From 919d89af4b1e44d30e04a883274f92604b7c70a5 Mon Sep 17 00:00:00 2001
From: Your Name <you@example.com>
Date: Wed, 5 Jun 2019 00:13:32 +0800
Subject: [PATCH] data ready

---
 .DS_Store                                     | Bin 0 -> 6148 bytes
 ._.DS_Store                                   | Bin 0 -> 4096 bytes
 .gitignore                                    |   1 +
 .idea/misc.xml                                |   4 +
 .idea/modules.xml                             |   8 +
 .idea/ocrcn_tf2.iml                           |  11 +
 .idea/vcs.xml                                 |   6 +
 .idea/workspace.xml                           | 251 ++++++++++++++++++
 dataset/.DS_Store                             | Bin 0 -> 6148 bytes
 dataset/._.DS_Store                           | Bin 0 -> 4096 bytes
 dataset/.gitignore                            |   3 +-
 dataset/casia_hwdb.py                         | 102 +++----
 dataset/charactors.txt                        |   0
 dataset/convert_to_tfrecord.py                |  40 +--
 ..._hwdb_1.0_1.1.tfrecord => dataset_hwdb.py} |   0
 dataset/get_hwdb_1.0_1.1.sh                   |   0
 readme.md                                     |   6 +
 sample.png                                    | Bin
 samples/.gitignore                            |   0
 samples/001-f.gnt                             | Bin
 samples/sample.png                            | Bin
 tests.py                                      |   0
 train.py                                      |   0
 23 files changed, 364 insertions(+), 68 deletions(-)
 create mode 100755 .DS_Store
 create mode 100755 ._.DS_Store
 create mode 100755 .gitignore
 create mode 100755 .idea/misc.xml
 create mode 100755 .idea/modules.xml
 create mode 100755 .idea/ocrcn_tf2.iml
 create mode 100755 .idea/vcs.xml
 create mode 100755 .idea/workspace.xml
 create mode 100755 dataset/.DS_Store
 create mode 100755 dataset/._.DS_Store
 mode change 100644 => 100755 dataset/.gitignore
 mode change 100644 => 100755 dataset/casia_hwdb.py
 mode change 100644 => 100755 dataset/charactors.txt
 mode change 100644 => 100755 dataset/convert_to_tfrecord.py
 rename dataset/{casia_hwdb_1.0_1.1.tfrecord => dataset_hwdb.py} (100%)
 mode change 100644 => 100755
 mode change 100644 => 100755 dataset/get_hwdb_1.0_1.1.sh
 mode change 100644 => 100755 readme.md
 mode change 100644 => 100755 sample.png
 mode change 100644 => 100755 samples/.gitignore
 mode change 100644 => 100755 samples/001-f.gnt
 mode change 100644 => 100755 samples/sample.png
 mode change 100644 => 100755 tests.py
 create mode 100755 train.py

diff --git a/.DS_Store b/.DS_Store
new file mode 100755
index 0000000000000000000000000000000000000000..bb3993eefd5c6c0d458bed205a89a8d8b05241a0
GIT binary patch
literal 6148
zcmeHK%Wl&^6upxgVizH@Kx&uXu(P71K?y97tWXx+AsN8}P-|l=wdC57?GP1{%F8ZU
z0$&7Qz?LO{0cRed*ln|f3eA!3oO#?k)|_k4c!-Ei7vYeoM?@x!v$2ih67X?u7tm2X
zx4?|gagbzhf+P#j<`ZgY1+)U!TLJ#<8q}v5#Z)%GU-koI&QAfch%SZXQwb|5YJ1aQ
zvv;s8=4x;F8qAZpC<lXYtg~g@xY;!=%d~D=uf5}J>6L!DD5ie?lDD4v<#C|u&$2A}
zQ}=`CakM<_-F=*;r5~qJE`sAQg3GHHaT;dJX|_niLd@gI0r8;2-fmS5$79Fd8||$e
zyP8Y}j(vYLUac&1=iczq!O_X-yXyVw?2}kFF>G!EcNG7o&#1ISdF$nAlBF|@@F<IN
zNaaJg6L248*c6$*!)smSZHVi`Z%&Dbm{Ur#W(@n#is?3Dil#T6Z}whG%$I+in4PK`
z4JVHMaI`TmAF(3f%DnKrwKQqv#l&kILA4Urht{V}&DaCXu$~p}pCd0ZvT=!j$8Gte
zdHtbYYm@H*8d?FZfL35#0lq)jFwU;xTC&(WP>3r4*g&@c>f+ZQZ1WDVtGJeo9)QVE
zuncADiow*)fyr=;yUM?oEW?S3Cu1J<WTtK?OkF&fE!>H@l69#S&<Zpa*pkg2KmVUx
zegAI;>6TVNEAU?_z>Ixwe~Klkv-QH__*rYij$j<zua+!AP^jZrRQOT63lqSY%`0G6
UaV;4=fc_B>GU!4p@K+W11$B7wRsaA1

