Merge remote-tracking branch 'origin/dygraph' into dygraph

20bf0924 · Leif · f11a1a20 · 332cb26a · 20bf0924 · 20bf0924
Commit 20bf0924 authored Sep 06, 2021 by Leif
17 changed files
--- a/README_ch.md
+++ b/README_ch.md
@@ -24,23 +24,23 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 ## 注意
 PaddleOCR同时支持动态图与静态图两种编程范式
- 动态图版本：release/2.2（默认分支，开发分支为dygraph分支），需将paddle版本升级至2.0.0或以上版本（[快速安装](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/doc/doc_ch/installation.md)）
+- 动态图版本：release/2.3（默认分支，开发分支为dygraph分支），需将paddle版本升级至2.0.0或以上版本（[快速安装](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/doc/doc_ch/installation.md)）
 - 静态图版本：develop分支
 **近期更新**
- PaddleOCR研发团队对最新发版内容技术深入解读，8月4日晚上20:15，[直播地址](https://live.bilibili.com/21689802)。
+- PaddleOCR研发团队对最新发版内容技术深入解读，9月8日晚上20:15，[直播地址](https://live.bilibili.com/21689802)。
- 2021.8.3 正式发布PaddleOCR v2.2，新增文档结构分析[PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README_ch.md)工具包，支持版面分析与表格识别（含Excel导出）。
+- 2021.9.7 发布PaddleOCR v2.3，发布PP-OCRv2算法，CPU推理速度相比于PP-OCR server提升220%；效果相比于PP-OCR mobile 提升7%。
+- 2021.8.3 发布PaddleOCR v2.2，新增文档结构分析[PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README_ch.md)工具包，支持版面分析与表格识别（含Excel导出）。
 - 2021.6.29 [FAQ](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/doc/doc_ch/FAQ.md)新增5个高频问题，总数248个，每周一都会更新，欢迎大家持续关注。
 - 2021.4.8 release 2.1版本，新增AAAI 2021论文[端到端识别算法PGNet](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/doc/doc_ch/pgnet.md)开源，[多语言模型](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/doc/doc_ch/multi_languages.md)支持种类增加到80+。
- 2021.2.8 正式发布PaddleOCRv2.0(branch release/2.0)并设置为推荐用户使用的默认分支. 发布的详细内容，请参考: https://github.com/PaddlePaddle/PaddleOCR/releases/tag/v2.0.0
- 2021.1.26,28,29 PaddleOCR官方研发团队带来技术深入解读三日直播课，1月26日、28日、29日晚上19:30，[直播地址](https://live.bilibili.com/21689802)
 - [More](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/doc/doc_ch/update.md)
 ## 特性
 - PPOCR系列高质量预训练模型，准确的识别效果
+    - 超轻量ppocrv2系列：检测（3.1M）+ 识别（8.5M）= 11.6M
    - 超轻量ppocr_mobile移动端系列：检测（3.0M）+方向分类器（1.4M）+ 识别（5.0M）= 9.4M
    - 通用ppocr_server系列：检测（47.1M）+方向分类器（1.4M）+ 识别（94.9M）= 143.4M
    - 支持中英文数字组合识别、竖排文本识别、长文本识别
@@ -84,6 +84,7 @@ PaddleOCR同时支持动态图与静态图两种编程范式
 <a name="模型下载"></a>
 ## PP-OCR 2.0系列模型列表（更新中）
 **说明** ：2.0版模型和[1.1版模型](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/models_list.md)的主要区别在于动态图训练vs.静态图训练，模型性能上无明显差距。
 | 模型简介     | 模型名称     |推荐场景          | 检测模型 | 方向分类器 | 识别模型 |
 | ------------ | --------------- | ----------------|---- | ---------- | -------- |
 | 中英文超轻量OCR模型（9.4M） | ch_ppocr_mobile_v2.0_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar)      |
@@ -93,8 +94,8 @@ PaddleOCR同时支持动态图与静态图两种编程范式
 ## 文档教程
 - [运行环境准备](./doc/doc_ch/environment.md)
- [快速开始](./doc/doc_ch/quickstart.md)
+- [快速开始（中英文/多语言/文档分析）](./doc/doc_ch/quickstart.md)
- [PaddleOCR全景图与安装](./doc/doc_ch/paddleOCR_overview.md)
+- [PaddleOCR全景图与项目克隆](./doc/doc_ch/paddleOCR_overview.md)
 - PP-OCR产业落地：从训练到部署
    - [PP-OCR模型与配置文件](./doc/doc_ch/models_and_config.md)
        - [PP-OCR模型下载](./doc/doc_ch/models_list.md)
@@ -137,13 +138,17 @@ PaddleOCR同时支持动态图与静态图两种编程范式
 - [代码组织结构](./doc/doc_ch/tree.md)
-<a name="PP-OCR"></a>
+<a name="PP-OCRv2"></a>
-## PP-OCR Pipeline
+## PP-OCRv2 Pipeline
 <div align="center">
-    <img src="./doc/ppocr_framework.png" width="800">
+    <img src="./doc/ppocrv2_framework.jpg" width="800">
 </div>
-PP-OCR是一个实用的超轻量OCR系统。主要由DB文本检测[2]、检测框矫正和CRNN文本识别三部分组成[7]。该系统从骨干网络选择和调整、预测头部的设计、数据增强、学习率变换策略、正则化参数选择、预训练模型使用以及模型自动裁剪量化8个方面，采用19个有效策略，对各个模块的模型进行效果调优和瘦身，最终得到整体大小为3.5M的超轻量中英文OCR和2.8M的英文数字OCR。更多细节请参考PP-OCR技术方案 https://arxiv.org/abs/2009.09941 。其中FPGM裁剪器[8]和PACT量化[9]的实现可以参考[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim)。
+[1] PP-OCR是一个实用的超轻量OCR系统。主要由DB文本检测、检测框矫正和CRNN文本识别三部分组成。该系统从骨干网络选择和调整、预测头部的设计、数据增强、学习率变换策略、正则化参数选择、预训练模型使用以及模型自动裁剪量化8个方面，采用19个有效策略，对各个模块的模型进行效果调优和瘦身(如绿框所示)，最终得到整体大小为3.5M的超轻量中英文OCR和2.8M的英文数字OCR。更多细节请参考PP-OCR技术方案 https://arxiv.org/abs/2009.09941
+[2] PP-OCRv2在PP—OCR的基础上，进一步在5个方面重点优化，检测模型采用CML协同互学习知识蒸馏策略和CopyPaste数据增广策略；识别模型采用LCNet轻量级骨干网络、UDML 改进知识蒸馏策略和Enhanced CTC loss损失函数改进（如上图红框所示），进一步在推理速度和预测效果上取得明显提升。更多细节请参考PP-OCR技术方案（arxiv链接生成中）。
 <a name="效果展示"></a>
 ## 效果展示 [more](./doc/doc_ch/visualization.md)

--- a/configs/rec/rec_icdar15_train.yml
+++ b/configs/rec/rec_icdar15_train.yml
@@ -14,8 +14,8 @@ Global:
  use_visualdl: False
  infer_img: doc/imgs_words_en/word_10.png
  # for data or label process
-  character_dict_path: ppocr/utils/ic15_dict.txt
+  character_dict_path: ppocr/utils/en_dict.txt
-  character_type: ch
+  character_type: EN
  max_text_length: 25
  infer_mode: False
  use_space_char: False

--- a/doc/datasets/icdar_rec.png
+++ b/doc/datasets/icdar_rec.png
--- a/doc/doc_ch/config.md
+++ b/doc/doc_ch/config.md
 # 配置文件内容与生成
-[toc]
 ## 1. 可选参数列表
 以下列表可以通过`--help`查看
@@ -56,7 +54,7 @@
 ### Architecture ([ppocr/modeling](../../ppocr/modeling))
-在ppocr中，网络被划分为Transform,Backbone,Neck和Head四个阶段
+在PaddleOCR中，网络被划分为Transform,Backbone,Neck和Head四个阶段
 |         字段             |            用途            |      默认值        |            备注             |
 | :---------------------: |  :---------------------:   | :--------------:  |   :--------------------:   |
@@ -128,4 +126,98 @@
 ## 3. 多语言配置文件生成
-【参考识别模型训练补充内容】
+PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi_languages` 路径下提供了一个多语言的配置文件模版: [rec_multi_language_lite_train.yml](../../configs/rec/multi_language/rec_multi_language_lite_train.yml)。
+您有两种方式创建所需的配置文件：
+1. 通过脚本自动生成
+[generate_multi_language_configs.py](../../configs/rec/multi_language/generate_multi_language_configs.py) 可以帮助您生成多语言模型的配置文件
+- 以意大利语为例，如果您的数据是按如下格式准备的：
+    ```
+    |-train_data
+        |- it_train.txt # 训练集标签
+        |- it_val.txt # 验证集标签
+        |- data
+            |- word_001.jpg
+            |- word_002.jpg
+            |- word_003.jpg
+            | ...
+    ```
+    可以使用默认参数，生成配置文件：
+    ```bash
+    # 该代码需要在指定目录运行
+    cd PaddleOCR/configs/rec/multi_language/
+    # 通过-l或者--language参数设置需要生成的语种的配置文件，该命令会将默认参数写入配置文件
+    python3 generate_multi_language_configs.py -l it
+    ```
+- 如果您的数据放置在其他位置，或希望使用自己的字典，可以通过指定相关参数来生成配置文件:
+    ```bash
+    # -l或者--language字段是必须的
+    # --train修改训练集，--val修改验证集，--data_dir修改数据集目录，--dict修改字典路径， -o修改对应默认参数
+    cd PaddleOCR/configs/rec/multi_language/
+    python3 generate_multi_language_configs.py -l it \  # 语种
+    --train {path/of/train_label.txt} \ # 训练标签文件的路径
+    --val {path/of/val_label.txt} \     # 验证集标签文件的路径
+    --data_dir {train_data/path} \      # 训练数据的根目录
+    --dict {path/of/dict} \             # 字典文件路径
+    -o Global.use_gpu=False             # 是否使用gpu
+    ...
+    ```
+意大利文由拉丁字母组成，因此执行完命令后会得到名为 rec_latin_lite_train.yml 的配置文件。
+2. 手动修改配置文件
+   您也可以手动修改模版中的以下几个字段得到配置文件:
+   ```
+    Global:
+      use_gpu: True
+      epoch_num: 500
+      ...
+      character_type: it  # 需要识别的语种
+      character_dict_path:  {path/of/dict} # 字典文件所在路径
+   Train:
+      dataset:
+        name: SimpleDataSet
+        data_dir: train_data/ # 数据存放根目录
+        label_file_list: ["./train_data/train_list.txt"] # 训练集label路径
+      ...
+   Eval:
+      dataset:
+        name: SimpleDataSet
+        data_dir: train_data/ # 数据存放根目录
+        label_file_list: ["./train_data/val_list.txt"] # 验证集label路径
+      ...
