Skip to content

M
models

PaddlePaddle / models
大约 1 年 前同步成功

通知 222
Star 6828
Fork 2962
M
models
未验证 提交 511476b0 编写于 作者: J Jacob Deng 提交者： GitHub
浏览文件
操作

Merge pull request #2 from denglelaibh/denglelaibh 

Realization of DRN 2016 (also similar to resNet 16)
上级 9d2e3ea7 fb1fa886
隐藏空白更改
内联 并排
Showing with 1030 addition and 1 deletion
drn/.idea/drn.iml 0 → 100644
浏览文件 @ 511476b0
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="inheritedJdk" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
<component name="TestRunnerService">
<option name="projectConfiguration" value="Nosetests" />
<option name="PROJECT_TEST_RUNNER" value="Nosetests" />
</component>
</module>
\ No newline at end of file
drn/.idea/misc.xml 0 → 100644
浏览文件 @ 511476b0
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectRootManager" version="2" project-jdk-name="Python 2.7.13 (C:\Users\67938\Anaconda2\python.exe)" project-jdk-type="Python SDK" />
</project>
\ No newline at end of file
drn/.idea/modules.xml 0 → 100644
浏览文件 @ 511476b0
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/drn.iml" filepath="$PROJECT_DIR$/.idea/drn.iml" />
</modules>
</component>
</project>
\ No newline at end of file
drn/.idea/workspace.xml 0 → 100644
浏览文件 @ 511476b0
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ChangeListManager">
<list default="true" id="8f4afb84-b4d6-47c4-8f67-a6e0810616b4" name="Default" comment="" />
<option name="EXCLUDED_CONVERTED_TO_IGNORED" value="true" />
<option name="TRACKING_ENABLED" value="true" />
<option name="SHOW_DIALOG" value="false" />
<option name="HIGHLIGHT_CONFLICTS" value="true" />
<option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
<option name="LAST_RESOLUTION" value="IGNORE" />
</component>
<component name="ExecutionTargetManager" SELECTED_TARGET="default_target" />
<component name="FileEditorManager">
<leaf SIDE_TABS_SIZE_LIMIT_KEY="300">
<file leaf-file-name="train.py" pinned="false" current-in-tab="false">
<entry file="file://$PROJECT_DIR$/train.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="1349">
<caret line="71" column="29" lean-forward="true" selection-start-line="71" selection-start-column="29" selection-end-line="75" selection-end-column="44" />
<folding>
<element signature="e#0#11#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
</file>
<file leaf-file-name="infer.py" pinned="false" current-in-tab="false">
<entry file="file://$PROJECT_DIR$/infer.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="266">
<caret line="26" column="10" lean-forward="false" selection-start-line="26" selection-start-column="10" selection-end-line="26" selection-end-column="10" />
<folding>
<element signature="e#0#9#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
</file>
<file leaf-file-name="drn.py" pinned="false" current-in-tab="true">
<entry file="file://$PROJECT_DIR$/drn.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="34">
<caret line="30" column="0" lean-forward="true" selection-start-line="30" selection-start-column="0" selection-end-line="30" selection-end-column="0" />
<folding />
</state>
</provider>
</entry>
</file>
</leaf>
</component>
<component name="FileTemplateManagerImpl">
<option name="RECENT_TEMPLATES">
<list>
<option value="Python Script" />
</list>
</option>
</component>
<component name="FindInProjectRecents">
<findStrings>
<find>lower</find>
<find>reader</find>
</findStrings>
</component>
<component name="IdeDocumentHistory">
<option name="CHANGED_PATHS">
<list>
<option value="$PROJECT_DIR$/utils.py" />
<option value="$PROJECT_DIR$/network_conf.py" />
<option value="$PROJECT_DIR$/new.py" />
<option value="$PROJECT_DIR$/infer.py" />
<option value="$PROJECT_DIR$/train.py" />
<option value="$PROJECT_DIR$/drn.py" />
</list>
</option>
</component>
<component name="ProjectFrameBounds">
<option name="x" value="-8" />
<option name="y" value="-8" />
<option name="width" value="1936" />
<option name="height" value="1056" />
</component>
<component name="ProjectView">
<navigator currentView="ProjectPane" proportions="" version="1">
<flattenPackages />
<showMembers />
<showModules />
<showLibraryContents />
<hideEmptyPackages />
<abbreviatePackageNames />
<autoscrollToSource />
<autoscrollFromSource />
<sortByType />
<manualOrder />
<foldersAlwaysOnTop value="true" />
</navigator>
<panes>
<pane id="ProjectPane">
<subPane>
<PATH>
<PATH_ELEMENT>
<option name="myItemId" value="drn" />
<option name="myItemType" value="com.intellij.ide.projectView.impl.nodes.ProjectViewProjectNode" />
</PATH_ELEMENT>
<PATH_ELEMENT>
<option name="myItemId" value="drn" />
<option name="myItemType" value="com.intellij.ide.projectView.impl.nodes.PsiDirectoryNode" />
</PATH_ELEMENT>
</PATH>
</subPane>
</pane>
<pane id="Scratches" />
<pane id="Scope" />
</panes>
</component>
<component name="RunDashboard">
<option name="ruleStates">
<list>
<RuleState>
<option name="name" value="ConfigurationTypeDashboardGroupingRule" />
</RuleState>
<RuleState>
<option name="name" value="StatusDashboardGroupingRule" />
</RuleState>
</list>
</option>
</component>
<component name="RunManager">
<configuration default="true" type="PythonConfigurationType" factoryName="Python">
<option name="INTERPRETER_OPTIONS" value="" />
