></div>
</div>
</dd></dl>
</div>
</div>
......
develop/doc_cn/api/v2/fluid/optimizer.html
浏览文件 @ aa798ba1
......@@ -239,105 +239,24 @@
<h1>Optimizer<a class="headerlink" href="#optimizer" title="永久链接至标题"></a></h1>
<div class="section" id="id1">
<h2>Optimizer<a class="headerlink" href="#id1" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">Optimizer</code><span class="sig-paren">(</span><em>global_step=None</em>, <em>regularization=None</em><span class="sig-paren">)</span></dt>
<dd><p>Optimizer Base class.</p>
<p>Define the common interface of an optimizer.
User should not use this class directly,
but need to use one of it&#8217;s implementation.</p>
<dl class="method">
<dt>
<code class="descname">create_optimization_pass</code><span class="sig-paren">(</span><em>parameters_and_grads</em>, <em>loss</em>, <em>startup_program=None</em><span class="sig-paren">)</span></dt>
<dd><p>Add optimization operators to update gradients to variables.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>loss</strong> &#8211; the target that this optimization is for.</li>
<li><strong>parameters_and_grads</strong> &#8211; a list of (variable, gradient) pair to update.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">a list of operators that will complete one step of
optimization. This will include parameter update ops, global step
update ops and any other custom ops required by subclasses to manage
their internal state.
:param startup_program:</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">return_op_list</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="method">
<dt>
<code class="descname">minimize</code><span class="sig-paren">(</span><em>loss</em>, <em>startup_program=None</em>, <em>parameter_list=None</em>, <em>no_grad_set=None</em><span class="sig-paren">)</span></dt>
<dd><p>Add operations to minimize <cite>loss</cite> by updating <cite>parameter_list</cite>.</p>
<p>This method combines interface <cite>append_backward()</cite> and
<cite>create_optimization_pass()</cite> into one.</p>
</dd></dl>
</dd></dl>
</div>
<div class="section" id="sgdoptimizer">
<h2>SGDOptimizer<a class="headerlink" href="#sgdoptimizer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">SGDOptimizer</code><span class="sig-paren">(</span><em>learning_rate</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Simple SGD optimizer without any state.</p>
</dd></dl>
</div>
<div class="section" id="momentumoptimizer">
<h2>MomentumOptimizer<a class="headerlink" href="#momentumoptimizer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">MomentumOptimizer</code><span class="sig-paren">(</span><em>learning_rate</em>, <em>momentum</em>, <em>use_nesterov=False</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Simple Momentum optimizer with velocity state</p>
</dd></dl>
</div>
<div class="section" id="adagradoptimizer">
<h2>AdagradOptimizer<a class="headerlink" href="#adagradoptimizer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">AdagradOptimizer</code><span class="sig-paren">(</span><em>learning_rate</em>, <em>epsilon=1e-06</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Simple Adagrad optimizer with moment state</p>
</dd></dl>
</div>
<div class="section" id="adamoptimizer">
<h2>AdamOptimizer<a class="headerlink" href="#adamoptimizer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">AdamOptimizer</code><span class="sig-paren">(</span><em>learning_rate=0.001</em>, <em>beta1=0.9</em>, <em>beta2=0.999</em>, <em>epsilon=1e-08</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the Adam Optimizer</p>
</dd></dl>
</div>
<div class="section" id="adamaxoptimizer">
<h2>AdamaxOptimizer<a class="headerlink" href="#adamaxoptimizer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">AdamaxOptimizer</code><span class="sig-paren">(</span><em>learning_rate=0.001</em>, <em>beta1=0.9</em>, <em>beta2=0.999</em>, <em>epsilon=1e-08</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the Adamax Optimizer</p>
</dd></dl>
</div>
<div class="section" id="decayedadagradoptimizer">
<h2>DecayedAdagradOptimizer<a class="headerlink" href="#decayedadagradoptimizer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.optimizer.</code><code class="descname">DecayedAdagradOptimizer</code><span class="sig-paren">(</span><em>learning_rate</em>, <em>decay=0.95</em>, <em>epsilon=1e-06</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Simple Decayed Adagrad optimizer with moment state</p>
</dd></dl>
</div>
</div>
......
develop/doc_cn/api/v2/fluid/profiler.html
浏览文件 @ aa798ba1
......@@ -239,35 +239,6 @@
<h1>Profiler<a class="headerlink" href="#profiler" title="永久链接至标题"></a></h1>
<div class="section" id="id1">
<h2>Profiler<a class="headerlink" href="#id1" title="永久链接至标题"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.profiler.</code><code class="descname">cuda_profiler</code><span class="sig-paren">(</span><em>*args</em>, <em>**kwds</em><span class="sig-paren">)</span></dt>
<dd><p>The CUDA profiler.
This fuctions is used to profile CUDA program by CUDA runtime application
programming interface. The profiling result will be written into
<cite>output_file</cite> with Key-Value pair format or Comma separated values format.
