Skip to content

P
Paddle

PaddlePaddle / Paddle
大约 1 年 前同步成功

通知 2299
Star 20931
Fork 5422
P
Paddle
提交 b056a6bd 编写于 作者: T Travis CI
浏览文件
操作

Deploy to GitHub Pages: 9536c4e3

上级 7b6b20c7
展开全部 隐藏空白更改
内联 并排
Showing with 220 addition and 2 deletion
develop/doc/_sources/api/v2/fluid/layers.rst.txt
浏览文件 @ b056a6bd
...@@ -505,6 +505,11 @@ swish ...@@ -505,6 +505,11 @@ swish
.. autofunction:: paddle.v2.fluid.layers.swish .. autofunction:: paddle.v2.fluid.layers.swish
:noindex: :noindex:
im2sequence
------
.. autofunction:: paddle.v2.fluid.layers.im2sequence
:noindex:
edit_distance edit_distance
--------------- ---------------
.. autofunction:: paddle.v2.fluid.layers.edit_distance_error .. autofunction:: paddle.v2.fluid.layers.edit_distance_error
......
develop/doc/api/v2/fluid/layers.html
浏览文件 @ b056a6bd
...@@ -3388,6 +3388,110 @@ Duplicable: False Optional: False</li> ...@@ -3388,6 +3388,110 @@ Duplicable: False Optional: False</li>
</table> </table>
</dd></dl> </dd></dl>
</div>
<div class="section" id="im2sequence">
<h2>im2sequence<a class="headerlink" href="#im2sequence" title="Permalink to this headline"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.layers.</code><code class="descname">im2sequence</code><span class="sig-paren">(</span><em>input</em>, <em>filter_size=1</em>, <em>stride=1</em>, <em>padding=0</em>, <em>name=None</em><span class="sig-paren">)</span></dt>
<dd><p>Extracts image patches from the input tensor to form a tensor of shape
{input.batch_size * output_height * output_width, filter_size_H *
filter_size_W * input.channels} which is similar with im2col.
This op use filter / kernel to scan images and convert these images to
sequences. After expanding, the number of time step are
output_height * output_width for an image, in which output_height and
output_width are calculated by below equation:</p>
<div class="math">
\[output\_size = 1 + (2 * padding + img\_size - block\_size + stride - 1) / stride\]</div>
<p>And the dimension of each time step is block_y * block_x * input.channels.</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 should be a tensor in NCHW format.</li>
<li><strong>filter_size</strong> (<em>int|tuple|None</em>) &#8211; The filter size. If filter_size is a tuple,
it must contain two integers, (filter_size_H, filter_size_W).
Otherwise, the filter will be a square.</li>
<li><strong>stride</strong> (<em>int|tuple</em>) &#8211; The stride size. If stride is a tuple, it must
contain two integers, (stride_H, stride_W). Otherwise, the
stride_H = stride_W = stride. Default: stride = 1.</li>
<li><strong>padding</strong> (<em>int|tuple</em>) &#8211; The padding size. If padding is a tuple, it can
contain two integers like (padding_H, padding_W) which means
padding_up = padding_down = padding_H and
padding_left = padding_right = padding_W. Or it can use
(padding_up, padding_left, padding_down, padding_right) to indicate
paddings of four direction. Otherwise, a scalar padding means
padding_up = padding_down = padding_left = padding_right = padding
Default: padding = 0.</li>
<li><strong>name</strong> (<em>int</em>) &#8211; The name of this layer. It is optional.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">The output is a LoDTensor with shape
{input.batch_size * output_height * output_width,
filter_size_H * filter_size_W * input.channels}.
If we regard output as a matrix, each row of this matrix is
a step of a sequence.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">output</p>
</td>
</tr>
</tbody>
</table>
<p>Examples:</p>
<p>As an example:</p>
<blockquote>
<div><div class="highlight-text"><div class="highlight"><pre><span></span>Given:
x = [[[[ 6. 2. 1.]
[ 8. 3. 5.]
[ 0. 2. 6.]]
[[ 2. 4. 4.]
[ 6. 3. 0.]
[ 6. 4. 7.]]]
[[[ 6. 7. 1.]
[ 5. 7. 9.]
[ 2. 4. 8.]]
[[ 1. 2. 1.]
[ 1. 3. 5.]
[ 9. 0. 8.]]]]
x.dims = {2, 2, 3, 3}
And:
filter = [2, 2]
stride = [1, 1]
padding = [0, 0]
Then:
output.data = [[ 6. 2. 8. 3. 2. 4. 6. 3.]
[ 2. 1. 3. 5. 4. 4. 3. 0.]
[ 8. 3. 0. 2. 6. 3. 6. 4.]
[ 3. 5. 2. 6. 3. 0. 4. 7.]
[ 6. 7. 5. 7. 1. 2. 1. 3.]
[ 7. 1. 7. 9. 2. 1. 3. 5.]
[ 5. 7. 2. 4. 1. 3. 9. 0.]
[ 7. 9. 4. 8. 3. 5. 0. 8.]]
output.dims = {8, 9}
output.lod = [[0, 4, 8]]
</pre></div>
</div>
<p>The simple usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">output</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">im2sequence</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">filter_size</span><span class="o">=</span><span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">])</span>
</pre></div>
</div>
</div></blockquote>
</dd></dl>
</div> </div>
<div class="section" id="edit-distance"> <div class="section" id="edit-distance">
<h2>edit_distance<a class="headerlink" href="#edit-distance" title="Permalink to this headline"></a></h2> <h2>edit_distance<a class="headerlink" href="#edit-distance" title="Permalink to this headline"></a></h2>