<option name="PARENT_ENVS" value="true" />
<envs>
<env name="PYTHONUNBUFFERED" value="1" />
</envs>
<option name="SDK_HOME" value="" />
<option name="WORKING_DIRECTORY" value="" />
<option name="IS_MODULE_SDK" value="false" />
<option name="ADD_CONTENT_ROOTS" value="true" />
<option name="ADD_SOURCE_ROOTS" value="true" />
<module name="drn" />
<option name="SCRIPT_NAME" value="" />
<option name="PARAMETERS" value="" />
<option name="SHOW_COMMAND_LINE" value="false" />
<option name="EMULATE_TERMINAL" value="false" />
<method />
</configuration>
<configuration default="true" type="Tox" factoryName="Tox">
<option name="INTERPRETER_OPTIONS" value="" />
<option name="PARENT_ENVS" value="true" />
<envs />
<option name="SDK_HOME" value="" />
<option name="WORKING_DIRECTORY" value="" />
<option name="IS_MODULE_SDK" value="false" />
<option name="ADD_CONTENT_ROOTS" value="true" />
<option name="ADD_SOURCE_ROOTS" value="true" />
<module name="drn" />
<method />
</configuration>
<configuration default="true" type="tests" factoryName="Doctests">
<option name="INTERPRETER_OPTIONS" value="" />
<option name="PARENT_ENVS" value="true" />
<envs />
<option name="SDK_HOME" value="" />
<option name="WORKING_DIRECTORY" value="" />
<option name="IS_MODULE_SDK" value="false" />
<option name="ADD_CONTENT_ROOTS" value="true" />
<option name="ADD_SOURCE_ROOTS" value="true" />
<module name="drn" />
<option name="SCRIPT_NAME" value="" />
<option name="CLASS_NAME" value="" />
<option name="METHOD_NAME" value="" />
<option name="FOLDER_NAME" value="" />
<option name="TEST_TYPE" value="TEST_SCRIPT" />
<option name="PATTERN" value="" />
<option name="USE_PATTERN" value="false" />
<method />
</configuration>
<configuration default="true" type="tests" factoryName="Nosetests">
<option name="INTERPRETER_OPTIONS" value="" />
<option name="PARENT_ENVS" value="true" />
<envs />
<option name="SDK_HOME" value="" />
<option name="WORKING_DIRECTORY" value="" />
<option name="IS_MODULE_SDK" value="false" />
<option name="ADD_CONTENT_ROOTS" value="true" />
<option name="ADD_SOURCE_ROOTS" value="true" />
<module name="drn" />
<option name="_new_regexPattern" value="&quot;&quot;" />
<option name="_new_additionalArguments" value="&quot;&quot;" />
<option name="_new_target" value="&quot;.&quot;" />
<option name="_new_targetType" value="&quot;PATH&quot;" />
<method />
</configuration>
</component>
<component name="ShelveChangesManager" show_recycled="false">
<option name="remove_strategy" value="false" />
</component>
<component name="TaskManager">
<task active="true" id="Default" summary="Default task">
<changelist id="8f4afb84-b4d6-47c4-8f67-a6e0810616b4" name="Default" comment="" />
<created>1520735743667</created>
<option name="number" value="Default" />
<option name="presentableId" value="Default" />
<updated>1520735743667</updated>
</task>
<servers />
</component>
<component name="ToolWindowManager">
<frame x="-8" y="-8" width="1936" height="1056" extended-state="7" />
<editor active="true" />
<layout>
<window_info id="Project" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="true" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="0" side_tool="false" content_ui="combo" />
<window_info id="TODO" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="6" side_tool="false" content_ui="tabs" />
<window_info id="Event Log" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="7" side_tool="true" content_ui="tabs" />
<window_info id="Run" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="2" side_tool="false" content_ui="tabs" />
<window_info id="Version Control" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="false" weight="0.33" sideWeight="0.5" order="7" side_tool="false" content_ui="tabs" />
<window_info id="Python Console" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="7" side_tool="false" content_ui="tabs" />
<window_info id="Structure" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="1" side_tool="false" content_ui="tabs" />
<window_info id="Terminal" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="7" side_tool="false" content_ui="tabs" />
<window_info id="Debug" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.4" sideWeight="0.5" order="3" side_tool="false" content_ui="tabs" />
<window_info id="Favorites" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="2" side_tool="true" content_ui="tabs" />
<window_info id="Data View" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="3" side_tool="false" content_ui="tabs" />
<window_info id="Cvs" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="4" side_tool="false" content_ui="tabs" />
<window_info id="Message" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="0" side_tool="false" content_ui="tabs" />
<window_info id="Commander" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.4" sideWeight="0.5" order="0" side_tool="false" content_ui="tabs" />
<window_info id="Inspection" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.4" sideWeight="0.5" order="5" side_tool="false" content_ui="tabs" />
<window_info id="Hierarchy" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="2" side_tool="false" content_ui="combo" />
<window_info id="Find" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="1" side_tool="false" content_ui="tabs" />