literal 0
HcmV?d00001

diff --git a/._.DS_Store b/._.DS_Store
new file mode 100755
index 0000000000000000000000000000000000000000..9ad849cdb9e467065f3aa98e6e57ed2552be42dd
GIT binary patch
literal 4096
zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDJkFz{^v(m+1nBL)UWIhYCu0iY;W;207T
zWIgNTe~1o-3apAo1xG_*Gz3ONU^E0qLtr!nMnhmU1V%$(Gz3ONU^E0qLx9R5zz8%C
zguy^ABqOs}p(wRDzqBYhRUs|EC|e;juOv0EBr`uRF(;=|AtyDhL?J0BF)tg~)rIOB
Q(iE!y;a-tpko*510KSwTa{vGU

literal 0
HcmV?d00001

diff --git a/.gitignore b/.gitignore
new file mode 100755
index 0000000..1d74e21
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+.vscode/
diff --git a/.idea/misc.xml b/.idea/misc.xml
new file mode 100755
index 0000000..65531ca
--- /dev/null
+++ b/.idea/misc.xml
@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.6" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100755
index 0000000..d875ec3
--- /dev/null
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/ocrcn_tf2.iml" filepath="$PROJECT_DIR$/.idea/ocrcn_tf2.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file
diff --git a/.idea/ocrcn_tf2.iml b/.idea/ocrcn_tf2.iml
new file mode 100755
index 0000000..6711606
--- /dev/null
+++ b/.idea/ocrcn_tf2.iml
@@ -0,0 +1,11 @@
+<?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="PROJECT_TEST_RUNNER" value="Unittests" />
+  </component>
+</module>
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100755
index 0000000..94a25f7
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file
diff --git a/.idea/workspace.xml b/.idea/workspace.xml
new file mode 100755
index 0000000..bdd3ca6
--- /dev/null
+++ b/.idea/workspace.xml
@@ -0,0 +1,251 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ChangeListManager">
+    <list default="true" id="c86d3061-c2c8-42bb-882f-53f6373c7f88" name="Default" comment="">
+      <change beforePath="$PROJECT_DIR$/dataset/.gitignore" afterPath="$PROJECT_DIR$/dataset/.gitignore" />
+      <change beforePath="$PROJECT_DIR$/dataset/casia_hwdb.py" afterPath="$PROJECT_DIR$/dataset/casia_hwdb.py" />
+      <change beforePath="$PROJECT_DIR$/dataset/casia_hwdb_1.0_1.1.tfrecord" afterPath="$PROJECT_DIR$/dataset/casia_hwdb_1.0_1.1.tfrecord" />
+      <change beforePath="$PROJECT_DIR$/dataset/charactors.txt" afterPath="$PROJECT_DIR$/dataset/charactors.txt" />
+      <change beforePath="$PROJECT_DIR$/dataset/convert_to_tfrecord.py" afterPath="$PROJECT_DIR$/dataset/convert_to_tfrecord.py" />
+      <change beforePath="$PROJECT_DIR$/dataset/get_hwdb_1.0_1.1.sh" afterPath="$PROJECT_DIR$/dataset/get_hwdb_1.0_1.1.sh" />
+      <change beforePath="$PROJECT_DIR$/readme.md" afterPath="$PROJECT_DIR$/readme.md" />
+      <change beforePath="$PROJECT_DIR$/sample.png" afterPath="$PROJECT_DIR$/sample.png" />
+      <change beforePath="$PROJECT_DIR$/samples/.gitignore" afterPath="$PROJECT_DIR$/samples/.gitignore" />
+      <change beforePath="$PROJECT_DIR$/samples/001-f.gnt" afterPath="$PROJECT_DIR$/samples/001-f.gnt" />
+      <change beforePath="$PROJECT_DIR$/samples/sample.png" afterPath="$PROJECT_DIR$/samples/sample.png" />
+      <change beforePath="$PROJECT_DIR$/tests.py" afterPath="$PROJECT_DIR$/tests.py" />
+    </list>
+    <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="FileEditorManager">
+    <leaf>
+      <file leaf-file-name="dataset_hwdb.py" pinned="false" current-in-tab="false">
+        <entry file="file://$PROJECT_DIR$/dataset/dataset_hwdb.py">
+          <provider selected="true" editor-type-id="text-editor">
+            <state relative-caret-position="0">
+              <caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
+              <folding />
+            </state>
+          </provider>
+        </entry>
+      </file>
+      <file leaf-file-name="casia_hwdb.py" pinned="false" current-in-tab="true">
+        <entry file="file://$PROJECT_DIR$/dataset/casia_hwdb.py">
+          <provider selected="true" editor-type-id="text-editor">
+            <state relative-caret-position="715">
+              <caret line="70" column="26" lean-forward="true" selection-start-line="70" selection-start-column="26" selection-end-line="70" selection-end-column="26" />
+              <folding />
