diff --git a/README_ch.md b/README_ch.md index 11e1097250dff6d7384845f5d48fa073a6adf298..ff4f45ba47a5666f65a94dc067179868bf0cca30 100755 --- 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)。 -- 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)。 +- 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)。 +- 2021.9.7 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 ## 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) -- [PaddleOCR全景图与安装](./doc/doc_ch/paddleOCR_overview.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) - -## PP-OCR Pipeline + + +## PP-OCRv2 Pipeline
+ +
+
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
+
+## 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,
-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)。
+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/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
+
+## 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
+
+## 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。
+
+
+## 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。
+
+## 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
+
+## 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"
```
+
+
+## 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
+```
+
+
+# 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。
diff --git a/doc/doc_ch/models_and_config.md b/doc/doc_ch/models_and_config.md
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..167b7ec2cb039a5b7943cda98474d809019a57b7 100644
--- a/doc/doc_ch/models_and_config.md
+++ b/doc/doc_ch/models_and_config.md
@@ -0,0 +1,38 @@
+
+# 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--)
+
+
+# 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。
+
+
+## 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;
+
+
+## 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。
+
+
+## 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。
diff --git a/doc/doc_ch/models_list.md b/doc/doc_ch/models_list.md
index 35713ae67f797618e043697eb93642208c3df865..43671bf5b051b85a7d0728253bfeab069cd82642 100644
--- 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_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_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) |
### 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|
-|V2.0(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|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|
+|V2.1(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|
diff --git a/doc/doc_ch/recognition.md b/doc/doc_ch/recognition.md
index 9d5bf2861ba2e700975cdb5584efcf6a8ab26801..cd1a64bd7b2aa6d645d59bb9ab1cc1a741f38adc 100644
--- a/doc/doc_ch/recognition.md
+++ b/doc/doc_ch/recognition.md
@@ -1,5 +1,6 @@
-## 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)
- - [2.3 小语种](#小语种)
+ - [2.2 通用模型训练](#通用模型训练)
+ - [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)
-### 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;
- - `通用数据` 用于训练以文本文件存储的数据集:
+ - `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(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
+
+
+
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.
-
-## TEST
+## 1.7 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).
diff --git a/doc/doc_en/models_and_config_en.md b/doc/doc_en/models_and_config_en.md
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..c88120b5531347304976919cc2175aa54c9f5597 100644
--- a/doc/doc_en/models_and_config_en.md
+++ b/doc/doc_en/models_and_config_en.md
@@ -0,0 +1,41 @@
+# 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.
diff --git a/doc/doc_en/models_list_en.md b/doc/doc_en/models_list_en.md
index 9bee4aef5121b1964a9bdbdeeaad4e81dd9ff6d4..1f9ee1489a87e5814f672a1615920ded41d41e03 100644
--- 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_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_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 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) |
### 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|
-|V2.0(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|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|
+|V2.1(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|
diff --git a/doc/doc_en/recognition_en.md b/doc/doc_en/recognition_en.md
index ff5b802d8dbf54e842c035bce9ed480428eade83..21233c80a298fd32c889b24c47acdfaa885fc682 100644
--- a/doc/doc_en/recognition_en.md
+++ b/doc/doc_en/recognition_en.md
@@ -1,4 +1,4 @@
-## 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)
- - [2.3 Multi-language](#Multi_language)
+ - [2.2 General Training](#Training)
+ - [2.3 Multi-language Training](#Multi_language)
- [3 EVALUATION](#EVALUATION)
@@ -17,12 +17,12 @@
- [4.1 Training engine prediction](#Training_engine_prediction)
-### DATA PREPARATION
+## 1 DATA PREPARATION
PaddleOCR supports two data formats:
-- `LMDB` is used to train data sets stored in lmdb format;
-- `general data` is used to train data sets stored in text files:
+- `LMDB` is used to train data sets stored in lmdb format(LMDBDataSet);
+- `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