<window_info id="Ant Build" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="1" side_tool="false" content_ui="tabs" />
</layout>
<layout-to-restore>
<window_info id="TODO" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="10" side_tool="false" content_ui="tabs" />
<window_info id="Cvs" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="8" side_tool="false" content_ui="tabs" />
<window_info id="Message" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="4" side_tool="false" content_ui="tabs" />
<window_info id="Commander" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.4" sideWeight="0.5" order="1" side_tool="false" content_ui="tabs" />
<window_info id="Event Log" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="0" side_tool="true" content_ui="tabs" />
<window_info id="Inspection" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.4" sideWeight="0.5" order="9" side_tool="false" content_ui="tabs" />
<window_info id="Version Control" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="false" weight="0.33" sideWeight="0.5" order="1" side_tool="false" content_ui="tabs" />
<window_info id="Python Console" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="2" side_tool="false" content_ui="tabs" />
<window_info id="Run" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="6" side_tool="false" content_ui="tabs" />
<window_info id="Terminal" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="3" side_tool="false" content_ui="tabs" />
<window_info id="Project" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="true" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="1" side_tool="false" content_ui="combo" />
<window_info id="Hierarchy" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="3" side_tool="false" content_ui="combo" />
<window_info id="Find" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="5" side_tool="false" content_ui="tabs" />
<window_info id="Structure" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="2" side_tool="false" content_ui="tabs" />
<window_info id="Ant Build" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="2" side_tool="false" content_ui="tabs" />
<window_info id="Favorites" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="0" side_tool="true" content_ui="tabs" />
<window_info id="Debug" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.4" sideWeight="0.5" order="7" side_tool="false" content_ui="tabs" />
<window_info id="Data View" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="0" side_tool="false" content_ui="tabs" />
</layout-to-restore>
</component>
<component name="VcsContentAnnotationSettings">
<option name="myLimit" value="2678400000" />
</component>
<component name="XDebuggerManager">
<breakpoint-manager />
<watches-manager />
</component>
<component name="editorHistoryManager">
<entry file="file://$PROJECT_DIR$/train.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="1425">
<caret line="75" column="44" lean-forward="false" selection-start-line="75" selection-start-column="44" selection-end-line="75" selection-end-column="44" />
<folding>
<element signature="e#0#11#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/drn.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="0">
<caret line="0" column="26" lean-forward="true" selection-start-line="0" selection-start-column="26" selection-end-line="0" selection-end-column="26" />
<folding />
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/infer.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="361">
<caret line="26" column="10" lean-forward="true" selection-start-line="26" selection-start-column="10" selection-end-line="26" selection-end-column="10" />
<folding>
<element signature="e#0#9#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/new.py" />
<entry file="file://$PROJECT_DIR$/utils.py" />
<entry file="file://$PROJECT_DIR$/network_conf.py" />
<entry file="file://$PROJECT_DIR$/infer.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="266">
<caret line="26" column="10" lean-forward="false" selection-start-line="26" selection-start-column="10" selection-end-line="26" selection-end-column="10" />
<folding>
<element signature="e#0#9#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/train.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="1349">
<caret line="71" column="29" lean-forward="true" selection-start-line="71" selection-start-column="29" selection-end-line="75" selection-end-column="44" />
<folding>
<element signature="e#0#11#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/drn.py">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="34">
<caret line="30" column="0" lean-forward="true" selection-start-line="30" selection-start-column="0" selection-end-line="30" selection-end-column="0" />
<folding />
</state>
</provider>
</entry>
</component>
</project>
\ No newline at end of file
drn/README.md 0 → 100644
浏览文件 @ 511476b0
The minimum PaddlePaddle version needed for the code sample in this directory is v0.10.0. If you are on a version of PaddlePaddle earlier than v0.10.0, please [update your installation](http://www.paddlepaddle.org/docs/develop/documentation/en/build_and_install/pip_install_en.html).