+            </state>
+          </provider>
+        </entry>
+      </file>
+      <file leaf-file-name="tests.py" pinned="false" current-in-tab="false">
+        <entry file="file://$PROJECT_DIR$/tests.py">
+          <provider selected="true" editor-type-id="text-editor">
+            <state relative-caret-position="0">
+              <caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
+              <folding />
+            </state>
+          </provider>
+        </entry>
+      </file>
+      <file leaf-file-name="convert_to_tfrecord.py" pinned="false" current-in-tab="false">
+        <entry file="file://$PROJECT_DIR$/dataset/convert_to_tfrecord.py">
+          <provider selected="true" editor-type-id="text-editor">
+            <state relative-caret-position="-301">
+              <caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
+              <folding />
+            </state>
+          </provider>
+        </entry>
+      </file>
+    </leaf>
+  </component>
+  <component name="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="IdeDocumentHistory">
+    <option name="CHANGED_PATHS">
+      <list>
+        <option value="$PROJECT_DIR$/dataset/casia_hwdb.py" />
+      </list>
+    </option>
+  </component>
+  <component name="JsBuildToolGruntFileManager" detection-done="true" sorting="DEFINITION_ORDER" />
+  <component name="JsBuildToolPackageJson" detection-done="true" sorting="DEFINITION_ORDER" />
+  <component name="JsGulpfileManager">
+    <detection-done>true</detection-done>
+    <sorting>DEFINITION_ORDER</sorting>
+  </component>
+  <component name="ProjectFrameBounds">
+    <option name="x" value="933" />
+    <option name="y" value="28" />
+    <option name="width" value="1538" />
+    <option name="height" value="1412" />
+  </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="Scratches" />
+      <pane id="ProjectPane">
+        <subPane>
+          <expand>
+            <path>
+              <item name="ocrcn_tf2" type="b2602c69:ProjectViewProjectNode" />
+              <item name="ocrcn_tf2" type="462c0819:PsiDirectoryNode" />
+            </path>
+            <path>
+              <item name="ocrcn_tf2" type="b2602c69:ProjectViewProjectNode" />
+              <item name="ocrcn_tf2" type="462c0819:PsiDirectoryNode" />
+              <item name="dataset" type="462c0819:PsiDirectoryNode" />
+            </path>
+          </expand>
+          <select />
+        </subPane>
+      </pane>
+      <pane id="Scope" />
+    </panes>
+  </component>
+  <component name="PropertiesComponent">
+    <property name="nodejs_interpreter_path.stuck_in_default_project" value="undefined stuck path" />
+    <property name="WebServerToolWindowFactoryState" value="false" />
+    <property name="settings.editor.selected.configurable" value="preferences.editor" />
+  </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="ShelveChangesManager" show_recycled="false">
+    <option name="remove_strategy" value="false" />
+  </component>
+  <component name="SvnConfiguration">
+    <configuration />
+  </component>
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="c86d3061-c2c8-42bb-882f-53f6373c7f88" name="Default" comment="" />
+      <created>1559385971852</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1559385971852</updated>
+    </task>
+    <servers />
+  </component>
+  <component name="ToolWindowManager">
+    <frame x="933" y="28" width="1538" height="1412" extended-state="0" />
+    <editor active="true" />
+    <layout>
+      <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="-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="-1" side_tool="true" 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="true" 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="-1" 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="-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="-1" 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="0.22386059" sideWeight="0.5" order="-1" side_tool="false" content_ui="combo" />
+      <window_info id="Docker" 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="Database" 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="-1" side_tool="false" content_ui="tabs" />