+   ```
+目前PaddleOCR支持的多语言算法有：
+| 配置文件 |  算法名称 |   backbone |   trans   |   seq      |     pred     |  language | character_type |
+| :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   | :-----:  | :-----:  |
+| rec_chinese_cht_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 中文繁体  | chinese_cht|
+| rec_en_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 英语（区分大小写）   | EN |
+| rec_french_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 法语 |  french |
+| rec_ger_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 德语   | german |
+| rec_japan_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 日语  | japan |
+| rec_korean_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 韩语  | korean |
+| rec_latin_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 拉丁字母  | latin |
+| rec_arabic_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 阿拉伯字母 |  ar |
+| rec_cyrillic_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 斯拉夫字母  | cyrillic |
+| rec_devanagari_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | 梵文字母  | devanagari |
+更多支持语种请参考: [多语言模型](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_ch/multi_languages.md#%E8%AF%AD%E7%A7%8D%E7%BC%A9%E5%86%99)
+多语言模型训练方式与中文模型一致，训练数据集均为100w的合成数据，少量的字体可以通过下面两种方式下载。
+* [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA)。提取码：frgi。
+* [google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)
--- a/doc/doc_ch/detection.md
+++ b/doc/doc_ch/detection.md
-# 文字检测
-本节以icdar2015数据集为例，介绍PaddleOCR中检测模型的训练、评估与测试。
+# 目录
+- [1. 文字检测](#1-----)
+  * [1.1 数据准备](#11-----)
+  * [1.2 下载预训练模型](#12--------)
+  * [1.3 启动训练](#13-----)
+  * [1.4 断点训练](#14-----)
+  * [1.5 更换Backbone 训练](#15---backbone---)
+  * [1.6 指标评估](#16-----)
+  * [1.7 测试检测效果](#17-------)
+  * [1.8 转inference模型测试](#18--inference----)
+- [2. FAQ](#2-faq)
-## 数据准备
+<a name="1-----"></a>
+# 1. 文字检测
+本节以icdar2015数据集为例，介绍PaddleOCR中检测模型训练、评估、测试的使用方式。
+<a name="11-----"></a>
+## 1.1 数据准备
 icdar2015数据集可以从[官网](https://rrc.cvc.uab.es/?ch=4&com=downloads)下载到，首次下载需注册。
+注册完成登陆后，下载下图中红色框标出的部分，其中， `Training Set Images`下载的内容保存为`icdar_c4_train_imgs`文件夹下，`Test Set Images` 下载的内容保存为`ch4_test_images`文件夹下
+<p align="center">
+ <img src="./doc/datasets/ic15_location_download.png" align="middle" width = "600"/>
+<p align="center">
 将下载到的数据集解压到工作目录下，假设解压在 PaddleOCR/train_data/ 下。另外，PaddleOCR将零散的标注文件整理成单独的标注文件
 ，您可以通过wget的方式进行下载。
 ```shell
@@ -23,7 +45,7 @@ python gen_label.py --mode="det" --root_path="/path/to/icdar_c4_train_imgs/"  \
                    --output_label="/path/to/train_icdar2015_label.txt"
 ```
-解压数据集和下载标注文件后，PaddleOCR/train_data/ 有两个文件夹和两个文件，分别是：
+解压数据集和下载标注文件后，PaddleOCR/train_data/ 有两个文件夹和两个文件，按照如下方式组织icdar2015数据集：
 ```
 /PaddleOCR/train_data/icdar2015/text_localization/
  └─ icdar_c4_train_imgs/         icdar数据集的训练数据
@@ -42,11 +64,13 @@ json.dumps编码前的图像标注信息是包含多个字典的list，字典中
 如果您想在其他数据集上训练，可以按照上述形式构建标注文件。
-## 快速启动训练
+<a name="12--------"></a>
+## 1.2 下载预训练模型
 首先下载模型backbone的pretrain model，PaddleOCR的检测模型目前支持两种backbone，分别是MobileNetV3、ResNet_vd系列，
-您可以根据需求使用[PaddleClas](https://github.com/PaddlePaddle/PaddleClas/tree/develop/ppcls/modeling/architectures)中的模型更换backbone，
+您可以根据需求使用[PaddleClas](https://github.com/PaddlePaddle/PaddleClas/tree/release/2.0/ppcls/modeling/architectures)中的模型更换backbone，
-对应的backbone预训练模型可以从[PaddleClas repo 主页中找到下载链接](https://github.com/PaddlePaddle/PaddleClas#mobile-series)。
+对应的backbone预训练模型可以从[PaddleClas repo 主页中找到下载链接](https://github.com/PaddlePaddle/PaddleClas/blob/release%2F2.0/README_cn.md#resnet%E5%8F%8A%E5%85%B6vd%E7%B3%BB%E5%88%97)。
 ```shell
 cd PaddleOCR/
 # 根据backbone的不同选择下载对应的预训练模型
@@ -56,23 +80,23 @@ wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dyg
 wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet18_vd_pretrained.pdparams
 # 或，下载ResNet50_vd的预训练模型
 wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_pretrained.pdparams
 ```
-#### 启动训练
+<a name="13-----"></a>
+## 1.3 启动训练
 *如果您安装的是cpu版本，请将配置文件中的 `use_gpu` 字段修改为false*
 ```shell
 # 单机单卡训练 mv3_db 模型
 python3 tools/train.py -c configs/det/det_mv3_db.yml \
-     -o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained/
+     -o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained
 # 单机多卡训练，通过 --gpus 参数设置使用的GPU ID
 python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs/det/det_mv3_db.yml \
-     -o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained/
+     -o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained
 ```
 上述指令中，通过-c 选择训练使用configs/det/det_db_mv3.yml配置文件。
 有关配置文件的详细解释，请参考[链接](./config.md)。
@@ -81,46 +105,122 @@ python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs/
 python3 tools/train.py -c configs/det/det_mv3_db.yml -o Optimizer.base_lr=0.0001
 ```
-#### 断点训练
+<a name="14-----"></a>
+## 1.4 断点训练
 如果训练程序中断，如果希望加载训练中断的模型从而恢复训练，可以通过指定Global.checkpoints指定要加载的模型路径：
 ```shell
 python3 tools/train.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=./your/trained/model
+```
+**注意**：`Global.checkpoints`的优先级高于`Global.pretrain_weights`的优先级，即同时指定两个参数时，优先加载`Global.checkpoints`指定的模型，如果`Global.checkpoints`指定的模型路径有误，会加载`Global.pretrain_weights`指定的模型。
+<a name="15---backbone---"></a>
+## 1.5 更换Backbone 训练
+PaddleOCR将网络划分为四部分，分别在[ppocr/modeling](../../ppocr/modeling)下。 进入网络的数据将按照顺序(transforms->backbones->
+necks->heads)依次通过这四个部分。
+```bash
+├── architectures # 网络的组网代码
+├── transforms    # 网络的图像变换模块
+├── backbones     # 网络的特征提取模块
+├── necks         # 网络的特征增强模块
+└── heads         # 网络的输出模块
 ```
+如果要更换的Backbone 在PaddleOCR中有对应实现，直接修改配置yml文件中`Backbone`部分的参数即可。
-**注意**：`Global.checkpoints`的优先级高于`Global.pretrain_weights`的优先级，即同时指定两个参数时，优先加载`Global.checkpoints`指定的模型，如果`Global.checkpoints`指定的模型路径有误，会加载`Global.pretrain_weights`指定的模型。
+如果要使用新的Backbone，更换backbones的例子如下:
+1. 在 [ppocr/modeling/backbones](../../ppocr/modeling/backbones) 文件夹下新建文件，如my_backbone.py。
+2. 在 my_backbone.py 文件内添加相关代码，示例代码如下:
+```python
+import paddle
+import paddle.nn as nn
+import paddle.nn.functional as F
+class MyBackbone(nn.Layer):
+    def __init__(self, *args, **kwargs):
+        super(MyBackbone, self).__init__()
+        # your init code
+        self.conv = nn.xxxx
+    def forward(self, inputs):
+        # your network forward
+        y = self.conv(inputs)
+        return y
+```
+3. 在 [ppocr/modeling/backbones/\__init\__.py](../../ppocr/modeling/backbones/__init__.py)文件内导入添加的`MyBackbone`模块，然后修改配置文件中Backbone进行配置即可使用，格式如下:
-## 指标评估
+```yaml
+Backbone:
+name: MyBackbone
+args1: args1
+```
-PaddleOCR计算三个OCR检测相关的指标，分别是：Precision、Recall、Hmean。
+**注意**：如果要更换网络的其他模块，可以参考[文档](./add_new_algorithm.md)。
-运行如下代码，根据配置文件`det_db_mv3.yml`中`save_res_path`指定的测试集检测结果文件，计算评估指标。
+<a name="16-----"></a>
+## 1.6 指标评估
+PaddleOCR计算三个OCR检测相关的指标，分别是：Precision、Recall、Hmean（F-Score）。
-评估时设置后处理参数`box_thresh=0.5`，`unclip_ratio=1.5`，使用不同数据集、不同模型训练，可调整这两个参数进行优化
 训练中模型参数默认保存在`Global.save_model_dir`目录下。在评估指标时，需要设置`Global.checkpoints`指向保存的参数文件。
 ```shell
-python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.checkpoints="{path/to/weights}/best_accuracy" PostProcess.box_thresh=0.5 PostProcess.unclip_ratio=1.5
+python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.checkpoints="{path/to/weights}/best_accuracy"
 ```
 * 注：`box_thresh`、`unclip_ratio`是DB后处理所需要的参数，在评估EAST模型时不需要设置
-## 测试检测效果
+<a name="17-------"></a>
+## 1.7 测试检测效果
 测试单张图像的检测效果
 ```shell
 python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy"
 ```
-测试DB模型时，调整后处理阈值，
+测试DB模型时，调整后处理阈值
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy"  PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy"  PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=2.0
 ```
 测试文件夹下所有图像的检测效果
 ```shell
 python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy"
 ```
+<a name="18--inference----"></a>
+## 1.8 转inference模型测试
+inference 模型（`paddle.jit.save`保存的模型）
+一般是模型训练，把模型结构和模型参数保存在文件中的固化模型，多用于预测部署场景。
+训练过程中保存的模型是checkpoints模型，保存的只有模型的参数，多用于恢复训练等。
+与checkpoints模型相比，inference 模型会额外保存模型的结构信息，在预测部署、加速推理上性能优越，灵活方便，适合于实际系统集成。
+检测模型转inference 模型方式：
+```shell
+# 加载配置文件`det_mv3_db.yml`，从`output/det_db`目录下加载`best_accuracy`模型，inference模型保存在`./output/det_db_inference`目录下
+python3 tools/export_model.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model="./output/det_db/best_accuracy" Global.save_inference_dir="./output/det_db_inference/"