-----------------------
# Deep Residual Networks（DRN）
## 简介
在论文[1]中提到了，1202层的ResNet出现了过拟合的问题，有待进一步改进。第二年，何的团队就发表了“Identity Mappings in Deep Residual Networks”这篇文章[2]，分析了ResNet成功的关键因素——residual block背后的算法，并对residual block以及after-addition activation进行改进，通过一系列的ablation experiments验证了，在residual block和after-addition activation上都使用identity mapping（恒等映射）时，能对模型训练产生很好的效果，通过这项改进，也成功的训练出了具有很好效果的ResNet-1001。
## DRN 网络结构
在原始的ResNet中，对于每一个residual building block：
![pic1](./img/pic1.png)
可以表现为以下形式:
$$
y_l = h(x_l) + f(x_l, w_l)
x_{l+1} = f(y_l)
$$
其中$h(x_1)$为一个恒等映射，$f(y_l)$代表ReLU激活函数，在[2]中提出了，如果如果$h(x)$和$f(y)$都是恒等映射，即$h(x_l)=x_l、f(y_l)=y_l$，那么在训练的前向和反向传播阶段，信号可以直接从一个单元传递到另外一个单元，使得训练变得更加简单。
在DNN16中，具有以下优良特性：
（1）对于任意深的单元**L**的特征 $x_L$ 可以表达为浅层单元**l**的特征 $x_l$加上一个形如 $\sum_{i=l}^{L−1}F$的残差函数，这表明了任意单元**L** 和 **l**之间都具有残差特性。
（2）对于任意深的单元 **L**，它的特征 $x_L = x_0 + \sum_{i=0}^{L−1}F(x_i,W_i)$，即为之前所有残差函数输出的总和(加上$x_0$)。而正好相反的是，“plain network”中的特征xL是一系列矩阵向量的乘积，也就是$\prod_{i=0}^{L−1}W_i x_0$，而求和的计算量远远小于求积的计算量。
实验发现，$h(x_l) = x_l$的误差衰减最快，误差也最低(下图a子图所示)：
![pic2](./img/pic2.png)
对于激活函数，验发现，将ReLU和BN都放在预激活中，即full pre-activation(下图子图e所示)在ResNet-110和ResNet-164上的效果都最好。
![pic3](./img/pic3.png)
## 复现文件一览
在复现文件中，包含以下文件：
<table>
<tr>
<th width=60%>文件</th>
<th width=40%>描述</th>
</tr>
<tr>
<td> train.py </td>
<td> DRN模型训练脚本 </td>
</tr>
<tr>
<td> infer.py </td>
<td> 利用训练好的DRN模型做预测 </td>
<tr>
<td> drn.py </td>
<td> 定义DRN的网络结构 </td>
</tr>
</table>
## 基于flower数据集的模型复现
### 数据准备
所使用的的数据集是paddle中自带的flowers数据集进行训练，直接import即可:
```
import paddle.v2.dataset.flowers as flowers
```
### 网络定义
网络的定义在文件```drn.py```中完整实现，其中最主要的是残差网络的部分：
```
def conv_bn_layer(input,
ch_out,
filter_size,
stride,
padding,
active_type=paddle.activation.Relu(),
ch_in=None):
tmp = paddle.layer.img_conv(
input=input,
filter_size=filter_size,
num_channels=ch_in,
num_filters=ch_out,
stride=stride,
padding=padding,
act=paddle.activation.Linear(),
bias_attr=False)
return paddle.layer.batch_norm(input=tmp, act=active_type)
```
### 训练
接下来，执行``` python train.py -model drn``` 即可训练过程，在训练过程中，建议使CUDA GPU进行训练，如果使用CPU训练耗时可长达90小时以上，关键代码为：
```
paddle.init(use_gpu=True, trainer_count=1)
image = paddle.layer.data(name="image", type=paddle.data_type.dense_vector(DATA_DIM))
lbl = paddle.layer.data(name="label", type=paddle.data_type.integer_value(CLASS_DIM))
（省略部分代码）
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=extra_layers)
（省略部分代码）
trainer.train(
reader=train_reader, num_passes=200, event_handler=event_handler)
```
下面是关于上述代码的解释：
1. 进行``` paddle.init ```以1个GPU的方式初始化
2. 定义```img```图像名 和 ```lbl``` 图像标签
3. 定义```trainer```，包含损失函数、参数、优化器和层数信息
4. 在```train```函数中进行实际训练，共执行200趟
执行过程中，控制台将打印如下所示的信息：
```
Pass 0, Batch 0, Cost 2.2512, ...
