Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into dygraph

300452c7 · LDOUBLEV · 217b0409 · 33c99d29 · 300452c7 · 300452c7
Commit 300452c7 authored Apr 26, 2022 by LDOUBLEV
20 changed files
--- a/deploy/pdserving/pipeline_http_client.py
+++ b/deploy/pdserving/pipeline_http_client.py
@@ -34,12 +34,28 @@ test_img_dir = args.image_dir
 for idx, img_file in enumerate(os.listdir(test_img_dir)):
    with open(os.path.join(test_img_dir, img_file), 'rb') as file:
        image_data1 = file.read()
+    # print file name
+    print('{}{}{}'.format('*' * 10, img_file, '*' * 10))
    image = cv2_to_base64(image_data1)
-    for i in range(1):
    data = {"key": ["image"], "value": [image]}
    r = requests.post(url=url, data=json.dumps(data))
-        print(r.json())
+    result = r.json()
+    print("erro_no:{}, err_msg:{}".format(result["err_no"], result["err_msg"]))
+    # check success
+    if result["err_no"] == 0:
+        ocr_result = result["value"][0]
+        try:
+            for item in eval(ocr_result):
+                # return transcription and points
+                print("{}, {}".format(item[0], item[1]))
+        except Exception as e:
+            print("No results")
+            continue
+    else:
+        print(
+            "For details about error message, see PipelineServingLogs/pipeline.log"
+        )
 print("==> total number of test imgs: ", len(os.listdir(test_img_dir)))
--- a/deploy/pdserving/web_service.py
+++ b/deploy/pdserving/web_service.py
@@ -15,6 +15,7 @@ from paddle_serving_server.web_service import WebService, Op
 import logging
 import numpy as np
+import copy
 import cv2
 import base64
 # from paddle_serving_app.reader import OCRReader
@@ -36,7 +37,7 @@ class DetOp(Op):
        self.filter_func = FilterBoxes(10, 10)
        self.post_func = DBPostProcess({
            "thresh": 0.3,
-            "box_thresh": 0.5,
+            "box_thresh": 0.6,
            "max_candidates": 1000,
            "unclip_ratio": 1.5,
            "min_size": 3
@@ -79,8 +80,10 @@ class RecOp(Op):
        raw_im = input_dict["image"]
        data = np.frombuffer(raw_im, np.uint8)
        im = cv2.imdecode(data, cv2.IMREAD_COLOR)
-        dt_boxes = input_dict["dt_boxes"]
+        self.dt_list = input_dict["dt_boxes"]
-        dt_boxes = self.sorted_boxes(dt_boxes)
+        self.dt_list = self.sorted_boxes(self.dt_list)
+        # deepcopy to save origin dt_boxes
+        dt_boxes = copy.deepcopy(self.dt_list)
        feed_list = []
        img_list = []
        max_wh_ratio = 0
@@ -126,25 +129,29 @@ class RecOp(Op):
                imgs[id] = norm_img
            feed = {"x": imgs.copy()}
            feed_list.append(feed)
        return feed_list, False, None, ""
    def postprocess(self, input_dicts, fetch_data, data_id, log_id):
-        res_list = []
+        rec_list = []
+        dt_num = len(self.dt_list)
        if isinstance(fetch_data, dict):
            if len(fetch_data) > 0:
                rec_batch_res = self.ocr_reader.postprocess(
                    fetch_data, with_score=True)
                for res in rec_batch_res:
-                    res_list.append(res[0])
+                    rec_list.append(res)
        elif isinstance(fetch_data, list):
            for one_batch in fetch_data:
                one_batch_res = self.ocr_reader.postprocess(
                    one_batch, with_score=True)
                for res in one_batch_res:
-                    res_list.append(res[0])
+                    rec_list.append(res)
+        result_list = []
-        res = {"res": str(res_list)}
+        for i in range(dt_num):
+            text = rec_list[i]
+            dt_box = self.dt_list[i]
+            result_list.append([text, dt_box.tolist()])
+        res = {"result": str(result_list)}
        return res, None, ""