+      <window_info id="SciView" 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="-1" 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="0.33" sideWeight="0.5" order="-1" side_tool="true" 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="-1" 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="0.33" sideWeight="0.5" order="-1" side_tool="false" content_ui="tabs" />
+    </layout>
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="1" />
+  </component>
+  <component name="VcsContentAnnotationSettings">
+    <option name="myLimit" value="2678400000" />
+  </component>
+  <component name="XDebuggerManager">
+    <breakpoint-manager />
+    <watches-manager />
+  </component>
+  <component name="editorHistoryManager">
+    <entry file="file:///usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py">
+      <provider selected="true" editor-type-id="text-editor">
+        <state relative-caret-position="-7666">
+          <caret line="309" column="6" lean-forward="false" selection-start-line="309" selection-start-column="6" selection-end-line="309" selection-end-column="6" />
+          <folding />
+        </state>
+      </provider>
+    </entry>
+    <entry file="file://$PROJECT_DIR$/dataset/charactors.txt">
+      <provider selected="true" editor-type-id="text-editor">
+        <state relative-caret-position="0">
+          <caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
+          <folding />
+        </state>
+      </provider>
+    </entry>
+    <entry file="file://$PROJECT_DIR$/dataset/convert_to_tfrecord.py">
+      <provider selected="true" editor-type-id="text-editor">
+        <state relative-caret-position="-301">
+          <caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
+          <folding />
+        </state>
+      </provider>
+    </entry>
+    <entry file="file://$PROJECT_DIR$/dataset/dataset_hwdb.py">
+      <provider selected="true" editor-type-id="text-editor">
+        <state relative-caret-position="0">
+          <caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
+          <folding />
+        </state>
+      </provider>
+    </entry>
+    <entry file="file://$PROJECT_DIR$/train.py">
+      <provider selected="true" editor-type-id="text-editor">
+        <state relative-caret-position="0">
+          <caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
+          <folding />
+        </state>
+      </provider>
+    </entry>
+    <entry file="file://$PROJECT_DIR$/sample.png">
+      <provider selected="true" editor-type-id="images">
+        <state />
+      </provider>
+    </entry>
+    <entry file="file://$PROJECT_DIR$/tests.py">
+      <provider selected="true" editor-type-id="text-editor">
+        <state relative-caret-position="0">
+          <caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
+          <folding />
+        </state>
+      </provider>
+    </entry>
+    <entry file="file://$PROJECT_DIR$/dataset/casia_hwdb.py">
+      <provider selected="true" editor-type-id="text-editor">
+        <state relative-caret-position="715">
+          <caret line="70" column="26" lean-forward="true" selection-start-line="70" selection-start-column="26" selection-end-line="70" selection-end-column="26" />
+          <folding />
+        </state>
+      </provider>
+    </entry>
+  </component>
+</project>
\ No newline at end of file
diff --git a/dataset/.DS_Store b/dataset/.DS_Store
new file mode 100755
index 0000000000000000000000000000000000000000..44503b4398f8d4ae6bd12434e24c6c427f1e4755
GIT binary patch
literal 6148
zcmeHK%Sr=55Uhy-qoM``5xndNh?twlCB%bgKOm1yG=bns5?{AHdh{#&E|30&R`(3S
z*^N1hNH_G<ysCGnX4u{V;M(`Y7SIIHpbOTvSgbG^7q3_?^lTEH#+cv+x5zQWs509+
z{-Of1ciTASzD=;8FZb_qnrDM)KH#_<ju-mLry6U(E;95nC!>!p#(2aK1ID?-bIf$-
zCFb!;W*058&lpQke1U5{N12|dVH_3jrKo$1I_A5~=oz_k2Im^(35%HPUQ66VGIE~V
z2cFs)xn1Q;8NC6cRaf^>inUK2`eceWBaO928?G04`=;sv^^aLqUFI0a>#3!scVN@Z
z6fgx$fwc-SXNxs<JX&cAm;$E2QUUosBy_<vVBt|e9W3+;K&-P{jdl556iyN_4On>O
z2+esa(NkTxVmMD{e-h@U0Sk|w4i_#TE<D+V8;aAXGk&7e;Zl!QngXUktiXnEHYNXG
z{Cxk9N!Bt2Oo4x;fU9?|I&Cf~<krgKB-bYN9$if46&{xqRx}lJuB754x*GcvsSwkE
Tg-7<#>_<Rlu)-AhRRz8PAfbR*