Pass 0, Batch 1, Cost 2.1532, ...
```
同时在```train.py```目录下，每趟训练完成时，将生成```params_pass_0.tar,gz```，最后一趟的200.tar.gz文件生成时，训练完成。
### 应用模型
应用训练好的模型，执行``` python infer.py -data_list <文件目录> =model drn```即可：
```
\# load parameters
with gzip.open('params_pass_200.tar.gz', 'r') as f:
parameters = paddle.parameters.Parameters.from_tar(f)
file_list = [line.strip() for line in open(image_list_file)]
test_data = [(paddle.image.load_and_transform(image_file, 256, 224, False)
.flatten().astype('float32'), )
for image_file in file_list]
probs = paddle.infer(
output_layer=out, parameters=parameters, input=test_data)
lab = np.argsort(-probs)
for file_name, result in zip(file_list, lab):
print "Label of %s is: %d" % (file_name, result[0])
```
代码将从图片文件夹中读取对应的图片文件，同时给出预测的标签结果，并进行输出。
drn/drn.py 0 → 100644
浏览文件 @ 511476b0
import paddle.v2 as paddle
__all__ = ['drn16']
def conv_bn_layer(input,
ch_out,
filter_size,
stride,
padding,
active_type=paddle.activation.Relu(),
ch_in=None):
tmp = paddle.layer.img_conv(
input=input,
filter_size=filter_size,
num_channels=ch_in,
num_filters=ch_out,
stride=stride,
padding=padding,
act=paddle.activation.Linear(),
bias_attr=False)
return paddle.layer.batch_norm(input=tmp, act=active_type)
def shortcut(input, ch_out, stride):
if input.num_filters != ch_out:
return conv_bn_layer(input, ch_out, 1, stride, 0,
paddle.activation.Linear())
else:
return input
def basicblock(input, ch_out, stride):
short = shortcut(input, ch_out, stride)
conv1 = conv_bn_layer(input, ch_out, 3, stride, 1)
conv2 = conv_bn_layer(conv1, ch_out, 3, 1, 1, paddle.activation.Linear())
return paddle.layer.addto(
input=[short, conv2], act=paddle.activation.Relu())
def bottleneck(input, ch_out, stride):
short = shortcut(input, ch_out * 4, stride)
conv1 = conv_bn_layer(input, ch_out, 1, stride, 0)
conv2 = conv_bn_layer(conv1, ch_out, 3, 1, 1)
conv3 = conv_bn_layer(conv2, ch_out * 4, 1, 1, 0,
paddle.activation.Linear())
return paddle.layer.addto(
input=[short, conv3], act=paddle.activation.Relu())
def layer_warp(block_func, input, ch_out, count, stride):
conv = block_func(input, ch_out, stride)
for i in range(1, count):
conv = block_func(conv, ch_out, 1)
return conv
def drn16(input, class_dim, depth=32):
assert (depth - 2) % 6 == 0
n = (depth - 2) / 6
conv1 = conv_bn_layer(
input, ch_in=3, ch_out=16, filter_size=3, stride=1, padding=1)
res1 = layer_warp(basicblock, conv1, 16, n, 1)
res2 = layer_warp(basicblock, res1, 32, n, 2)
res3 = layer_warp(basicblock, res2, 64, n, 2)
pool = paddle.layer.img_pool(
input=res3, pool_size=8, stride=1, pool_type=paddle.pooling.Avg())
out = paddle.layer.fc(input=pool,
size=class_dim,
act=paddle.activation.Softmax())
return out
\ No newline at end of file
drn/infer.py 0 → 100644
浏览文件 @ 511476b0
import os
import gzip
import argparse
import numpy as np
from PIL import Image
import paddle.v2 as paddle
import drn
DATA_DIM = 3 * 224 * 224
CLASS_DIM = 102
def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument(
'data_list',
help='The path of data list file, which consists of one image path per line'
)
parser.add_argument(
'model',
help='The model for image classification',
choices=[
'drn'
])
parser.add_argument(
'params_path', help='The file which stores the parameters')
args = parser.parse_args()
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=1)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(DATA_DIM))
if args.model == 'drn':
out = drn.drn16(image, class_dim=CLASS_DIM)
# load parameters
with gzip.open(args.params_path, 'r') as f:
parameters = paddle.parameters.Parameters.from_tar(f)
file_list = [line.strip() for line in open(args.data_list)]
test_data = [(paddle.image.load_and_transform(image_file, 256, 224, False)
.flatten().astype('float32'), ) for image_file in file_list]
probs = paddle.infer(
output_layer=out, parameters=parameters, input=test_data)
lab = np.argsort(-probs)
for file_name, result in zip(file_list, lab):
print "Label of %s is: %d" % (file_name, result[0])
if __name__ == '__main__':
main()
\ No newline at end of file
drn/train.py 0 → 100644
浏览文件 @ 511476b0
import gzip
import argparse
import paddle.v2.dataset.flowers as flowers
import paddle.v2 as paddle
import drn
DATA_DIM = 3 * 224 * 224
CLASS_DIM = 102
BATCH_SIZE = 128
def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument(
'model',
help='The model for image classification',
choices=[
'drn'
])
args = parser.parse_args()
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=1)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(DATA_DIM))
lbl = paddle.layer.data(
name="label", type=paddle.data_type.integer_value(CLASS_DIM))
extra_layers = None
learning_rate = 0.01