+```
+DB检测模型inference 模型预测：
+```shell
+python3 tools/infer/predict_det.py --det_algorithm="DB" --det_model_dir="./output/det_db_inference/" --image_dir="./doc/imgs/" --use_gpu=True
+```
+如果是其他检测，比如EAST模型，det_algorithm参数需要修改为EAST，默认为DB算法：
+```shell
+python3 tools/infer/predict_det.py --det_algorithm="EAST" --det_model_dir="./output/det_db_inference/" --image_dir="./doc/imgs/" --use_gpu=True
+```
+<a name="2"></a>
+# 2. FAQ
+Q1: 训练模型转inference 模型之后预测效果不一致？
+**A**：此类问题出现较多，问题多是trained model预测时候的预处理、后处理参数和inference model预测的时候的预处理、后处理参数不一致导致的。以det_mv3_db.yml配置文件训练的模型为例，训练模型、inference模型预测结果不一致问题解决方式如下：
+- 检查[trained model预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L116)，和[inference model的预测预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/predict_det.py#L42)函数是否一致。算法在评估的时候，输入图像大小会影响精度，为了和论文保持一致，训练icdar15配置文件中将图像resize到[736, 1280]，但是在inference model预测的时候只有一套默认参数，会考虑到预测速度问题，默认限制图像最长边为960做resize的。训练模型预处理和inference模型的预处理函数位于[ppocr/data/imaug/operators.py](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/ppocr/data/imaug/operators.py#L147)
+- 检查[trained model后处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L51)，和[inference 后处理参数](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/utility.py#L50)是否一致。
--- a/doc/doc_ch/models_and_config.md
+++ b/doc/doc_ch/models_and_config.md
+# 目录
+- [1. OCR 简要介绍](#1-ocr-----)
+  * [1.1 OCR 检测模型基本概念](#11-ocr---------)
+  * [1.2 OCR 识别模型基本概念](#12-ocr---------)
+  * [1.3 PP-OCR模型](#13-pp-ocr--)
+<a name="1-ocr-----"></a>
+# 1. OCR 简要介绍
+本节简要介绍OCR检测模型、识别模型的基本概念，并介绍PaddleOCR的PP-OCR模型。
+OCR（Optical Character Recognition，光学字符识别）目前是文字识别的统称，已不限于文档或书本文字识别，更包括识别自然场景下的文字，又可以称为STR（Scene Text Recognition）。
+OCR文字识别一般包括两个部分，文本检测和文本识别；文本检测首先利用检测算法检测到图像中的文本行；然后检测到的文本行用识别算法去识别到具体文字。
+<a name="11-ocr---------"></a>
+## 1.1 OCR 检测模型基本概念
+文本检测就是要定位图像中的文字区域，然后通常以边界框的形式将单词或文本行标记出来。传统的文字检测算法多是通过手工提取特征的方式，特点是速度快，简单场景效果好，但是面对自然场景，效果会大打折扣。当前多是采用深度学习方法来做。
+基于深度学习的文本检测算法可以大致分为以下几类：
+1. 基于目标检测的方法；一般是预测得到文本框后，通过NMS筛选得到最终文本框，多是四点文本框，对弯曲文本场景效果不理想。典型算法为EAST、Text Box等方法。
+2. 基于分割的方法；将文本行当成分割目标，然后通过分割结果构建外接文本框，可以处理弯曲文本，对于文本交叉场景问题效果不理想。典型算法为DB、PSENet等方法。
+3. 混合目标检测和分割的方法；
+<a name="12-ocr---------"></a>
+## 1.2 OCR 识别模型基本概念
+OCR识别算法的输入数据一般是文本行，背景信息不多，文字占据主要部分，识别算法目前可以分为两类算法：
+1. 基于CTC的方法；即识别算法的文字预测模块是基于CTC的，常用的算法组合为CNN+RNN+CTC。目前也有一些算法尝试在网络中加入transformer模块等等。
+2. 基于Attention的方法；即识别算法的文字预测模块是基于Attention的，常用算法组合是CNN+RNN+Attention。
+<a name="13-pp-ocr--"></a>
+## 1.3 PP-OCR模型
+PaddleOCR 中集成了很多OCR算法，文本检测算法有DB、EAST、SAST等等，文本识别算法有CRNN、RARE、StarNet、Rosetta、SRN等算法。
+其中PaddleOCR针对中英文自然场景通用OCR，推出了PP-OCR系列模型，PP-OCR模型由DB+CRNN算法组成，利用海量中文数据训练加上模型调优方法，在中文场景上具备较高的文本检测识别能力。并且PaddleOCR推出了高精度超轻量PP-OCRv2模型，检测模型仅3M，识别模型仅8.5M，利用[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim)的模型量化方法，可以在保持精度不降低的情况下，将检测模型压缩到0.8M，识别压缩到3M，更加适用于移动端部署场景。
--- a/doc/doc_ch/models_list.md
+++ b/doc/doc_ch/models_list.md
@@ -32,6 +32,8 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训
 |模型名称|模型简介|配置文件|推理模型大小|下载地址|
 | --- | --- | --- | --- | --- |
+|ch_ppocr_mobile_slim_v2.1_det|slim量化+蒸馏版超轻量模型，支持中英文、多语种文本检测|[ch_det_lite_train_cml_v2.1.yml](../../configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml)| 3M |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_slim_quant_infer.tar)|
+|ch_ppocr_mobile_v2.1_det|原始超轻量模型，支持中英文、多语种文本检测|[ch_det_lite_train_cml_v2.1.ym](../../configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml)|3M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_distill_train.tar)|
 |ch_ppocr_mobile_slim_v2.0_det|slim裁剪版超轻量模型，支持中英文、多语种文本检测|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)| 2.6M |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_infer.tar)|
 |ch_ppocr_mobile_v2.0_det|原始超轻量模型，支持中英文、多语种文本检测|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|3M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|
 |ch_ppocr_server_v2.0_det|通用模型，支持中英文、多语种文本检测，比超轻量模型更大，但效果更好|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)|
@@ -45,6 +47,8 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训
 |模型名称|模型简介|配置文件|推理模型大小|下载地址|
 | --- | --- | --- | --- | --- |
+|ch_ppocr_mobile_slim_v2.1_rec|slim量化版超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train_distillation_v2.1.yml](../../configs/rec/ch_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml)| 9M |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_slim_quant_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_slim_quant_train.tar) |
+|ch_ppocr_mobile_v2.1_rec|原始超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train_distillation_v2.1.yml](../../configs/rec/ch_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml)|8.5M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_train.tar) |
 |ch_ppocr_mobile_slim_v2.0_rec|slim裁剪量化版超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)| 6M |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_train.tar) |
 |ch_ppocr_mobile_v2.0_rec|原始超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)|5.2M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) |
 |ch_ppocr_server_v2.0_rec|通用模型，支持中英文、数字识别|[rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml)|94.8M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) |
@@ -125,13 +129,15 @@ python3 generate_multi_language_configs.py -l it \
 |模型名称|模型简介|配置文件|推理模型大小|下载地址|
 | --- | --- | --- | --- | --- |
-|ch_ppocr_mobile_slim_v2.0_cls|slim量化版模型|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)| 2.1M |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) |
+|ch_ppocr_mobile_slim_v2.0_cls|slim量化版模型，对检测到的文本行文字角度分类|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)| 2.1M |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) |
-|ch_ppocr_mobile_v2.0_cls|原始模型|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)|1.38M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |
+|ch_ppocr_mobile_v2.0_cls|原始分类器模型，对检测到的文本行文字角度分类|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)|1.38M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |
 <a name="Paddle-Lite模型"></a>
 ### 四、Paddle-Lite 模型
 |模型版本|模型简介|模型大小|检测模型|文本方向分类模型|识别模型|Paddle-Lite版本|
 |---|---|---|---|---|---|---|
-|V2.0|超轻量中文OCR 移动端模型|7.8M|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_det_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_rec_opt.nb)|v2.9|
+|V2.1|ppocr_v2.1蒸馏版超轻量中文OCR移动端模型|11M|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_infer_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_infer_opt.nb)|v2.9|
-|V2.0(slim)|超轻量中文OCR 移动端模型|3.3M|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_det_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_rec_slim_opt.nb)|v2.9|
+|V2.1(slim)|ppocr_v2.1蒸馏版超轻量中文OCR移动端模型|4.9M|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_slim_opt.nb)|v2.9|
+|V2.0|ppocr_v2.0超轻量中文OCR移动端模型|7.8M|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_det_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_rec_opt.nb)|v2.9|
+|V2.0(slim)|ppocr_v2.0超轻量中文OCR移动端模型|3.3M|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_det_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_rec_slim_opt.nb)|v2.9|
--- a/doc/doc_ch/recognition.md
+++ b/doc/doc_ch/recognition.md
-## 文字识别
+# 文字识别
+本文提供了PaddleOCR文本识别任务的全流程指南，包括数据准备、模型训练、调优、评估、预测，各个阶段的详细说明：
 - [1 数据准备](#数据准备)
    - [1.1 自定义数据集](#自定义数据集)
@@ -9,22 +10,21 @@
 - [2 启动训练](#启动训练)
    - [2.1 数据增强](#数据增强)
-    - [2.2 训练](#训练)
+    - [2.2 通用模型训练](#通用模型训练)
-    - [2.3 小语种](#小语种)
+    - [2.3 多语言模型训练](#多语言模型训练)
 - [3 评估](#评估)
 - [4 预测](#预测)
-    - [4.1 训练引擎预测](#训练引擎预测)
 <a name="数据准备"></a>
-### 1. 数据准备
+## 1. 数据准备
 PaddleOCR 支持两种数据格式:
- - `lmdb` 用于训练以lmdb格式存储的数据集;
+ - `lmdb` 用于训练以lmdb格式存储的数据集(LMDBDataSet);
- - `通用数据` 用于训练以文本文件存储的数据集:
+ - `通用数据` 用于训练以文本文件存储的数据集(SimpleDataSet);
 训练数据的默认存储路径是 `PaddleOCR/train_data`,如果您的磁盘上已有数据集，只需创建软链接至数据集目录：
@@ -36,7 +36,7 @@ mklink /d <path/to/paddle_ocr>/train_data/dataset <path/to/dataset>
 ```
 <a name="准备数据集"></a>
-#### 1.1 自定义数据集
+### 1.1 自定义数据集
 下面以通用数据集为例， 介绍如何准备数据集：
 * 训练集
@@ -82,14 +82,13 @@ train_data/rec/train/word_002.jpg   用科技让复杂的世界更简单
 <a name="数据下载"></a>
-1.2 数据下载
+### 1.2 数据下载
-若您本地没有数据集，可以在官网下载 [icdar2015](http://rrc.cvc.uab.es/?ch=4&com=downloads) 数据，用于快速验证。也可以参考[DTRB](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here) ，下载 benchmark 所需的lmdb格式数据集。
