update readme

.idea/workspace.xml

@@ -14,12 +14,12 @@
     <session id="821246655">
       <usages-collector id="statistics.file.extensions.edit">
         <counts>
-          <entry key="md" value="16" />
+          <entry key="md" value="17" />
         </counts>
       </usages-collector>
       <usages-collector id="statistics.file.types.edit">
         <counts>
-          <entry key="Markdown" value="16" />
+          <entry key="Markdown" value="17" />
         </counts>
       </usages-collector>
     </session>
@@ -30,8 +30,8 @@
         <entry file="file://$PROJECT_DIR$/README.md">
           <provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
             <state split_layout="SPLIT">
-              <first_editor relative-caret-position="396">
-                <caret line="27" column="12" selection-start-line="27" selection-start-column="12" selection-end-line="27" selection-end-column="12" />
+              <first_editor relative-caret-position="388">
+                <caret line="41" column="61" selection-start-line="41" selection-start-column="61" selection-end-line="41" selection-end-column="61" />
               </first_editor>
               <second_editor />
             </state>
@@ -79,6 +79,11 @@
     <detection-done>true</detection-done>
     <sorting>DEFINITION_ORDER</sorting>
   </component>
+  <component name="ProjectFrameBounds" extendedState="6">
+    <option name="x" value="953" />
+    <option name="width" value="974" />
+    <option name="height" value="1087" />
+  </component>
   <component name="ProjectLevelVcsManager" settingsEditedManually="true" />
   <component name="ProjectView">
     <navigator proportions="" version="1">

README.md

@@ -13,13 +13,6 @@ A Chinese characters recognition repository based on convolutional recurrent net
 <img src='images/demo_2.jpg' title='example2' style='max-width:600px'></img>
 </p>
 
-## Data
-#### Synthetic Chinese String Dataset
-1. Download the dataset in [here](https://pan.baidu.com/s/1ufYbnZAZ1q0AlK7yZ08cvQ)
-2. Put char_std_5990.txt in lib/dataset/txt/
-3. Download the preprocessed labels in [here](https://pan.baidu.com/s/1rd4tm0sCq5fFgB2ziUxcrA) (password:w877)
-4. And put train.txt and test.txt in lib/dataset/txt/
-
 ## Data
 #### Synthetic Chinese String Dataset
 1. Download the dataset in [here](https://pan.baidu.com/s/1ufYbnZAZ1q0AlK7yZ08cvQ)
@@ -46,7 +39,7 @@ A Chinese characters recognition repository based on convolutional recurrent net
 
 #### loss overview
 <p>
-<img src='images/loss_1.png' title='loss1' style='max-width:600px'></img>
+<img src='images/loss_1.png' title='loss1' style='max-width:800px'></img>
 </p>
 <p>
 <img src='images/loss_2.png' title='loss1' style='max-width:600px'></img>