if args.model == 'drn':
out = drn.drn16(image, class_dim=CLASS_DIM)
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
# Create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 *
BATCH_SIZE),
learning_rate=learning_rate / BATCH_SIZE,
learning_rate_decay_a=0.1,
learning_rate_decay_b=128000 * 35,
learning_rate_schedule="discexp", )
train_reader = paddle.batch(
paddle.reader.shuffle(
flowers.train(),
# To use other data, replace the above line with:
# reader.train_reader('train.list'),
buf_size=1000),
batch_size=BATCH_SIZE)
test_reader = paddle.batch(
flowers.valid(),
# To use other data, replace the above line with:
# reader.test_reader('val.list'),
batch_size=BATCH_SIZE)
# Create trainer
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=extra_layers)
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 1 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if isinstance(event, paddle.event.EndPass):
with gzip.open('params_pass_%d.tar.gz' % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(reader=test_reader)
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
trainer.train(
reader=train_reader, num_passes=200, event_handler=event_handler)
if __name__ == '__main__':
main()
\ No newline at end of file
fluid/DeepASR/examples/aishell/profile.sh 0 → 100644
浏览文件 @ 511476b0
export CUDA_VISIBLE_DEVICES=2,3,4,5
python -u ../../tools/profile.py --feature_lst data/train_feature.lst \
--label_lst data/train_label.lst \
--mean_var data/aishell/global_mean_var \
--parallel \
--frame_dim 2640 \
--class_num 101 \
fluid/DeepQNetwork/DQN.py 0 → 100644
浏览文件 @ 511476b0
#-*- coding: utf-8 -*-
#File: DQN.py
from agent import Model
import gym
import argparse
from tqdm import tqdm
from expreplay import ReplayMemory, Experience
import numpy as np
import os
UPDATE_FREQ = 4
MEMORY_WARMUP_SIZE = 1000
def run_episode(agent, env, exp, train_or_test):
assert train_or_test in ['train', 'test'], train_or_test
total_reward = 0
state = env.reset()
for step in range(200):
action = agent.act(state, train_or_test)
next_state, reward, isOver, _ = env.step(action)
if train_or_test == 'train':
exp.append(Experience(state, action, reward, isOver))
# train model
# start training
if len(exp) > MEMORY_WARMUP_SIZE:
batch_idx = np.random.randint(
len(exp) - 1, size=(args.batch_size))
if step % UPDATE_FREQ == 0:
batch_state, batch_action, batch_reward, \
batch_next_state, batch_isOver = exp.sample(batch_idx)
agent.train(batch_state, batch_action, batch_reward, \
batch_next_state, batch_isOver)
total_reward += reward
state = next_state
if isOver:
break
return total_reward
def train_agent():
env = gym.make(args.env)
state_shape = env.observation_space.shape
exp = ReplayMemory(args.mem_size, state_shape)
action_dim = env.action_space.n
agent = Model(state_shape[0], action_dim, gamma=0.99)
while len(exp) < MEMORY_WARMUP_SIZE:
run_episode(agent, env, exp, train_or_test='train')
max_episode = 4000
# train
total_episode = 0
pbar = tqdm(total=max_episode)
recent_100_reward = []
for episode in xrange(max_episode):
# start epoch
total_reward = run_episode(agent, env, exp, train_or_test='train')
pbar.set_description('[train]exploration:{}'.format(agent.exploration))
pbar.update()
# recent 100 reward
total_reward = run_episode(agent, env, exp, train_or_test='test')
recent_100_reward.append(total_reward)
if len(recent_100_reward) > 100:
recent_100_reward = recent_100_reward[1:]
pbar.write("episode:{} test_reward:{}".format(\
episode, np.mean(recent_100_reward)))
pbar.close()
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--env', type=str, default='MountainCar-v0', \
help='enviroment to train DQN model, e.g CartPole-v0')
parser.add_argument('--gamma', type=float, default=0.99, \
help='discount factor for accumulated reward computation')
parser.add_argument('--mem_size', type=int, default=500000, \
help='memory size for experience replay')
parser.add_argument('--batch_size', type=int, default=192, \
help='batch size for training')
args = parser.parse_args()
train_agent()
fluid/DeepQNetwork/README.md 0 → 100644
浏览文件 @ 511476b0
<img src="mountain_car.gif" width="300" height="200">
# Reproduce DQN model
+ DQN in:
[Human-level Control Through Deep Reinforcement Learning](http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html)
# Mountain-CAR benchmark & performance
[MountainCar-v0](https://gym.openai.com/envs/MountainCar-v0/)
A car is on a one-dimensional track, positioned between two "mountains". The goal is to drive up the mountain on the right; however, the car's engine is not strong enough to scale the mountain in a single pass. Therefore, the only way to succeed is to drive back and forth to build up momentum.