--- a/doc/datasets/CDLA_demo/val_0633.jpg
+++ b/doc/datasets/CDLA_demo/val_0633.jpg
--- a/doc/datasets/CDLA_demo/val_0941.jpg
+++ b/doc/datasets/CDLA_demo/val_0941.jpg
--- a/doc/datasets/publaynet_demo/gt_PMC3724501_00006.jpg
+++ b/doc/datasets/publaynet_demo/gt_PMC3724501_00006.jpg
--- a/doc/datasets/publaynet_demo/gt_PMC5086060_00002.jpg
+++ b/doc/datasets/publaynet_demo/gt_PMC5086060_00002.jpg
--- a/doc/datasets/tablebank_demo/004.png
+++ b/doc/datasets/tablebank_demo/004.png
--- a/doc/datasets/tablebank_demo/005.png
+++ b/doc/datasets/tablebank_demo/005.png
--- a/doc/doc_ch/layout_datasets.md
+++ b/doc/doc_ch/layout_datasets.md
+## 版面分析数据集
+这里整理了常用版面分析数据集，持续更新中，欢迎各位小伙伴贡献数据集～
+- [publaynet数据集](#publaynet)
+- [CDLA数据集](#CDLA)
+- [TableBank数据集](#TableBank)
+版面分析数据集多为目标检测数据集，除了开源数据，用户还可使用合成工具自行合成，如[labelme](https://github.com/wkentaro/labelme)等。
+<a name="publaynet"></a>
+#### 1、publaynet数据集
+- **数据来源**：https://github.com/ibm-aur-nlp/PubLayNet
+- **数据简介**：publaynet数据集的训练集合中包含35万张图像，验证集合中包含1.1万张图像。总共包含5个类别，分别是： `text, title, list, table, figure`。部分图像以及标注框可视化如下所示。
+<div align="center">
+    <img src="../datasets/publaynet_demo/gt_PMC3724501_00006.jpg" width="500">
+    <img src="../datasets/publaynet_demo/gt_PMC5086060_00002.jpg" width="500">
+</div>
+- **下载地址**：https://developer.ibm.com/exchanges/data/all/publaynet/
+- **说明**：使用该数据集时，需要遵守[CDLA-Permissive](https://cdla.io/permissive-1-0/)协议。
+<a name="CDLA"></a>
+#### 2、CDLA数据集
+- **数据来源**：https://github.com/buptlihang/CDLA
+- **数据简介**：publaynet数据集的训练集合中包含5000张图像，验证集合中包含1000张图像。总共包含10个类别，分别是： `Text, Title, Figure, Figure caption, Table, Table caption, Header, Footer, Reference, Equation`。部分图像以及标注框可视化如下所示。
+<div align="center">
+    <img src="../datasets/CDLA_demo/val_0633.jpg" width="500">
+    <img src="../datasets/CDLA_demo/val_0941.jpg" width="500">
+</div>
+- **下载地址**：https://github.com/buptlihang/CDLA
+- **说明**：基于[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/tree/develop)套件，在该数据集上训练目标检测模型时，在转换label时，需要将`label.txt`中的`__ignore__`与`_background_`去除。
+<a name="TableBank"></a>
+#### 3、TableBank数据集
+- **数据来源**：https://doc-analysis.github.io/tablebank-page/index.html
+- **数据简介**：TableBank数据集包含Latex（训练集187199张，验证集7265张，测试集5719张）与Word（训练集73383张，验证集2735张，测试集2281张）两种类别的文档。仅包含`Table` 1个类别。部分图像以及标注框可视化如下所示。
+<div align="center">
+    <img src="../datasets/tablebank_demo/004.png" height="700">
+    <img src="../datasets/tablebank_demo/005.png" height="700">
+</div>
+- **下载地址**：https://doc-analysis.github.io/tablebank-page/index.html
+- **说明**：使用该数据集时，需要遵守[Apache-2.0](https://github.com/doc-analysis/TableBank/blob/master/LICENSE)协议。
--- a/paddleocr.py
+++ b/paddleocr.py
@@ -47,7 +47,7 @@ __all__ = [
 ]
 SUPPORT_DET_MODEL = ['DB']
-VERSION = '2.4.0.4'
+VERSION = '2.5'
 SUPPORT_REC_MODEL = ['CRNN']
 BASE_DIR = os.path.expanduser("~/.paddleocr/")
@@ -442,7 +442,7 @@ class PPStructure(StructureSystem):
        logger.debug(params)
        super().__init__(params)
-    def __call__(self, img):
+    def __call__(self, img, return_ocr_result_in_table=False):
        if isinstance(img, str):
            # download net image
            if img.startswith('http'):
@@ -460,7 +460,7 @@ class PPStructure(StructureSystem):
        if isinstance(img, np.ndarray) and len(img.shape) == 2:
            img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
-        res = super().__call__(img)
+        res = super().__call__(img, return_ocr_result_in_table)
        return res