literal 0
HcmV?d00001

diff --git a/dataset/._.DS_Store b/dataset/._.DS_Store
new file mode 100755
index 0000000000000000000000000000000000000000..9ad849cdb9e467065f3aa98e6e57ed2552be42dd
GIT binary patch
literal 4096
zcmZQz6=P>$Vqox1Ojhs@R)|o50+1L3ClDJkFz{^v(m+1nBL)UWIhYCu0iY;W;207T
zWIgNTe~1o-3apAo1xG_*Gz3ONU^E0qLtr!nMnhmU1V%$(Gz3ONU^E0qLx9R5zz8%C
zguy^ABqOs}p(wRDzqBYhRUs|EC|e;juOv0EBr`uRF(;=|AtyDhL?J0BF)tg~)rIOB
Q(iE!y;a-tpko*510KSwTa{vGU

literal 0
HcmV?d00001

diff --git a/dataset/.gitignore b/dataset/.gitignore
old mode 100644
new mode 100755
index 60704fd..e24f3a0
--- a/dataset/.gitignore
+++ b/dataset/.gitignore
@@ -1,2 +1,3 @@
 hwdb_raw/
-*.tfrecord
\ No newline at end of file
+*.tfrecord
+casia_hwdb.pyhwdb_11.tfrecord
diff --git a/dataset/casia_hwdb.py b/dataset/casia_hwdb.py
old mode 100644
new mode 100755
index bef2bd8..175a823
--- a/dataset/casia_hwdb.py
+++ b/dataset/casia_hwdb.py
@@ -6,9 +6,13 @@ we using this class to get .png and label from raw
 .gnt data
 
 """
+from alfred.dl.tf.common import mute_tf
+
+mute_tf()
 import struct
 import numpy as np
 import cv2
+import tensorflow as tf
 
 
 class CASIAHWDBGNT(object):
@@ -24,61 +28,57 @@ class CASIAHWDBGNT(object):
         with open(self.f_p, 'rb') as f:
             while True:
                 header = np.fromfile(f, dtype='uint8', count=header_size)
-                if not header.size: 
+                if not header.size:
                     break
-                sample_size = header[0] + (header[1]<<8) + (header[2]<<16) + (header[3]<<24)
-                tagcode = header[5] + (header[4]<<8)
-                width = header[6] + (header[7]<<8)
-                height = header[8] + (header[9]<<8)
-                if header_size + width*height != sample_size:
+                sample_size = header[0] + (header[1] << 8) + (
+                        header[2] << 16) + (header[3] << 24)
+                tagcode = header[5] + (header[4] << 8)
+                width = header[6] + (header[7] << 8)
+                height = header[8] + (header[9] << 8)
+                if header_size + width * height != sample_size:
                     break
-                image = np.fromfile(f, dtype='uint8', count=width*height).reshape((height, width))
+                image = np.fromfile(f, dtype='uint8',
+                                    count=width * height).reshape(
+                    (height, width))
                 yield image, tagcode
 