<img src="curve.png" >
# How to use
+ Dependencies:
+ python2.7
+ gym
+ tqdm
+ paddle-fluid
+ Start Training:
```
# use mountain-car enviroment as default
python DQN.py
# use other enviorment
python DQN.py --env CartPole-v0
```
fluid/DeepQNetwork/agent.py 0 → 100644
浏览文件 @ 511476b0
#-*- coding: utf-8 -*-
#File: agent.py
import paddle.fluid as fluid
from paddle.fluid.param_attr import ParamAttr
import numpy as np
from tqdm import tqdm
import math
UPDATE_TARGET_STEPS = 200
class Model(object):
def __init__(self, state_dim, action_dim, gamma):
self.global_step = 0
self.state_dim = state_dim
self.action_dim = action_dim
self.gamma = gamma
self.exploration = 1.0
self._build_net()
def _get_inputs(self):
return [fluid.layers.data(\
name='state', shape=[self.state_dim], dtype='float32'),
fluid.layers.data(\
name='action', shape=[1], dtype='int32'),
fluid.layers.data(\
name='reward', shape=[], dtype='float32'),
fluid.layers.data(\
name='next_s', shape=[self.state_dim], dtype='float32'),
fluid.layers.data(\
name='isOver', shape=[], dtype='bool')]
def _build_net(self):
state, action, reward, next_s, isOver = self._get_inputs()
self.pred_value = self.get_DQN_prediction(state)
self.predict_program = fluid.default_main_program().clone()
action_onehot = fluid.layers.one_hot(action, self.action_dim)
action_onehot = fluid.layers.cast(action_onehot, dtype='float32')
pred_action_value = fluid.layers.reduce_sum(\
fluid.layers.elementwise_mul(action_onehot, self.pred_value), dim=1)
targetQ_predict_value = self.get_DQN_prediction(next_s, target=True)
best_v = fluid.layers.reduce_max(targetQ_predict_value, dim=1)
best_v.stop_gradient = True
target = reward + (1.0 - fluid.layers.cast(\
isOver, dtype='float32')) * self.gamma * best_v
cost = fluid.layers.square_error_cost(\
input=pred_action_value, label=target)
cost = fluid.layers.reduce_mean(cost)
self._sync_program = self._build_sync_target_network()
optimizer = fluid.optimizer.Adam(1e-3)
optimizer.minimize(cost)
# define program
self.train_program = fluid.default_main_program()
# fluid exe
place = fluid.CUDAPlace(0)
self.exe = fluid.Executor(place)
self.exe.run(fluid.default_startup_program())
def get_DQN_prediction(self, state, target=False):
variable_field = 'target' if target else 'policy'
# layer fc1
param_attr = ParamAttr(name='{}_fc1'.format(variable_field))
bias_attr = ParamAttr(name='{}_fc1_b'.format(variable_field))
fc1 = fluid.layers.fc(input=state,
size=256,
act='relu',
param_attr=param_attr,
bias_attr=bias_attr)
param_attr = ParamAttr(name='{}_fc2'.format(variable_field))
bias_attr = ParamAttr(name='{}_fc2_b'.format(variable_field))
fc2 = fluid.layers.fc(input=fc1,
size=128,
act='tanh',
param_attr=param_attr,
bias_attr=bias_attr)
param_attr = ParamAttr(name='{}_fc3'.format(variable_field))
bias_attr = ParamAttr(name='{}_fc3_b'.format(variable_field))
value = fluid.layers.fc(input=fc2,
size=self.action_dim,
param_attr=param_attr,
bias_attr=bias_attr)
return value
def _build_sync_target_network(self):
vars = fluid.default_main_program().list_vars()
policy_vars = []
target_vars = []
for var in vars:
if 'GRAD' in var.name: continue
if 'policy' in var.name:
policy_vars.append(var)
elif 'target' in var.name:
target_vars.append(var)
policy_vars.sort(key=lambda x: x.name.split('policy_')[1])
target_vars.sort(key=lambda x: x.name.split('target_')[1])
sync_program = fluid.default_main_program().clone()