+- ICDAR2015
-如果你使用的是icdar2015的公开数据集，PaddleOCR 提供了一份用于训练 icdar2015 数据集的标签文件，通过以下方式下载：
+若您本地没有数据集，可以在官网下载 [ICDAR2015](http://rrc.cvc.uab.es/?ch=4&com=downloads) 数据，用于快速验证。也可以参考[DTRB](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here) ，下载 benchmark 所需的lmdb格式数据集。
-如果希望复现SRN的论文指标，需要下载离线[增广数据](https://pan.baidu.com/s/1-HSZ-ZVdqBF2HaBZ5pRAKA),提取码: y3ry。增广数据是由MJSynth和SynthText做旋转和扰动得到的。数据下载完成后请解压到 {your_path}/PaddleOCR/train_data/data_lmdb_release/training/ 路径下。
+如果你使用的是icdar2015的公开数据集，PaddleOCR 提供了一份用于训练 ICDAR2015 数据集的标签文件，通过以下方式下载：
 ```
 # 训练集标签
 wget -P ./train_data/ic15_data  https://paddleocr.bj.bcebos.com/dataset/rec_gt_train.txt
@@ -97,15 +96,25 @@ wget -P ./train_data/ic15_data  https://paddleocr.bj.bcebos.com/dataset/rec_gt_t
 wget -P ./train_data/ic15_data  https://paddleocr.bj.bcebos.com/dataset/rec_gt_test.txt
 ```
-PaddleOCR 也提供了数据格式转换脚本，可以将官网 label 转换支持的数据格式。 数据转换工具在 `ppocr/utils/gen_label.py`, 这里以训练集为例：
+PaddleOCR 也提供了数据格式转换脚本，可以将ICDAR官网 label 转换为PaddleOCR支持的数据格式。 数据转换工具在 `ppocr/utils/gen_label.py`, 这里以训练集为例：
 ```
 # 将官网下载的标签文件转换为 rec_gt_label.txt
 python gen_label.py --mode="rec" --input_path="{path/of/origin/label}" --output_label="rec_gt_label.txt"
 ```
+数据样式格式如下，(a)为原始图片,(b)为每张图片对应的 Ground Truth 文本文件：
+![](../datasets/icdar_rec.png)
+- 多语言数据集
+多语言模型的训练数据集均为100w的合成数据，使用了开源合成工具 [text_renderer](https://github.com/Sanster/text_renderer) ，少量的字体可以通过下面两种方式下载。
+* [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) 提取码：frgi
+* [google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)
 <a name="字典"></a>
-1.3 字典
+### 1.3 字典
 最后需要提供一个字典（{word_dict_name}.txt），使模型在训练时，可以将所有出现的字符映射为字典的索引。
@@ -152,13 +161,27 @@ PaddleOCR内置了一部分字典，可以按需使用。
 并将 `character_type` 设置为 `ch`。
 <a name="支持空格"></a>
-1.4 添加空格类别
+### 1.4 添加空格类别
 如果希望支持识别"空格"类别, 请将yml文件中的 `use_space_char` 字段设置为 `True`。
 <a name="启动训练"></a>
-### 2. 启动训练
+## 2. 启动训练
+<a name="数据增强"></a>
+### 2.1 数据增强
+PaddleOCR提供了多种数据增强方式，默认配置文件中已经添加了数据增广。
+默认的扰动方式有：颜色空间转换(cvtColor)、模糊(blur)、抖动(jitter)、噪声(Gasuss noise)、随机切割(random crop)、透视(perspective)、颜色反转(reverse)、TIA数据增广。
+训练过程中每种扰动方式以40%的概率被选择，具体代码实现请参考：[rec_img_aug.py](../../ppocr/data/imaug/rec_img_aug.py)
+*由于OpenCV的兼容性问题，扰动操作暂时只支持Linux*
+<a name="通用模型训练"></a>
+### 2.2 通用模型训练
 PaddleOCR提供了训练脚本、评估脚本和预测脚本，本节将以 CRNN 识别模型为例：
@@ -178,23 +201,16 @@ tar -xf rec_mv3_none_bilstm_ctc_v2.0_train.tar && rm -rf rec_mv3_none_bilstm_ctc
 *如果您安装的是cpu版本，请将配置文件中的 `use_gpu` 字段修改为false*
 ```
-# GPU训练 支持单卡，多卡训练，通过--gpus参数指定卡号
+# GPU训练 支持单卡，多卡训练
 # 训练icdar15英文数据 训练日志会自动保存为 "{save_model_dir}" 下的train.log
-python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_icdar15_train.yml
-```
-<a name="数据增强"></a>
-#### 2.1 数据增强
-PaddleOCR提供了多种数据增强方式，默认配置文件中已经添加了数据增广。
-默认的扰动方式有：颜色空间转换(cvtColor)、模糊(blur)、抖动(jitter)、噪声(Gasuss noise)、随机切割(random crop)、透视(perspective)、颜色反转(reverse)、TIA数据增广。
+#单卡训练（训练周期长，不建议）
+python3 tools/train.py -c configs/rec/rec_icdar15_train.yml
-训练过程中每种扰动方式以40%的概率被选择，具体代码实现请参考：[rec_img_aug.py](../../ppocr/data/imaug/rec_img_aug.py)
+#多卡训练，通过--gpus参数指定卡号
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_icdar15_train.yml
-*由于OpenCV的兼容性问题，扰动操作暂时只支持Linux*
+```
-<a name="训练"></a>
-#### 2.2 训练
 PaddleOCR支持训练和评估交替进行, 可以在 `configs/rec/rec_icdar15_train.yml` 中修改 `eval_batch_step` 设置评估频率，默认每500个iter评估一次。评估过程中默认将最佳acc模型，保存为 `output/rec_CRNN/best_accuracy` 。
@@ -283,85 +299,12 @@ Eval:
 ```
 **注意，预测/评估时的配置文件请务必与训练一致。**
-<a name="小语种"></a>
+<a name="多语言模型训练"></a>
-#### 2.3 小语种
+### 2.3 多语言模型训练
 PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi_languages` 路径下提供了一个多语言的配置文件模版: [rec_multi_language_lite_train.yml](../../configs/rec/multi_language/rec_multi_language_lite_train.yml)。
-您有两种方式创建所需的配置文件：
+按语系划分，目前PaddleOCR支持的语种有：
-1. 通过脚本自动生成
-[generate_multi_language_configs.py](../../configs/rec/multi_language/generate_multi_language_configs.py) 可以帮助您生成多语言模型的配置文件
- 以意大利语为例，如果您的数据是按如下格式准备的：
-    ```
-    |-train_data
-        |- it_train.txt # 训练集标签
-        |- it_val.txt # 验证集标签
-        |- data
-            |- word_001.jpg
-            |- word_002.jpg
-            |- word_003.jpg
-            | ...
-    ```
-    可以使用默认参数，生成配置文件：
-    ```bash
-    # 该代码需要在指定目录运行
-    cd PaddleOCR/configs/rec/multi_language/
-    # 通过-l或者--language参数设置需要生成的语种的配置文件，该命令会将默认参数写入配置文件
-    python3 generate_multi_language_configs.py -l it
-    ```
- 如果您的数据放置在其他位置，或希望使用自己的字典，可以通过指定相关参数来生成配置文件:
-    ```bash
-    # -l或者--language字段是必须的
-    # --train修改训练集，--val修改验证集，--data_dir修改数据集目录，--dict修改字典路径， -o修改对应默认参数
-    cd PaddleOCR/configs/rec/multi_language/
-    python3 generate_multi_language_configs.py -l it \  # 语种
-    --train {path/of/train_label.txt} \ # 训练标签文件的路径
-    --val {path/of/val_label.txt} \     # 验证集标签文件的路径
-    --data_dir {train_data/path} \      # 训练数据的根目录
-    --dict {path/of/dict} \             # 字典文件路径
-    -o Global.use_gpu=False             # 是否使用gpu
-    ...
-    ```
-意大利文由拉丁字母组成，因此执行完命令后会得到名为 rec_latin_lite_train.yml 的配置文件。
-2. 手动修改配置文件
-   您也可以手动修改模版中的以下几个字段:
-   ```
-    Global:
-      use_gpu: True
-      epoch_num: 500
-      ...
-      character_type: it  # 需要识别的语种
-      character_dict_path:  {path/of/dict} # 字典文件所在路径
-   Train:
-      dataset:
-        name: SimpleDataSet
-        data_dir: train_data/ # 数据存放根目录
-        label_file_list: ["./train_data/train_list.txt"] # 训练集label路径
-      ...
-   Eval:
-      dataset:
-        name: SimpleDataSet
-        data_dir: train_data/ # 数据存放根目录
-        label_file_list: ["./train_data/val_list.txt"] # 验证集label路径
-      ...
-   ```
-目前PaddleOCR支持的多语言算法有：
 | 配置文件 |  算法名称 |   backbone |   trans   |   seq      |     pred     |  language | character_type |
 | :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   | :-----:  | :-----:  |
@@ -378,10 +321,6 @@ PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi
 更多支持语种请参考: [多语言模型](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_ch/multi_languages.md#%E8%AF%AD%E7%A7%8D%E7%BC%A9%E5%86%99)
-多语言模型训练方式与中文模型一致，训练数据集均为100w的合成数据，少量的字体可以通过下面两种方式下载。
-* [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA)。提取码：frgi。
-* [google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)
 如您希望在现有模型效果的基础上调优，请参考下列说明修改配置文件：
 以 `rec_french_lite_train` 为例：
@@ -417,7 +356,7 @@ Eval:
    ...
 ```
 <a name="评估"></a>
-### 3 评估
+## 3 评估
 评估数据集可以通过 `configs/rec/rec_icdar15_train.yml`  修改Eval中的 `label_file_path` 设置。
@@ -427,14 +366,29 @@ python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec
 ```
 <a name="预测"></a>
-### 4 预测
+## 4 预测
-<a name="训练引擎预测"></a>
-#### 4.1 训练引擎的预测
 使用 PaddleOCR 训练好的模型，可以通过以下脚本进行快速预测。
-默认预测图片存储在 `infer_img` 里，通过 `-o Global.checkpoints` 指定权重：
+默认预测图片存储在 `infer_img` 里，通过 `-o Global.checkpoints` 加载训练好的参数文件：
+根据配置文件中设置的的 `save_model_dir` 和 `save_epoch_step` 字段，会有以下几种参数被保存下来：
+```
+output/rec/
+├── best_accuracy.pdopt  
+├── best_accuracy.pdparams  
+├── best_accuracy.states  
+├── config.yml  
+├── iter_epoch_3.pdopt  
+├── iter_epoch_3.pdparams  
+├── iter_epoch_3.states  
+├── latest.pdopt  
+├── latest.pdparams  
+├── latest.states  
+└── train.log
+```
+其中 best_accuracy.* 是评估集上的最优模型；iter_epoch_x.* 是以 `save_epoch_step` 为间隔保存下来的模型；latest.* 是最后一个epoch的模型。
 ```
 # 预测英文结果

--- a/doc/doc_ch/training.md
+++ b/doc/doc_ch/training.md
+# 模型训练
+本文将介绍模型训练时需掌握的基本概念，和训练时的调优方法。
+同时会简单介绍PaddleOCR模型训练数据的组成部分，以及如何在垂类场景中准备数据finetune模型。
+- [1. 基本概念](#基本概念)
+  * [1.1 学习率](#学习率)
+  * [1.2 正则化](#正则化)
+  * [1.3 评估指标](#评估指标)
+- [2. 常见问题](#常见问题)
+- [3. 数据与垂类场景](#数据与垂类场景)
+  * [3.1 训练数据](#训练数据)
+  * [3.2 垂类场景](#垂类场景)
+  * [3.3 自己构建数据集](#自己构建数据集)
+<a name="基本概念"></a>
+## 1. 基本概念
+OCR(Optical Character Recognition,光学字符识别)是指对图像进行分析识别处理，获取文字和版面信息的过程，是典型的计算机视觉任务，
+通常由文本检测和文本识别两个子任务构成。
+模型调优时需要关注以下参数：
+<a name="学习率"></a>
+### 1.1 学习率
+学习率是训练神经网络的重要超参数之一，它代表在每一次迭代中梯度向损失函数最优解移动的步长。
+在PaddleOCR中提供了多种学习率更新策略,可以通过配置文件修改，例如：
+```
+Optimizer:
+  ...
+  lr:
+    name: Piecewise
+    decay_epochs : [700, 800]
+    values : [0.001, 0.0001]
+    warmup_epoch: 5
+```
+Piecewise 代表分段常数衰减，在不同的学习阶段指定不同的学习率，在每段内学习率相同。
+warmup_epoch 代表在前5个epoch中，学习率将逐渐从0增加到base_lr。全部策略可以参考代码[learning_rate.py](../../ppocr/optimizer/learning_rate.py) 。
+<a name="正则化"></a>
+### 1.2 正则化
+正则化可以有效的避免算法过拟合，PaddleOCR中提供了L1、L2正则方法，L1 和 L2 正则化是最常用的正则化方法。L1 正则化向目标函数添加正则化项，以减少参数的绝对值总和；而 L2 正则化中，添加正则化项的目的在于减少参数平方的总和。配置方法如下：
+```
+Optimizer:
+  ...