The user can set the output mode by <cite>output_mode</cite> argument and set the
counters/options for profiling by <cite>config</cite> argument. The default config
is [&#8216;gpustarttimestamp&#8217;, &#8216;gpustarttimestamp&#8217;, &#8216;gridsize3d&#8217;,
&#8216;threadblocksize&#8217;, &#8216;streamid&#8217;, &#8216;enableonstart 0&#8217;, &#8216;conckerneltrace&#8217;].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple">
<li><strong>output_file</strong> (<em>string</em>) &#8211; The output file name, the result will be
written into this file.</li>
<li><strong>output_mode</strong> (<em>string</em>) &#8211; The output mode has Key-Value pair format and
Comma separated values format. It should be &#8216;kvp&#8217; or &#8216;csv&#8217;.</li>
<li><strong>config</strong> (<em>list of string</em>) &#8211; The profiler options and counters can refer
to &#8220;Compute Command Line Profiler User Guide&#8221;.</li>
</ul>
</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
</div>
......
develop/doc_cn/api/v2/fluid/regularizer.html
浏览文件 @ aa798ba1
......@@ -239,36 +239,12 @@
<h1>Regularizer<a class="headerlink" href="#regularizer" title="永久链接至标题"></a></h1>
<div class="section" id="weightdecayregularizer">
<h2>WeightDecayRegularizer<a class="headerlink" href="#weightdecayregularizer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.regularizer.</code><code class="descname">WeightDecayRegularizer</code></dt>
<dd><p>Base class for weight decay regularizers</p>
<p>Defines the common interface of weight-decay regularizers.
Weight-decay regularizers are added only during the backward
pass for faster regularization. They add operations to the network
that correspond to gradient of the regularization function.
Users should not use this class directly, but need to use one
of its implementations</p>
</dd></dl>
</div>
<div class="section" id="l2decayregularizer">
<h2>L2DecayRegularizer<a class="headerlink" href="#l2decayregularizer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.regularizer.</code><code class="descname">L2DecayRegularizer</code><span class="sig-paren">(</span><em>regularization_coeff=0.0</em><span class="sig-paren">)</span></dt>
<dd><p>Implements the L2 Weight Decay Regularization</p>
</dd></dl>
</div>
<div class="section" id="module-paddle.v2.fluid.regularizer">
<span id="l1decayregularizer"></span><h2>L1DecayRegularizer<a class="headerlink" href="#module-paddle.v2.fluid.regularizer" title="永久链接至标题"></a></h2>
<dl class="class">
<dt id="paddle.v2.fluid.regularizer.L1DecayRegularizer">
<em class="property">class </em><code class="descclassname">paddle.v2.fluid.regularizer.</code><code class="descname">L1DecayRegularizer</code><span class="sig-paren">(</span><em>regularization_coeff=0.0</em><span class="sig-paren">)</span><a class="headerlink" href="#paddle.v2.fluid.regularizer.L1DecayRegularizer" title="永久链接至目标"></a></dt>
<dd><p>Implements the L1 Weight Decay Regularization</p>
</dd></dl>
<div class="section" id="l1decayregularizer">
<h2>L1DecayRegularizer<a class="headerlink" href="#l1decayregularizer" title="永久链接至标题"></a></h2>
</div>
</div>
......
develop/doc_cn/genindex.html
浏览文件 @ aa798ba1
......@@ -236,7 +236,6 @@
<a href="#B"><strong>B</strong></a>
| <a href="#C"><strong>C</strong></a>
| <a href="#L"><strong>L</strong></a>
| <a href="#M"><strong>M</strong></a>
| <a href="#P"><strong>P</strong></a>
| <a href="#R"><strong>R</strong></a>
| <a href="#S"><strong>S</strong></a>
......@@ -262,14 +261,12 @@
<h2 id="L">L</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/fluid/regularizer.html#paddle.v2.fluid.regularizer.L1DecayRegularizer">L1DecayRegularizer (paddle.v2.fluid.regularizer 中的类)</a>
</li>
<li><a href="api/v2/data/image.html#paddle.v2.image.left_right_flip">left_right_flip() (在 paddle.v2.image 模块中)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/data/image.html#paddle.v2.image.load_and_transform">load_and_transform() (在 paddle.v2.image 模块中)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/data/image.html#paddle.v2.image.load_image">load_image() (在 paddle.v2.image 模块中)</a>
</li>
<li><a href="api/v2/data/image.html#paddle.v2.image.load_image_bytes">load_image_bytes() (在 paddle.v2.image 模块中)</a>
......@@ -277,20 +274,8 @@
</ul></td>
</tr></table>
<h2 id="M">M</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/fluid/evaluator.html#paddle.v2.fluid.evaluator.Evaluator.metrics">metrics (paddle.v2.fluid.evaluator.Evaluator 属性)</a>
</li>
</ul></td>
</tr></table>
<h2 id="P">P</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/fluid/regularizer.html#module-paddle.v2.fluid.regularizer">paddle.v2.fluid.regularizer (模块)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/data/image.html#module-paddle.v2.image">paddle.v2.image (模块)</a>
</li>
......@@ -313,10 +298,6 @@
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/data/image.html#paddle.v2.image.simple_transform">simple_transform() (在 paddle.v2.image 模块中)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="api/v2/fluid/evaluator.html#paddle.v2.fluid.evaluator.Evaluator.states">states (paddle.v2.fluid.evaluator.Evaluator 属性)</a>
</li>
</ul></td>
</tr></table>
......
develop/doc_cn/py-modindex.html
浏览文件 @ aa798ba1
......@@ -248,11 +248,6 @@
<td>
<code class="xref">paddle</code></td><td>
<em></em></td></tr>
<tr class="cg-1">
<td></td>
<td>&#160;&#160;&#160;
<a href="api/v2/fluid/regularizer.html#module-paddle.v2.fluid.regularizer"><code class="xref">paddle.v2.fluid.regularizer</code></a></td><td>
<em></em></td></tr>
<tr class="cg-1">
<td></td>
<td>&#160;&#160;&#160;
......
develop/doc_cn/searchindex.js
浏览文件 @ aa798ba1
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