 
-def resize_padding_or_crop(target_size, ori_img, padding_value=255):
-    if len(ori_img.shape) == 3:
-        res = np.zeros([ori_img.shape[0], target_size, target_size])
-    else:
-        res = np.ones([target_size, target_size])*padding_value
-        end_x = target_size
-        end_y = target_size
-        start_x = 0
-        start_y = 0
-        if ori_img.shape[0] < target_size:
-            end_x = int((target_size + ori_img.shape[0])/2)
-        if ori_img.shape[1] < target_size:
-            end_y = int((target_size + ori_img.shape[1])/2)
-        if ori_img.shape[0] < target_size:
-            start_x = int((target_size - ori_img.shape[0])/2)
-        if ori_img.shape[1] < target_size:
-            start_y = int((target_size - ori_img.shape[1])/2)
-        res[start_x:end_x, start_y:end_y] = ori_img
-        return np.array(res, dtype=np.uint8)
+def parse_example(record):
+    features = tf.io.parse_single_example(record,
+                                          features={
+                                              'label':
+                                                  tf.io.FixedLenFeature([], tf.int64),
+                                              'image':
+                                                  tf.io.FixedLenFeature([], tf.string),
+                                          })
+    img = tf.io.decode_raw(features['image'], out_type=tf.uint8)
+    label = tf.cast(features['label'], tf.int32)
+    return img, label
+
+
+def load_ds():
+    input_files = ['casia_hwdb_1.0_1.1.tfrecord']
+    ds = tf.data.TFRecordDataset(input_files)
+    ds = ds.map(parse_example)
+    return ds
+
+
+def load_charactors():
+    a = open('charactors.txt', 'r').readlines()
+    return [i.strip() for i in a]
+
 
 if __name__ == "__main__":
-    gnt = CASIAHWDBGNT('samples/1001-f.gnt')
-
-    full_img = np.zeros([900, 900], dtype=np.uint8)
-    charset = []
-    i = 0
-    for img, tagcode in gnt.get_data_iter():
-        # cv2.imshow('rr', img)
-        try:
-            label = struct.pack('>H', tagcode).decode('gb2312')            
-            img_padded = resize_padding_or_crop(90, img)
-            col_idx = i%10
-            row_idx = i//10
-            full_img[row_idx*90:(row_idx+1)*90, col_idx*90:(col_idx+1)*90] = img_padded
-            charset.append(label.replace('\x00', ''))
-            if i >= 99:
-                cv2.imshow('rrr', full_img)
-                cv2.imwrite('sample.png', full_img)
-                cv2.waitKey(0)
-                print(charset)
-                break
-            i += 1
-        except Exception as e:
-            # print(e.with_traceback(0))
-            print('decode error')
-            continue
+    ds = load_ds()
+    charactors = load_charactors()
+    for img, label in ds.take(9):
+        # start training on model...
+        img = img.numpy()
+        img = np.resize(img, (64, 64))
+        print(img.shape)
+        label = label.numpy()
+        label = charactors[label]
+        print(label)
+        cv2.imshow('rr', img)
+        cv2.waitKey(0)
+        # break
diff --git a/dataset/charactors.txt b/dataset/charactors.txt
old mode 100644
new mode 100755
diff --git a/dataset/convert_to_tfrecord.py b/dataset/convert_to_tfrecord.py
old mode 100644
new mode 100755
index cd446e3..9bf9e44
--- a/dataset/convert_to_tfrecord.py
+++ b/dataset/convert_to_tfrecord.py
@@ -7,6 +7,7 @@ import cv2
 from alfred.utils.log import logger as logging
 import tensorflow as tf
 import glob
+import os
 