+  regularizer:
+    name: L2
+    factor: 2.0e-05
+```
+<a name="评估指标"></a>
+### 1.3 评估指标
+（1）检测阶段：先按照检测框和标注框的IOU评估，IOU大于某个阈值判断为检测准确。这里检测框和标注框不同于一般的通用目标检测框，是采用多边形进行表示。检测准确率：正确的检测框个数在全部检测框的占比，主要是判断检测指标。检测召回率：正确的检测框个数在全部标注框的占比，主要是判断漏检的指标。
+（2）识别阶段： 字符识别准确率，即正确识别的文本行占标注的文本行数量的比例，只有整行文本识别对才算正确识别。
+（3）端到端统计： 端对端召回率：准确检测并正确识别文本行在全部标注文本行的占比； 端到端准确率：准确检测并正确识别文本行在 检测到的文本行数量 的占比； 准确检测的标准是检测框与标注框的IOU大于某个阈值，正确识别的的检测框中的文本与标注的文本相同。
+<a name="常见问题"></a>
+## 2. 常见问题
+**Q**：训练CRNN识别时，如何选择合适的网络输入shape？
+    A：一般高度采用32，最长宽度的选择，有两种方法：
+    （1）统计训练样本图像的宽高比分布。最大宽高比的选取考虑满足80%的训练样本。
+    （2）统计训练样本文字数目。最长字符数目的选取考虑满足80%的训练样本。然后中文字符长宽比近似认为是1，英文认为3：1，预估一个最长宽度。
+**Q**：识别训练时，训练集精度已经到达90了，但验证集精度一直在70，涨不上去怎么办？
+    A：训练集精度90，测试集70多的话，应该是过拟合了，有两个可尝试的方法：
+    （1）加入更多的增广方式或者调大增广prob的[概率](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/ppocr/data/imaug/rec_img_aug.py#L341)，默认为0.4。
+    （2）调大系统的[l2 dcay值](https://github.com/PaddlePaddle/PaddleOCR/blob/a501603d54ff5513fc4fc760319472e59da25424/configs/rec/ch_ppocr_v1.1/rec_chinese_lite_train_v1.1.yml#L47)
+**Q**: 识别模型训练时，loss能正常下降，但acc一直为0
+    A：识别模型训练初期acc为0是正常的，多训一段时间指标就上来了。
+<a name="数据与垂类场景"></a>
+## 3. 数据与垂类场景
+<a name="训练数据"></a>
+### 3.1 训练数据
+目前开源的模型，数据集和量级如下：
+    - 检测：  
+        - 英文数据集，ICDAR2015  
+        - 中文数据集，LSVT街景数据集训练数据3w张图片
+    - 识别：  
+        - 英文数据集，MJSynth和SynthText合成数据，数据量上千万。  
+        - 中文数据集，LSVT街景数据集根据真值将图crop出来，并进行位置校准，总共30w张图像。此外基于LSVT的语料，合成数据500w。
+        - 小语种数据集，使用不同语料和字体，分别生成了100w合成数据集，并使用ICDAR-MLT作为验证集。
+其中，公开数据集都是开源的，用户可自行搜索下载，也可参考[中文数据集](./datasets.md)，合成数据暂不开源，用户可使用开源合成工具自行合成，可参考的合成工具包括[text_renderer](https://github.com/Sanster/text_renderer) 、[SynthText](https://github.com/ankush-me/SynthText) 、[TextRecognitionDataGenerator](https://github.com/Belval/TextRecognitionDataGenerator) 等。
+<a name="垂类场景"></a>
+### 3.2 垂类场景
+PaddleOCR主要聚焦通用OCR，如果有垂类需求，您可以用PaddleOCR+垂类数据自己训练；
+如果缺少带标注的数据，或者不想投入研发成本，建议直接调用开放的API，开放的API覆盖了目前比较常见的一些垂类。
+<a name="自己构建数据集"></a>
+### 3.3 自己构建数据集
+在构建数据集时有几个经验可供参考：
+（1） 训练集的数据量：
+    a. 检测需要的数据相对较少，在PaddleOCR模型的基础上进行Fine-tune，一般需要500张可达到不错的效果。
+    b. 识别分英文和中文，一般英文场景需要几十万数据可达到不错的效果，中文则需要几百万甚至更多。
+（2）当训练数据量少时，可以尝试以下三种方式获取更多的数据：
+    a. 人工采集更多的训练数据，最直接也是最有效的方式。
+    b. 基于PIL和opencv基本图像处理或者变换。例如PIL中ImageFont, Image, ImageDraw三个模块将文字写到背景中，opencv的旋转仿射变换，高斯滤波等。
+    c. 利用数据生成算法合成数据，例如pix2pix或StyleText等算法。
--- a/doc/doc_en/config_en.md
+++ b/doc/doc_en/config_en.md
@@ -51,7 +51,7 @@ Take rec_chinese_lite_train_v2.0.yml as an example
 ### Architecture ([ppocr/modeling](../../ppocr/modeling))
-In ppocr, the network is divided into four stages: Transform, Backbone, Neck and Head
+In PaddleOCR, the network is divided into four stages: Transform, Backbone, Neck and Head
 |         Parameter             |            Use            |      Defaults        |            Note             |
 | :---------------------: |  :---------------------:   | :--------------:  |   :--------------------:   |
@@ -120,3 +120,108 @@ In ppocr, the network is divided into four stages: Transform, Backbone, Neck and
 |      batch_size_per_card        |        Single card batch size during training         |  256 | \  |
 |      drop_last        |        Whether to discard the last incomplete mini-batch because the number of samples in the data set cannot be divisible by batch_size        |  True | \  |
 |      num_workers        |        The number of sub-processes used to load data, if it is 0, the sub-process is not started, and the data is loaded in the main process       |  8 | \  |
+## 3. MULTILINGUAL CONFIG FILE GENERATION
+PaddleOCR currently supports 80 (except Chinese) language recognition. A multi-language configuration file template is
+provided under the path `configs/rec/multi_languages`: [rec_multi_language_lite_train.yml](../../configs/rec/multi_language/rec_multi_language_lite_train.yml)。
+There are two ways to create the required configuration file:：
+1. Automatically generated by script
+[generate_multi_language_configs.py](../../configs/rec/multi_language/generate_multi_language_configs.py) Can help you generate configuration files for multi-language models
+- Take Italian as an example, if your data is prepared in the following format:
+    ```
+    |-train_data
+        |- it_train.txt # train_set label
+        |- it_val.txt # val_set label
+        |- data
+            |- word_001.jpg
+            |- word_002.jpg
+            |- word_003.jpg
+            | ...
+    ```
+    You can use the default parameters to generate a configuration file:
+    ```bash
+    # The code needs to be run in the specified directory
+    cd PaddleOCR/configs/rec/multi_language/
+    # Set the configuration file of the language to be generated through the -l or --language parameter.
+    # This command will write the default parameters into the configuration file
+    python3 generate_multi_language_configs.py -l it
+    ```
+- If your data is placed in another location, or you want to use your own dictionary, you can generate the configuration file by specifying the relevant parameters:
+    ```bash
+    # -l or --language field is required
+    # --train to modify the training set
+    # --val to modify the validation set
+    # --data_dir to modify the data set directory
+    # --dict to modify the dict path
+    # -o to modify the corresponding default parameters
+    cd PaddleOCR/configs/rec/multi_language/
+    python3 generate_multi_language_configs.py -l it \  # language
+    --train {path/of/train_label.txt} \ # path of train_label
+    --val {path/of/val_label.txt} \     # path of val_label
+    --data_dir {train_data/path} \      # root directory of training data
+    --dict {path/of/dict} \             # path of dict
+    -o Global.use_gpu=False             # whether to use gpu
+    ...
+    ```
+Italian is made up of Latin letters, so after executing the command, you will get the rec_latin_lite_train.yml.
+2. Manually modify the configuration file
+   You can also manually modify the following fields in the template:
+   ```
+    Global:
+      use_gpu: True
+      epoch_num: 500
+      ...
+      character_type: it  # language
+      character_dict_path:  {path/of/dict} # path of dict
+   Train:
+      dataset:
+        name: SimpleDataSet
+        data_dir: train_data/ # root directory of training data
+        label_file_list: ["./train_data/train_list.txt"] # train label path
+      ...
+   Eval:
+      dataset:
+        name: SimpleDataSet
+        data_dir: train_data/ # root directory of val data
+        label_file_list: ["./train_data/val_list.txt"] # val label path
+      ...
+   ```
+Currently, the multi-language algorithms supported by PaddleOCR are:
+| Configuration file |  Algorithm name |   backbone |   trans   |   seq      |     pred     |  language | character_type |
+| :--------: |  :-------:   | :-------:  |   :-------:   |   :-----:   |  :-----:   | :-----:  | :-----:  |
+| rec_chinese_cht_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | chinese traditional  | chinese_cht|
+| rec_en_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | English(Case sensitive)   | EN |
+| rec_french_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | French |  french |
+| rec_ger_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | German   | german |
+| rec_japan_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | Japanese | japan |
+| rec_korean_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | Korean  | korean |
+| rec_latin_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | Latin  | latin |
+| rec_arabic_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | arabic |  ar |
+| rec_cyrillic_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | cyrillic   | cyrillic |
+| rec_devanagari_lite_train.yml |  CRNN |   Mobilenet_v3 small 0.5 |  None   |  BiLSTM |  ctc  | devanagari  | devanagari |
+For more supported languages, please refer to : [Multi-language model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md#4-support-languages-and-abbreviations)
+The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded using the following two methods.
+* [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA),Extraction code:frgi.
+* [Google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)
--- a/doc/doc_en/detection_en.md
+++ b/doc/doc_en/detection_en.md
-# TEXT DETECTION
+# CONTENT
+- [Paste Your Document In Here](#paste-your-document-in-here)
+- [1. TEXT DETECTION](#1-text-detection)
+  * [1.1 DATA PREPARATION](#11-data-preparation)
+  * [1.2 DOWNLOAD PRETRAINED MODEL](#12-download-pretrained-model)
+  * [1.3 START TRAINING](#13-start-training)
+  * [1.4 LOAD TRAINED MODEL AND CONTINUE TRAINING](#14-load-trained-model-and-continue-training)
+  * [1.5 TRAINING WITH NEW BACKBONE](#15-training-with-new-backbone)
+  * [1.6 EVALUATION](#16-evaluation)
+  * [1.7 TEST](#17-test)
+  * [1.8 INFERENCE MODEL PREDICTION](#18-inference-model-prediction)
+- [2. FAQ](#2-faq)
+# 1. TEXT DETECTION
 This section uses the icdar2015 dataset as an example to introduce the training, evaluation, and testing of the detection model in PaddleOCR.
-## DATA PREPARATION
+## 1.1 DATA PREPARATION
 The icdar2015 dataset can be obtained from [official website](https://rrc.cvc.uab.es/?ch=4&com=downloads). Registration is required for downloading.
+After registering and logging in, download the part marked in the red box in the figure below. And, the content downloaded by `Training Set Images` should be saved as the folder `icdar_c4_train_imgs`, and the content downloaded by `Test Set Images` is saved as the folder `ch4_test_images`
+<p align="center">
+ <img src="./doc/datasets/ic15_location_download.png" align="middle" width = "600"/>
+<p align="center">
 Decompress the downloaded dataset to the working directory, assuming it is decompressed under PaddleOCR/train_data/. In addition, PaddleOCR organizes many scattered annotation files into two separate annotation files for train and test respectively, which can be downloaded by wget:
 ```shell
 # Under the PaddleOCR path
@@ -36,10 +58,11 @@ The `points` in the dictionary represent the coordinates (x, y) of the four poin
 If you want to train PaddleOCR on other datasets, please build the annotation file according to the above format.