with fluid.program_guard(sync_program):
sync_ops = []
for i, var in enumerate(policy_vars):
sync_op = fluid.layers.assign(policy_vars[i], target_vars[i])
sync_ops.append(sync_op)
sync_program = sync_program.prune(sync_ops)
return sync_program
def act(self, state, train_or_test):
sample = np.random.random()
if train_or_test == 'train' and sample < self.exploration:
act = np.random.randint(self.action_dim)
else:
state = np.expand_dims(state, axis=0)
pred_Q = self.exe.run(self.predict_program,
feed={'state': state.astype('float32')},
fetch_list=[self.pred_value])[0]
pred_Q = np.squeeze(pred_Q, axis=0)
act = np.argmax(pred_Q)
self.exploration = max(0.1, self.exploration - 1e-6)
return act
def train(self, state, action, reward, next_state, isOver):
if self.global_step % UPDATE_TARGET_STEPS == 0:
self.sync_target_network()
self.global_step += 1
action = np.expand_dims(action, -1)
self.exe.run(self.train_program, \
feed={'state': state, \
'action': action, \
'reward': reward, \
'next_s': next_state, \
'isOver': isOver})
def sync_target_network(self):
self.exe.run(self._sync_program)
fluid/DeepQNetwork/expreplay.py 0 → 100644
浏览文件 @ 511476b0
#-*- coding: utf-8 -*-
#File: expreplay.py
from collections import namedtuple
import numpy as np
Experience = namedtuple('Experience', ['state', 'action', 'reward', 'isOver'])
class ReplayMemory(object):
def __init__(self, max_size, state_shape):
self.max_size = int(max_size)
self.state_shape = state_shape
self.state = np.zeros((self.max_size, ) + state_shape, dtype='float32')
self.action = np.zeros((self.max_size, ), dtype='int32')
self.reward = np.zeros((self.max_size, ), dtype='float32')
self.isOver = np.zeros((self.max_size, ), dtype='bool')
self._curr_size = 0
self._curr_pos = 0
def append(self, exp):
if self._curr_size < self.max_size:
self._assign(self._curr_pos, exp)
self._curr_size += 1
else:
self._assign(self._curr_pos, exp)
self._curr_pos = (self._curr_pos + 1) % self.max_size
def _assign(self, pos, exp):
self.state[pos] = exp.state
self.action[pos] = exp.action
self.reward[pos] = exp.reward
self.isOver[pos] = exp.isOver
def __len__(self):
return self._curr_size
def sample(self, batch_idx):
# index mapping to avoid sampling lastest state
batch_idx = (self._curr_pos + batch_idx) % self._curr_size
next_idx = (batch_idx + 1) % self._curr_size
state = self.state[batch_idx]
reward = self.reward[batch_idx]
action = self.action[batch_idx]
next_state = self.state[next_idx]
isOver = self.isOver[batch_idx]
return (state, action, reward, next_state, isOver)
fluid/ocr_recognition/ctc_reader.py
浏览文件 @ 511476b0
......@@ -136,6 +136,7 @@ class DataGenerator(object):
img = Image.open(img_path).convert('L')
img = np.array(img) - 127.5
img = img[np.newaxis, ...]
label = [int(c) for c in line.split(' ')[3].split(',')]
yield img, label
else:
while True:
......
generate_sequence_by_rnn_lm/README.md
浏览文件 @ 511476b0
......@@ -99,7 +99,7 @@ RNN是一个序列模型，基本思路是：在时刻$t$，将前一时刻$t-1$
```
1. `max_word_num`：指定字典中含有多少个词。
2. `cutoff_word_fre`：字典中词语在训练语料中出现的最低频率。
- 加入指定了 `max_word_num = 5000`，并且 `cutoff_word_fre = 10`，词频统计发现训练语料中出现频率高于10次的词语仅有3000个，那么最终会取3000个词构成词典。
- 假如指定了 `max_word_num = 5000`，并且 `cutoff_word_fre = 10`，词频统计发现训练语料中出现频率高于10次的词语仅有3000个，那么最终会取3000个词构成词典。
- 构建词典时，会自动加入两个特殊符号：
1. `<unk>`：不出现在字典中的词
2. `<e>`：句子的结束符
......
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