 
 class CASIAHWDBGNT(object):
@@ -39,20 +40,27 @@ def run():
     logging.info('got all {} gnt files.'.format(len(all_hwdb_gnt_files)))
     logging.info('gathering charset...')
     charset = []
-    for gnt in all_hwdb_gnt_files:
-        hwdb = CASIAHWDBGNT(gnt)
-        for img, tagcode in hwdb.get_data_iter():
-            try:
-                label = struct.pack('>H', tagcode).decode('gb2312')            
-                label = label.replace('\x00', '')
-                charset.append(label)
-            except Exception as e:
-                continue
-    charset = sorted(set(charset))
+    if os.path.exists('charactors.txt'):
+        logging.info('found exist charactors.txt...')
+        with open('charactors.txt', 'r') as f:
+            charset = f.readlines()
+            charset = [i.strip() for i in charset]
+    else:
+        for gnt in all_hwdb_gnt_files:
+            hwdb = CASIAHWDBGNT(gnt)
+            for img, tagcode in hwdb.get_data_iter():
+                try:
+                    label = struct.pack('>H', tagcode).decode('gb2312')            
+                    label = label.replace('\x00', '')
+                    charset.append(label)
+                except Exception as e:
+                    continue
+        charset = sorted(set(charset))
+        with open('charactors.txt', 'w') as f:
+            f.writelines('\n'.join(charset))
     logging.info('all got {} charactors.'.format(len(charset)))
-    with open('charactors.txt', 'w') as f:
-        f.writelines('\n'.join(charset))
-
+    logging.info('{}'.format(charset[:10]))
+    
     tfrecord_f = 'casia_hwdb_1.0_1.1.tfrecord'
     i = 0
     with tf.io.TFRecordWriter(tfrecord_f) as tfrecord_writer:
@@ -60,7 +68,7 @@ def run():
             hwdb = CASIAHWDBGNT(gnt)
             for img, tagcode in hwdb.get_data_iter():
                 try:
-                    img = cv.resize(img, (64, 64))
+                    img = cv2.resize(img, (64, 64))
                     label = struct.pack('>H', tagcode).decode('gb2312')            
                     label = label.replace('\x00', '')
                     index = charset.index(label)
@@ -68,11 +76,11 @@ def run():
                     example = tf.train.Example(features=tf.train.Features(
                         feature={
                         "label": tf.train.Feature(int64_list=tf.train.Int64List(value=[index])),
-                        'image': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img]))
+                        'image': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img.tobytes()]))
                     }))
                     tfrecord_writer.write(example.SerializeToString())
                     if i%500:
-                        logging.info('solved {} examples.'.format(i))
+                        logging.info('solved {} examples. {}: {}'.format(i, label, index))
                     i += 1
                 except Exception as e:
                     logging.error(e)
diff --git a/dataset/casia_hwdb_1.0_1.1.tfrecord b/dataset/dataset_hwdb.py
old mode 100644
new mode 100755
similarity index 100%
rename from dataset/casia_hwdb_1.0_1.1.tfrecord
rename to dataset/dataset_hwdb.py
diff --git a/dataset/get_hwdb_1.0_1.1.sh b/dataset/get_hwdb_1.0_1.1.sh
old mode 100644
new mode 100755
diff --git a/readme.md b/readme.md
old mode 100644
new mode 100755
index 8624018..2f7414f
--- a/readme.md
+++ b/readme.md
@@ -27,7 +27,13 @@
 
 **更新**:
 实际上，由于单个汉字图片其实很小，差不多也就最大80x80的大小，这个大小不适合转成图片保存到本地，因此我们将hwdb原始的二进制保存为tfrecord。同时也方便后面训练，可以直接从tfrecord读取图片进行训练。
+![](https://s2.ax1x.com/2019/05/29/VKSEZt.png)
 
+在我们存储完成的时候大概处理了89万个汉字，总共汉字的空间是3755个汉字。由于我们暂时仅仅使用了1.0，所以还有大概3000个汉字没有加入进来，但是处理是一样。使用本仓库来生成你的tfrecord步骤如下：
+
+- `cd dataset && python3 convert_to_tfrecord.py`, 请注意我们使用的是tf2.0；
+- 你需要修改对应的路径，等待生成完成，大概有89万个example，如果1.0和1.1都用，那估计得double。
+  
 
 ## Model
 
diff --git a/sample.png b/sample.png
old mode 100644
new mode 100755
diff --git a/samples/.gitignore b/samples/.gitignore
old mode 100644
new mode 100755
diff --git a/samples/001-f.gnt b/samples/001-f.gnt
old mode 100644
new mode 100755
diff --git a/samples/sample.png b/samples/sample.png
old mode 100644
new mode 100755
diff --git a/tests.py b/tests.py
old mode 100644
new mode 100755
diff --git a/train.py b/train.py
new file mode 100755
index 0000000..e69de29