-## TRAINING
+## 1.2 DOWNLOAD PRETRAINED MODEL
+First download the pretrained model. The detection model of PaddleOCR currently supports 3 backbones, namely MobileNetV3, ResNet18_vd and ResNet50_vd. You can use the model in [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/tree/release/2.0/ppcls/modeling/architectures) to replace backbone according to your needs.
+And the responding download link of backbone pretrain weights can be found in (https://github.com/PaddlePaddle/PaddleClas/blob/release%2F2.0/README_cn.md#resnet%E5%8F%8A%E5%85%B6vd%E7%B3%BB%E5%88%97).
-First download the pretrained model. The detection model of PaddleOCR currently supports 3 backbones, namely MobileNetV3, ResNet18_vd and ResNet50_vd. You can use the model in [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/tree/develop/ppcls/modeling/architectures) to replace backbone according to your needs.
-And the responding download link of backbone pretrain weights can be found in [PaddleClas repo](https://github.com/PaddlePaddle/PaddleClas#mobile-series).
 ```shell
 cd PaddleOCR/
 # Download the pre-trained model of MobileNetV3
@@ -49,11 +72,13 @@ wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dyg
 # or, download the pre-trained model of ResNet50_vd
 wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_pretrained.pdparams
+```
-#### START TRAINING
+## 1.3 START TRAINING
 *If CPU version installed, please set the parameter `use_gpu` to `false` in the configuration.*
 ```shell
-python3 tools/train.py -c configs/det/det_mv3_db.yml
+python3 tools/train.py -c configs/det/det_mv3_db.yml  \
+         -o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained
 ```
 In the above instruction, use `-c` to select the training to use the `configs/det/det_db_mv3.yml` configuration file.
@@ -62,16 +87,17 @@ For a detailed explanation of the configuration file, please refer to [config](.
 You can also use `-o` to change the training parameters without modifying the yml file. For example, adjust the training learning rate to 0.0001
 ```shell
 # single GPU training
-python3 tools/train.py -c configs/det/det_mv3_db.yml -o Optimizer.base_lr=0.0001
+python3 tools/train.py -c configs/det/det_mv3_db.yml -o   \
+         Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained  \
+         Optimizer.base_lr=0.0001
 # multi-GPU training
 # Set the GPU ID used by the '--gpus' parameter.
-python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/det/det_mv3_db.yml -o Optimizer.base_lr=0.0001
+python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/det/det_mv3_db.yml -o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained
 ```
-#### load trained model and continue training
+## 1.4 LOAD TRAINED MODEL AND CONTINUE TRAINING
 If you expect to load trained model and continue the training again, you can specify the parameter `Global.checkpoints` as the model path to be loaded.
 For example:
@@ -82,9 +108,59 @@ python3 tools/train.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=./you
 **Note**: The priority of `Global.checkpoints` is higher than that of `Global.pretrain_weights`, that is, when two parameters are specified at the same time, the model specified by `Global.checkpoints` will be loaded first. If the model path specified by `Global.checkpoints` is wrong, the one specified by `Global.pretrain_weights` will be loaded.
-## EVALUATION
+## 1.5 TRAINING WITH NEW BACKBONE
+The network part completes the construction of the network, and PaddleOCR divides the network into four parts, which are under [ppocr/modeling](../../ppocr/modeling). The data entering the network will pass through these four parts in sequence(transforms->backbones->
+necks->heads).
+```bash
+├── architectures # Code for building network
+├── transforms    # Image Transformation Module
+├── backbones     # Feature extraction module
+├── necks         # Feature enhancement module
+└── heads         # Output module
+```
+If the Backbone to be replaced has a corresponding implementation in PaddleOCR, you can directly modify the parameters in the `Backbone` part of the configuration yml file.
+However, if you want to use a new Backbone, an example of replacing the backbones is as follows:
+1. Create a new file under the [ppocr/modeling/backbones](../../ppocr/modeling/backbones) folder, such as my_backbone.py.
+2. Add code in the my_backbone.py file, the sample code is as follows:
+```python
+import paddle
+import paddle.nn as nn
+import paddle.nn.functional as F
+class MyBackbone(nn.Layer):
+    def __init__(self, *args, **kwargs):
+        super(MyBackbone, self).__init__()
+        # your init code
+        self.conv = nn.xxxx
+    def forward(self, inputs):
+        # your network forward
+        y = self.conv(inputs)
+        return y
+```
+3. Import the added module in the [ppocr/modeling/backbones/\__init\__.py](../../ppocr/modeling/backbones/__init__.py) file.
+After adding the four-part modules of the network, you only need to configure them in the configuration file to use, such as:
+```yaml
+  Backbone:
+    name: MyBackbone
+    args1: args1
+```
+**NOTE**: More details about replace Backbone and other mudule can be found in [doc](add_new_algorithm_en.md).
+## 1.6 EVALUATION
-PaddleOCR calculates three indicators for evaluating performance of OCR detection task: Precision, Recall, and Hmean.
+PaddleOCR calculates three indicators for evaluating performance of OCR detection task: Precision, Recall, and Hmean(F-Score).
 Run the following code to calculate the evaluation indicators. The result will be saved in the test result file specified by `save_res_path` in the configuration file `det_db_mv3.yml`
@@ -95,10 +171,9 @@ The model parameters during training are saved in the `Global.save_model_dir` di
 python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.checkpoints="{path/to/weights}/best_accuracy" PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
 ```
+* Note: `box_thresh` and `unclip_ratio` are parameters required for DB post-processing, and not need to be set when evaluating the EAST and SAST model.
-* Note: `box_thresh` and `unclip_ratio` are parameters required for DB post-processing, and not need to be set when evaluating the EAST model.
+## 1.7 TEST
-## TEST
 Test the detection result on a single image:
 ```shell
@@ -107,7 +182,7 @@ python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./
 When testing the DB model, adjust the post-processing threshold:
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy"  PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy"  PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=2.0
 ```
@@ -115,3 +190,33 @@ Test the detection result on all images in the folder:
 ```shell
 python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy"
 ```
+## 1.8 INFERENCE MODEL PREDICTION
+The inference model (the model saved by `paddle.jit.save`) is generally a solidified model saved after the model training is completed, and is mostly used to give prediction in deployment.
+The model saved during the training process is the checkpoints model, which saves the parameters of the model and is mostly used to resume training.
+Compared with the checkpoints model, the inference model will additionally save the structural information of the model. Therefore, it is easier to deploy because the model structure and model parameters are already solidified in the inference model file, and is suitable for integration with actual systems.
+Firstly, we can convert DB trained model to inference model:
+```shell
+python3 tools/export_model.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model="./output/det_db/best_accuracy" Global.save_inference_dir="./output/det_db_inference/"
+```
+The detection inference model prediction：
+```shell
+python3 tools/infer/predict_det.py --det_algorithm="DB" --det_model_dir="./output/det_db_inference/" --image_dir="./doc/imgs/" --use_gpu=True
+```
+If it is other detection algorithms, such as the EAST, the det_algorithm parameter needs to be modified to EAST, and the default is the DB algorithm:
+```shell
+python3 tools/infer/predict_det.py --det_algorithm="EAST" --det_model_dir="./output/det_db_inference/" --image_dir="./doc/imgs/" --use_gpu=True
+```
+# 2. FAQ
+Q1: The prediction results of trained model and inference model are inconsistent?
+**A**: Most of the problems are caused by the inconsistency of the pre-processing and post-processing parameters during the prediction of the trained model and the pre-processing and post-processing parameters during the prediction of the inference model. Taking the model trained by the det_mv3_db.yml configuration file as an example, the solution to the problem of inconsistent prediction results between the training model and the inference model is as follows:
+- Check whether the [trained model preprocessing](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L116) is consistent with the prediction [preprocessing function of the inference model](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/predict_det.py#L42). When the algorithm is evaluated, the input image size will affect the accuracy. In order to be consistent with the paper, the image is resized to [736, 1280] in the training icdar15 configuration file, but there is only a set of default parameters when the inference model predicts, which will be considered To predict the speed problem, the longest side of the image is limited to 960 for resize by default. The preprocessing function of the training model preprocessing and the inference model is located in [ppocr/data/imaug/operators.py](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/ppocr/data/imaug/operators.py#L147)
+- Check whether the [post-processing of the trained model](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L51) is consistent with the [post-processing parameters of the inference](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/utility.py#L50).
--- a/doc/doc_en/models_and_config_en.md
+++ b/doc/doc_en/models_and_config_en.md
+# CONTENT
+- [Paste Your Document In Here](#paste-your-document-in-here)
+- [INTRODUCTION ABOUT OCR](#introduction-about-ocr)
+  * [BASIC CONCEPTS OF OCR DETECTION MODEL](#basic-concepts-of-ocr-detection-model)
+  * [Basic concepts of OCR recognition model](#basic-concepts-of-ocr-recognition-model)
+  * [PP-OCR model](#pp-ocr-model)
+  * [And a table of contents](#and-a-table-of-contents)
+  * [On the right](#on-the-right)
+# INTRODUCTION ABOUT OCR
+This section briefly introduces the basic concepts of OCR detection model and recognition model, and introduces PaddleOCR's PP-OCR model.
+OCR (Optical Character Recognition, Optical Character Recognition) is currently the general term for text recognition. It is not limited to document or book text recognition, but also includes recognizing text in natural scenes. It can also be called STR (Scene Text Recognition).
+OCR text recognition generally includes two parts, text detection and text recognition. The text detection module first uses detection algorithms to detect text lines in the image. And then the recognition algorithm to identify the specific text in the text line.
+## BASIC CONCEPTS OF OCR DETECTION MODEL
+Text detection can locate the text area in the image, and then usually mark the word or text line in the form of a bounding box. Traditional text detection algorithms mostly extract features manually, which are characterized by fast speed and good effect in simple scenes, but the effect will be greatly reduced when faced with natural scenes. Currently, deep learning methods are mostly used.
+Text detection algorithms based on deep learning can be roughly divided into the following categories:
+1. Method based on target detection. Generally, after the text box is predicted, the final text box is filtered through NMS, which is mostly four-point text box, which is not ideal for curved text scenes. Typical algorithms are methods such as EAST and Text Box.
+2. Method based on text segmentation. The text line is regarded as the segmentation target, and then the external text box is constructed through the segmentation result, which can handle curved text, and the effect is not ideal for the text cross scene problem. Typical algorithms are DB, PSENet and other methods.
+3. Hybrid target detection and segmentation method.
+## Basic concepts of OCR recognition model
+The input of the OCR recognition algorithm is generally text lines images which has less background information, and the text information occupies the main part. The recognition algorithm can be divided into two types of algorithms:
+1. CTC-based method. The text prediction module of the recognition algorithm is based on CTC, and the commonly used algorithm combination is CNN+RNN+CTC. There are also some algorithms that try to add transformer modules to the network and so on.
+2. Attention-based method. The text prediction module of the recognition algorithm is based on Attention, and the commonly used algorithm combination is CNN+RNN+Attention.
+## PP-OCR model
+PaddleOCR integrates many OCR algorithms, text detection algorithms include DB, EAST, SAST, etc., text recognition algorithms include CRNN, RARE, StarNet, Rosetta, SRN and other algorithms.