......
develop/doc/searchindex.js
浏览文件 @ b056a6bd
因为 它太大了无法显示 source diff 。你可以改为 查看blob。
develop/doc_cn/_sources/api/v2/fluid/layers.rst.txt
浏览文件 @ b056a6bd
...@@ -505,6 +505,11 @@ swish ...@@ -505,6 +505,11 @@ swish
.. autofunction:: paddle.v2.fluid.layers.swish .. autofunction:: paddle.v2.fluid.layers.swish
:noindex: :noindex:
im2sequence
------
.. autofunction:: paddle.v2.fluid.layers.im2sequence
:noindex:
edit_distance edit_distance
--------------- ---------------
.. autofunction:: paddle.v2.fluid.layers.edit_distance_error .. autofunction:: paddle.v2.fluid.layers.edit_distance_error
......
develop/doc_cn/api/v2/fluid/layers.html
浏览文件 @ b056a6bd
...@@ -3407,6 +3407,110 @@ Duplicable: False Optional: False</li> ...@@ -3407,6 +3407,110 @@ Duplicable: False Optional: False</li>
</table> </table>
</dd></dl> </dd></dl>
</div>
<div class="section" id="im2sequence">
<h2>im2sequence<a class="headerlink" href="#im2sequence" title="永久链接至标题"></a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.fluid.layers.</code><code class="descname">im2sequence</code><span class="sig-paren">(</span><em>input</em>, <em>filter_size=1</em>, <em>stride=1</em>, <em>padding=0</em>, <em>name=None</em><span class="sig-paren">)</span></dt>
<dd><p>Extracts image patches from the input tensor to form a tensor of shape
{input.batch_size * output_height * output_width, filter_size_H *
filter_size_W * input.channels} which is similar with im2col.
This op use filter / kernel to scan images and convert these images to
sequences. After expanding, the number of time step are
output_height * output_width for an image, in which output_height and
output_width are calculated by below equation:</p>
<div class="math">
\[output\_size = 1 + (2 * padding + img\_size - block\_size + stride - 1) / stride\]</div>
<p>And the dimension of each time step is block_y * block_x * input.channels.</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 should be a tensor in NCHW format.</li>
<li><strong>filter_size</strong> (<em>int|tuple|None</em>) &#8211; The filter size. If filter_size is a tuple,
it must contain two integers, (filter_size_H, filter_size_W).
Otherwise, the filter will be a square.</li>
<li><strong>stride</strong> (<em>int|tuple</em>) &#8211; The stride size. If stride is a tuple, it must
contain two integers, (stride_H, stride_W). Otherwise, the
stride_H = stride_W = stride. Default: stride = 1.</li>
<li><strong>padding</strong> (<em>int|tuple</em>) &#8211; The padding size. If padding is a tuple, it can
contain two integers like (padding_H, padding_W) which means
padding_up = padding_down = padding_H and
padding_left = padding_right = padding_W. Or it can use
(padding_up, padding_left, padding_down, padding_right) to indicate
paddings of four direction. Otherwise, a scalar padding means
padding_up = padding_down = padding_left = padding_right = padding
Default: padding = 0.</li>
<li><strong>name</strong> (<em>int</em>) &#8211; The name of this layer. It is optional.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">The output is a LoDTensor with shape
{input.batch_size * output_height * output_width,
filter_size_H * filter_size_W * input.channels}.
If we regard output as a matrix, each row of this matrix is
a step of a sequence.</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">output</p>
</td>
</tr>
</tbody>
</table>
<p>Examples:</p>
<p>As an example:</p>
<blockquote>
<div><div class="highlight-text"><div class="highlight"><pre><span></span>Given:
x = [[[[ 6. 2. 1.]
[ 8. 3. 5.]
[ 0. 2. 6.]]
[[ 2. 4. 4.]
[ 6. 3. 0.]
[ 6. 4. 7.]]]
[[[ 6. 7. 1.]
[ 5. 7. 9.]
[ 2. 4. 8.]]
[[ 1. 2. 1.]
[ 1. 3. 5.]
[ 9. 0. 8.]]]]
x.dims = {2, 2, 3, 3}
And:
filter = [2, 2]
stride = [1, 1]
padding = [0, 0]
Then:
output.data = [[ 6. 2. 8. 3. 2. 4. 6. 3.]
[ 2. 1. 3. 5. 4. 4. 3. 0.]
[ 8. 3. 0. 2. 6. 3. 6. 4.]
[ 3. 5. 2. 6. 3. 0. 4. 7.]
[ 6. 7. 5. 7. 1. 2. 1. 3.]
[ 7. 1. 7. 9. 2. 1. 3. 5.]
[ 5. 7. 2. 4. 1. 3. 9. 0.]
[ 7. 9. 4. 8. 3. 5. 0. 8.]]
output.dims = {8, 9}
output.lod = [[0, 4, 8]]
</pre></div>
</div>
<p>The simple usage is:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">output</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">im2sequence</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">layer</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">filter_size</span><span class="o">=</span><span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">])</span>
</pre></div>
</div>
</div></blockquote>
</dd></dl>
</div> </div>
<div class="section" id="edit-distance"> <div class="section" id="edit-distance">
<h2>edit_distance<a class="headerlink" href="#edit-distance" title="永久链接至标题"></a></h2> <h2>edit_distance<a class="headerlink" href="#edit-distance" title="永久链接至标题"></a></h2>
......
develop/doc_cn/searchindex.js
浏览文件 @ b056a6bd
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