+Among them, PaddleOCR has released the PP-OCR series model for the general OCR in Chinese and English natural scenes. The PP-OCR model is composed of the DB+CRNN algorithm. It uses massive Chinese data training and model tuning methods to have high text detection and recognition capabilities in Chinese scenes. And PaddleOCR has launched a high-precision and ultra-lightweight PP-OCRv2 model. The detection model is only 3M, and the recognition model is only 8.5M. Using [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim)'s model quantification method, the detection model can be compressed to 0.8M without reducing the accuracy. The recognition is compressed to 3M, which is more suitable for mobile deployment scenarios.
--- a/doc/doc_en/models_list_en.md
+++ b/doc/doc_en/models_list_en.md
@@ -28,6 +28,8 @@ Relationship of the above models is as follows.
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
+|ch_ppocr_mobile_slim_v2.1_det|slim quantization with distillation lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_lite_train_cml_v2.1.yml](../../configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml)| 3M |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_slim_quant_infer.tar)|
+|ch_ppocr_mobile_v2.1_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_lite_train_cml_v2.1.ym](../../configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_distill_train.tar)|
 |ch_ppocr_mobile_slim_v2.0_det|Slim pruned lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|2.6M |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_infer.tar)|
 |ch_ppocr_mobile_v2.0_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|
 |ch_ppocr_server_v2.0_det|General model, which is larger than the lightweight model, but achieved better performance|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)|
@@ -40,6 +42,8 @@ Relationship of the above models is as follows.
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
+|ch_ppocr_mobile_slim_v2.1_rec|Slim qunatization with distillation lightweight model, supporting Chinese, English, multilingual text detection|[rec_chinese_lite_train_distillation_v2.1.yml](../../configs/rec/ch_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml)| 9M |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_slim_quant_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_slim_quant_train.tar) |
+|ch_ppocr_mobile_v2.1_rec|Original lightweight model, supporting Chinese, English, multilingual text detection|[rec_chinese_lite_train_distillation_v2.1.yml](../../configs/rec/ch_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml)|8.5M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_train.tar) |
 |ch_ppocr_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)| 6M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_train.tar) |
 |ch_ppocr_mobile_v2.0_rec|Original lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)|5.2M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) |
 |ch_ppocr_server_v2.0_rec|General model, supporting Chinese, English and number recognition|[rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml)|94.8M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) |
@@ -120,12 +124,14 @@ For more supported languages, please refer to : [Multi-language model](./multi_l
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
-|ch_ppocr_mobile_slim_v2.0_cls|Slim quantized model|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)| 2.1M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_train.tar) |
+|ch_ppocr_mobile_slim_v2.0_cls|Slim quantized model for text angle classification|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)| 2.1M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_train.tar) |
-|ch_ppocr_mobile_v2.0_cls|Original model|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)|1.38M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |
+|ch_ppocr_mobile_v2.0_cls|Original model for text angle classification|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)|1.38M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |
 <a name="Paddle-Lite"></a>
 ### 4. Paddle-Lite Model
 |Version|Introduction|Model size|Detection model|Text Direction model|Recognition model|Paddle-Lite branch|
 |---|---|---|---|---|---|---|
-|V2.0|extra-lightweight chinese OCR optimized model|7.8M|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_det_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_rec_opt.nb)|v2.9|
+|V2.1|ppocr_v2.1 extra-lightweight chinese OCR optimized model|11M|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_infer_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_infer_opt.nb)|v2.9|
-|V2.0(slim)|extra-lightweight chinese OCR optimized model|3.3M|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_det_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_rec_slim_opt.nb)|v2.9|
+|V2.1(slim)|extra-lightweight chinese OCR optimized model|4.9M|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_det_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/chinese/ch_ppocr_mobile_v2.1_rec_slim_opt.nb)|v2.9|
+|V2.0|ppocr_v2.0 extra-lightweight chinese OCR optimized model|7.8M|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_det_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_rec_opt.nb)|v2.9|
+|V2.0(slim)|ppovr_v2.0 extra-lightweight chinese OCR optimized model|3.3M|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_det_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_slim_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_rec_slim_opt.nb)|v2.9|
--- a/doc/doc_en/recognition_en.md
+++ b/doc/doc_en/recognition_en.md
-## TEXT RECOGNITION
+# TEXT RECOGNITION
 - [1 DATA PREPARATION](#DATA_PREPARATION)
    - [1.1 Costom Dataset](#Costom_Dataset)
@@ -8,8 +8,8 @@
 - [2 TRAINING](#TRAINING)
    - [2.1 Data Augmentation](#Data_Augmentation)
-    - [2.2 Training](#Training)
+    - [2.2 General Training](#Training)
-    - [2.3 Multi-language](#Multi_language)
+    - [2.3 Multi-language Training](#Multi_language)
 - [3 EVALUATION](#EVALUATION)
@@ -17,12 +17,12 @@
    - [4.1 Training engine prediction](#Training_engine_prediction)
 <a name="DATA_PREPARATION"></a>
-### DATA PREPARATION
+## 1 DATA PREPARATION
 PaddleOCR supports two data formats:
- `LMDB` is used to train data sets stored in lmdb format;
+- `LMDB` is used to train data sets stored in lmdb format（LMDBDataSet）;
- `general data` is used to train data sets stored in text files:
+- `general data` is used to train data sets stored in text files（SimpleDataSet）:
 Please organize the dataset as follows:
@@ -36,7 +36,7 @@ mklink /d <path/to/paddle_ocr>/train_data/dataset <path/to/dataset>
 ```
 <a name="Costom_Dataset"></a>
-#### 1.1 Costom dataset
+### 1.1 Costom dataset
 If you want to use your own data for training, please refer to the following to organize your data.
@@ -84,11 +84,12 @@ Similar to the training set, the test set also needs to be provided a folder con
 ```
 <a name="Dataset_download"></a>
-#### 1.2 Dataset download
+### 1.2 Dataset download
-If you do not have a dataset locally, you can download it on the official website [icdar2015](http://rrc.cvc.uab.es/?ch=4&com=downloads). Also refer to [DTRB](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here) ，download the lmdb format dataset required for benchmark
+- ICDAR2015
-If you want to reproduce the paper indicators of SRN, you need to download offline [augmented data](https://pan.baidu.com/s/1-HSZ-ZVdqBF2HaBZ5pRAKA), extraction code: y3ry. The augmented data is obtained by rotation and perturbation of mjsynth and synthtext. Please unzip the data to {your_path}/PaddleOCR/train_data/data_lmdb_Release/training/path.
+If you do not have a dataset locally, you can download it on the official website [icdar2015](http://rrc.cvc.uab.es/?ch=4&com=downloads).
+Also refer to [DTRB](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here) ，download the lmdb format dataset required for benchmark
 PaddleOCR provides label files for training the icdar2015 dataset, which can be downloaded in the following ways:
@@ -99,8 +100,28 @@ wget -P ./train_data/ic15_data  https://paddleocr.bj.bcebos.com/dataset/rec_gt_t
 wget -P ./train_data/ic15_data  https://paddleocr.bj.bcebos.com/dataset/rec_gt_test.txt
 ```
+PaddleOCR also provides a data format conversion script, which can convert ICDAR official website label to a data format
+supported by PaddleOCR. The data conversion tool is in `ppocr/utils/gen_label.py`, here is the training set as an example:
+```
+# convert the official gt to rec_gt_label.txt
+python gen_label.py --mode="rec" --input_path="{path/of/origin/label}" --output_label="rec_gt_label.txt"
+```
+The data format is as follows, (a) is the original picture, (b) is the Ground Truth text file corresponding to each picture:
+![](../datasets/icdar_rec.png)
+- Multilingual dataset
+The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded using the following two methods.
+* [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) ,Extraction code:frgi.
+* [Google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)
 <a name="Dictionary"></a>
-#### 1.3 Dictionary
+### 1.3 Dictionary
 Finally, a dictionary ({word_dict_name}.txt) needs to be provided so that when the model is trained, all the characters that appear can be mapped to the dictionary index.
@@ -145,14 +166,26 @@ To customize the dict file, please modify the `character_dict_path` field in `co
 If you need to customize dic file, please add character_dict_path field in configs/rec/rec_icdar15_train.yml to point to your dictionary path. And set character_type to ch.
 <a name="Add_space_category"></a>
-#### 1.4 Add space category
+### 1.4 Add space category
 If you want to support the recognition of the `space` category, please set the `use_space_char` field in the yml file to `True`.
 **Note: use_space_char only takes effect when character_type=ch**
 <a name="TRAINING"></a>
-### 2 TRAINING
+## 2 TRAINING
+<a name="Data_Augmentation"></a>
+### 2.1 Data Augmentation
+PaddleOCR provides a variety of data augmentation methods. All the augmentation methods are enabled by default.
+The default perturbation methods are: cvtColor, blur, jitter, Gasuss noise, random crop, perspective, color reverse, TIA augmentation.
+Each disturbance method is selected with a 40% probability during the training process. For specific code implementation, please refer to: [rec_img_aug.py](../../ppocr/data/imaug/rec_img_aug.py)
+<a name="Training"></a>
+### 2.2 General Training
 PaddleOCR provides training scripts, evaluation scripts, and prediction scripts. In this section, the CRNN recognition model will be used as an example:
@@ -170,21 +203,15 @@ tar -xf rec_mv3_none_bilstm_ctc_v2.0_train.tar && rm -rf rec_mv3_none_bilstm_ctc
 Start training:
 ```
-# GPU training Support single card and multi-card training, specify the card number through --gpus
+# GPU training Support single card and multi-card training
 # Training icdar15 English data and The training log will be automatically saved as train.log under "{save_model_dir}"
+#specify the single card training(Long training time, not recommended)
+python3 tools/train.py -c configs/rec/rec_icdar15_train.yml
+#specify the card number through --gpus
 python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_icdar15_train.yml
 ```
-<a name="Data_Augmentation"></a>
-#### 2.1 Data Augmentation
-PaddleOCR provides a variety of data augmentation methods. All the augmentation methods are enabled by default.
-The default perturbation methods are: cvtColor, blur, jitter, Gasuss noise, random crop, perspective, color reverse, TIA augmentation.
-Each disturbance method is selected with a 40% probability during the training process. For specific code implementation, please refer to: [rec_img_aug.py](../../ppocr/data/imaug/rec_img_aug.py)
-<a name="Training"></a>
-#### 2.2 Training
 PaddleOCR supports alternating training and evaluation. You can modify `eval_batch_step` in `configs/rec/rec_icdar15_train.yml` to set the evaluation frequency. By default, it is evaluated every 500 iter and the best acc model is saved under `output/rec_CRNN/best_accuracy` during the evaluation process.
@@ -277,87 +304,7 @@ Eval:
 **Note that the configuration file for prediction/evaluation must be consistent with the training.**
 <a name="Multi_language"></a>
-#### 2.3 Multi-language
+### 2.3 Multi-language Training
-PaddleOCR currently supports 80 (except Chinese) language recognition. A multi-language configuration file template is
-provided under the path `configs/rec/multi_languages`: [rec_multi_language_lite_train.yml](../../configs/rec/multi_language/rec_multi_language_lite_train.yml)。
-There are two ways to create the required configuration file:：
-1. Automatically generated by script
-[generate_multi_language_configs.py](../../configs/rec/multi_language/generate_multi_language_configs.py) Can help you generate configuration files for multi-language models
- Take Italian as an example, if your data is prepared in the following format:
-    ```
-    |-train_data
-        |- it_train.txt # train_set label
-        |- it_val.txt # val_set label
-        |- data
-            |- word_001.jpg
-            |- word_002.jpg
-            |- word_003.jpg
-            | ...
-    ```
-    You can use the default parameters to generate a configuration file:
-    ```bash
-    # The code needs to be run in the specified directory
-    cd PaddleOCR/configs/rec/multi_language/
-    # Set the configuration file of the language to be generated through the -l or --language parameter.
-    # This command will write the default parameters into the configuration file
-    python3 generate_multi_language_configs.py -l it
-    ```
- If your data is placed in another location, or you want to use your own dictionary, you can generate the configuration file by specifying the relevant parameters:
-    ```bash
-    # -l or --language field is required
-    # --train to modify the training set
-    # --val to modify the validation set
-    # --data_dir to modify the data set directory
-    # --dict to modify the dict path
-    # -o to modify the corresponding default parameters
-    cd PaddleOCR/configs/rec/multi_language/
-    python3 generate_multi_language_configs.py -l it \  # language
-    --train {path/of/train_label.txt} \ # path of train_label
-    --val {path/of/val_label.txt} \     # path of val_label
-    --data_dir {train_data/path} \      # root directory of training data
-    --dict {path/of/dict} \             # path of dict
-    -o Global.use_gpu=False             # whether to use gpu
-    ...
-    ```
-Italian is made up of Latin letters, so after executing the command, you will get the rec_latin_lite_train.yml.
-2. Manually modify the configuration file
-   You can also manually modify the following fields in the template:
-   ```
-    Global:
-      use_gpu: True
-      epoch_num: 500
-      ...
-      character_type: it  # language
-      character_dict_path:  {path/of/dict} # path of dict
-   Train:
-      dataset:
-        name: SimpleDataSet
-        data_dir: train_data/ # root directory of training data
-        label_file_list: ["./train_data/train_list.txt"] # train label path
-      ...
-   Eval:
-      dataset:
-        name: SimpleDataSet
-        data_dir: train_data/ # root directory of val data
-        label_file_list: ["./train_data/val_list.txt"] # val label path
-      ...
-   ```
 Currently, the multi-language algorithms supported by PaddleOCR are:
@@ -376,9 +323,6 @@ Currently, the multi-language algorithms supported by PaddleOCR are:
 For more supported languages, please refer to : [Multi-language model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md#4-support-languages-and-abbreviations)
-The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded using the following two methods.
-* [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA),Extraction code:frgi.
-* [Google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)
 If you want to finetune on the basis of the existing model effect, please refer to the following instructions to modify the configuration file:
@@ -417,7 +361,7 @@ Eval:
 ```
 <a name="EVALUATION"></a>
-### 3 EVALUATION
+## 3 EVALUATION
 The evaluation dataset can be set by modifying the `Eval.dataset.label_file_list` field in the `configs/rec/rec_icdar15_train.yml` file.
@@ -427,20 +371,39 @@ python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec
 ```
 <a name="PREDICTION"></a>
-### 4 PREDICTION
+## 4 PREDICTION
-<a name="Training_engine_prediction"></a>
-#### 4.1 Training engine prediction
 Using the model trained by paddleocr, you can quickly get prediction through the following script.
-The default prediction picture is stored in `infer_img`, and the weight is specified via `-o Global.checkpoints`:
+The default prediction picture is stored in `infer_img`, and the trained weight is specified via `-o Global.checkpoints`:
+According to the `save_model_dir` and `save_epoch_step` fields set in the configuration file, the following parameters will be saved:
+```
+output/rec/
+├── best_accuracy.pdopt  
+├── best_accuracy.pdparams  
+├── best_accuracy.states  
+├── config.yml  
+├── iter_epoch_3.pdopt  
+├── iter_epoch_3.pdparams  
+├── iter_epoch_3.states  
+├── latest.pdopt  
+├── latest.pdparams  
+├── latest.states  
+└── train.log
+```
+Among them, best_accuracy.* is the best model on the evaluation set; iter_epoch_x.* is the model saved at intervals of `save_epoch_step`; latest.* is the model of the last epoch.
 ```
 # Predict English results
 python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/en/word_1.jpg
 ```
 Input image:
 ![](../imgs_words/en/word_1.png)

--- a/doc/doc_en/training_en.md
+++ b/doc/doc_en/training_en.md
+# MODEL TRAINING
+- [1. Basic concepts](#1-basic-concepts)
+  * [1.1 Learning rate](#11-learning-rate)
+  * [1.2 Regularization](#12-regularization)
+  * [1.3 Evaluation indicators](#13-evaluation-indicators-)
+- [2. FAQ](#2-faq)
+- [3. Data and vertical scenes](#3-data-and-vertical-scenes)
+  * [3.1 Training data](#31-training-data)
+  * [3.2 Vertical scene](#32-vertical-scene)
+  * [3.3 Build your own data set](#33-build-your-own-data-set)
+This article will introduce the basic concepts that need to be mastered during model training and the tuning methods during training.
+At the same time, it will briefly introduce the components of the PaddleOCR model training data and how to prepare the data finetune model in the vertical scene.
+<a name="1-basic-concepts"></a>
+# 1. Basic concepts
+OCR (Optical Character Recognition) refers to the process of analyzing and recognizing images to obtain text and layout information. It is a typical computer vision task.
+It usually consists of two subtasks: text detection and text recognition.
+The following parameters need to be paid attention to when tuning the model:
+<a name="11-learning-rate"></a>
+## 1.1 Learning rate
+The learning rate is one of the important hyperparameters for training neural networks. It represents the step length of the gradient moving to the optimal solution of the loss function in each iteration.
+A variety of learning rate update strategies are provided in PaddleOCR, which can be modified through configuration files, for example:
+```
+Optimizer:
+  ...
+  lr:
+    name: Piecewise
+    decay_epochs : [700, 800]
+    values : [0.001, 0.0001]
+    warmup_epoch: 5
+```
+Piecewise stands for piecewise constant attenuation. Different learning rates are specified in different learning stages,
+and the learning rate is the same in each stage.
+warmup_epoch means that in the first 5 epochs, the learning rate will gradually increase from 0 to base_lr. For all strategies, please refer to the code [learning_rate.py](../../ppocr/optimizer/learning_rate.py).
+<a name="12-regularization"></a>
+## 1.2 Regularization
+Regularization can effectively avoid algorithm overfitting. PaddleOCR provides L1 and L2 regularization methods.
+L1 and L2 regularization are the most commonly used regularization methods.
+L1 regularization adds a regularization term to the objective function to reduce the sum of absolute values of the parameters;
+while in L2 regularization, the purpose of adding a regularization term is to reduce the sum of squared parameters.
+The configuration method is as follows:
+```
+Optimizer:
+  ...
+  regularizer:
+    name: L2
+    factor: 2.0e-05
+```
+<a name="13-evaluation-indicators-"></a>
+## 1.3 Evaluation indicators
+(1) Detection stage: First, evaluate according to the IOU of the detection frame and the labeled frame. If the IOU is greater than a certain threshold, it is judged that the detection is accurate. Here, the detection frame and the label frame are different from the general general target detection frame, and they are represented by polygons. Detection accuracy: the percentage of the correct detection frame number in all detection frames is mainly used to judge the detection index. Detection recall rate: the percentage of correct detection frames in all marked frames, which is mainly an indicator of missed detection.
+(2) Recognition stage: Character recognition accuracy, that is, the ratio of correctly recognized text lines to the number of marked text lines. Only the entire line of text recognition pairs can be regarded as correct recognition.
+(3) End-to-end statistics: End-to-end recall rate: accurately detect and correctly identify the proportion of text lines in all labeled text lines; End-to-end accuracy rate: accurately detect and correctly identify the number of text lines in the detected text lines The standard for accurate detection is that the IOU of the detection box and the labeled box is greater than a certain threshold, and the text in the correctly identified detection box is the same as the labeled text.
+<a name="2-faq"></a>
+# 2. FAQ
+**Q**: How to choose a suitable network input shape when training CRNN recognition?
+    A: The general height is 32, the longest width is selected, there are two methods:
+    (1) Calculate the aspect ratio distribution of training sample images. The selection of the maximum aspect ratio considers 80% of the training samples.
+    (2) Count the number of texts in training samples. The selection of the longest number of characters considers the training sample that satisfies 80%. Then the aspect ratio of Chinese characters is approximately considered to be 1, and that of English is 3:1, and the longest width is estimated.
+**Q**: During the recognition training, the accuracy of the training set has reached 90, but the accuracy of the verification set has been kept at 70, what should I do?
+    A: If the accuracy of the training set is 90 and the test set is more than 70, it should be over-fitting. There are two methods to try:
+    (1) Add more augmentation methods or increase the [probability] of augmented prob (https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/ppocr/data/imaug/rec_img_aug.py#L341), The default is 0.4.
+    (2) Increase the [l2 dcay value] of the system (https://github.com/PaddlePaddle/PaddleOCR/blob/a501603d54ff5513fc4fc760319472e59da25424/configs/rec/ch_ppocr_v1.1/rec_chinese_lite_train_v1.1.yml#L47)
+**Q**: When the recognition model is trained, loss can drop normally, but acc is always 0
+    A: It is normal for the acc to be 0 at the beginning of the recognition model training, and the indicator will come up after a longer training period.
+<a name="3-data-and-vertical-scenes"></a>
+# 3. Data and vertical scenes
+<a name="31-training-data"></a>
+## 3.1 Training data
+The current open source models, data sets and magnitudes are as follows:
+- Detection:
+    - English data set, ICDAR2015
+    - Chinese data set, LSVT street view data set training data 3w pictures
+- Identification:
+    - English data set, MJSynth and SynthText synthetic data, the data volume is tens of millions.
+    - Chinese data set, LSVT street view data set crops the image according to the truth value, and performs position calibration, a total of 30w images. In addition, based on the LSVT corpus, 500w of synthesized data.
+    - Small language data set, using different corpora and fonts, respectively generated 100w synthetic data set, and using ICDAR-MLT as the verification set.
+Among them, the public data sets are all open source, users can search and download by themselves, or refer to [Chinese data set](./datasets.md), synthetic data is not open source, users can use open source synthesis tools to synthesize by themselves. Synthesis tools include [text_renderer](https://github.com/Sanster/text_renderer), [SynthText](https://github.com/ankush-me/SynthText), [TextRecognitionDataGenerator](https://github.com/Belval/TextRecognitionDataGenerator) etc.
+<a name="32-vertical-scene"></a>
+## 3.2 Vertical scene
+PaddleOCR mainly focuses on general OCR. If you have vertical requirements, you can use PaddleOCR + vertical data to train yourself;
+If there is a lack of labeled data, or if you do not want to invest in research and development costs, it is recommended to directly call the open API, which covers some of the more common vertical categories.  
+<a name="33-build-your-own-data-set"></a>
+## 3.3 Build your own data set
+There are several experiences for reference when constructing the data set:
+(1) The amount of data in the training set:
+    a. The data required for detection is relatively small. For Fine-tune based on the PaddleOCR model, 500 sheets are generally required to achieve good results.
+    b. Recognition is divided into English and Chinese. Generally, English scenarios require hundreds of thousands of data to achieve good results, while Chinese requires several million or more.
+(2) When the amount of training data is small, you can try the following three ways to get more data:
+    a. Manually collect more training data, the most direct and effective way.
+    b. Basic image processing or transformation based on PIL and opencv. For example, the three modules of ImageFont, Image, ImageDraw in PIL write text into the background, opencv's rotating affine transformation, Gaussian filtering and so on.
+    c. Use data generation algorithms to synthesize data, such as algorithms such as pix2pix.
--- a/doc/ic15_location_download.png
+++ b/doc/ic15_location_download.png
--- a/doc/ppocrv2_framework.jpg
+++ b/doc/ppocrv2_framework.jpg