--- a/ppocr/postprocess/rec_postprocess.py
+++ b/ppocr/postprocess/rec_postprocess.py
@@ -73,7 +73,7 @@ class BaseRecLabelDecode(object):
                conf_list = [0]
            text = ''.join(char_list)
-            result_list.append((text, np.mean(conf_list)))
+            result_list.append((text, np.mean(conf_list).tolist()))
        return result_list
    def get_ignored_tokens(self):
@@ -196,7 +196,7 @@ class NRTRLabelDecode(BaseRecLabelDecode):
                else:
                    conf_list.append(1)
            text = ''.join(char_list)
-            result_list.append((text.lower(), np.mean(conf_list)))
+            result_list.append((text.lower(), np.mean(conf_list).tolist()))
        return result_list
@@ -241,7 +241,7 @@ class AttnLabelDecode(BaseRecLabelDecode):
                else:
                    conf_list.append(1)
            text = ''.join(char_list)
-            result_list.append((text, np.mean(conf_list)))
+            result_list.append((text, np.mean(conf_list).tolist()))
        return result_list
    def __call__(self, preds, label=None, *args, **kwargs):
@@ -333,7 +333,7 @@ class SEEDLabelDecode(BaseRecLabelDecode):
                else:
                    conf_list.append(1)
            text = ''.join(char_list)
-            result_list.append((text, np.mean(conf_list)))
+            result_list.append((text, np.mean(conf_list).tolist()))
        return result_list
    def __call__(self, preds, label=None, *args, **kwargs):
@@ -417,7 +417,7 @@ class SRNLabelDecode(BaseRecLabelDecode):
                    conf_list.append(1)
            text = ''.join(char_list)
-            result_list.append((text, np.mean(conf_list)))
+            result_list.append((text, np.mean(conf_list).tolist()))
        return result_list
    def add_special_char(self, dict_character):
@@ -636,7 +636,7 @@ class SARLabelDecode(BaseRecLabelDecode):
                comp = re.compile('[^A-Z^a-z^0-9^\u4e00-\u9fa5]')
                text = text.lower()
                text = comp.sub('', text)
-            result_list.append((text, np.mean(conf_list)))
+            result_list.append((text, np.mean(conf_list).tolist()))
        return result_list
    def __call__(self, preds, label=None, *args, **kwargs):
@@ -699,7 +699,7 @@ class PRENLabelDecode(BaseRecLabelDecode):
            text = ''.join(char_list)
            if len(text) > 0:
-                result_list.append((text, np.mean(conf_list)))
+                result_list.append((text, np.mean(conf_list).tolist()))
            else:
                # here confidence of empty recog result is 1
                result_list.append(('', 1))

--- a/ppstructure/docs/inference.md
+++ b/ppstructure/docs/inference.md
 # 基于Python预测引擎推理
- [版面分析+表格识别](#1)
+- [1. Structure](#1)
- [DocVQA](#2)
+  - [1.1 版面分析+表格识别](#1.1)
+  - [1.2 版面分析](#1.2)
+  - [1.3 表格识别](#1.3)
+- [2. DocVQA](#2)
 <a name="1"></a>
-## 1. 版面分析+表格识别
+## 1. Structure
+进入`ppstructure`目录
 ```bash
 cd ppstructure
+````
-# 下载模型
+下载模型
+```bash
 mkdir inference && cd inference
 # 下载PP-OCRv2文本检测模型并解压
 wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar
@@ -18,17 +23,42 @@ wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant
 # 下载超轻量级英文表格预测模型并解压
 wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
 cd ..
+```
+<a name="1.1"></a>
+### 1.1 版面分析+表格识别
+```bash
 python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \
                          --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \
                          --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \
-                          --image_dir=../doc/table/1.png \
+                          --image_dir=./docs/table/1.png \
                          --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
-                          --output=../output/table \
+                          --output=../output \
                          --vis_font_path=../doc/fonts/simfang.ttf
 ```
-运行完成后，每张图片会在`output`字段指定的目录下的`talbe`目录下有一个同名目录，图片里的每个表格会存储为一个excel，图片区域会被裁剪之后保存下来，excel文件和图片名名为表格在图片里的坐标。
+运行完成后，每张图片会在`output`字段指定的目录下的`structure`目录下有一个同名目录，图片里的每个表格会存储为一个excel，图片区域会被裁剪之后保存下来，excel文件和图片名为表格在图片里的坐标。详细的结果会存储在`res.txt`文件中。
+<a name="1.2"></a>
+### 1.2 版面分析
+```bash
+python3 predict_system.py --image_dir=./docs/table/1.png --table=false --ocr=false --output=../output/
+```
+运行完成后，每张图片会在`output`字段指定的目录下的`structure`目录下有一个同名目录，图片区域会被裁剪之后保存下来，图片名为表格在图片里的坐标。版面分析结果会存储在`res.txt`文件中。
+<a name="1.3"></a>
+### 1.3 表格识别
+```bash
+python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \
+                          --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \
+                          --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \
+                          --image_dir=./docs/table/table.jpg \
+                          --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
+                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
+                          --output=../output \
+                          --vis_font_path=../doc/fonts/simfang.ttf \
+                          --layout=false
+```
+运行完成后，每张图片会在`output`字段指定的目录下的`structure`目录下有一个同名目录，表格会存储为一个excel，excel文件名为`[0,0,img_h,img_w]`。
 <a name="2"></a>
 ## 2. DocVQA

--- a/ppstructure/docs/inference_en.md
+++ b/ppstructure/docs/inference_en.md
-# 基于Python预测引擎推理
+# Python Inference
- [版面分析+表格识别](#1)
+- [1. Structure](#1)
- [DocVQA](#2)
+  - [1.1 layout analysis + table recognition](#1.1)
+  - [1.2 layout analysis](#1.2)
+  - [1.3 table recognition](#1.3)
+- [2. DocVQA](#2)
 <a name="1"></a>
-## 1. 版面分析+表格识别
+## 1. Structure
+Go to the `ppstructure` directory
 ```bash
 cd ppstructure
+````
-# 下载模型
+download model
+```bash
 mkdir inference && cd inference
-# 下载PP-OCRv2文本检测模型并解压
+# Download the PP-OCRv2 text detection model and unzip it
 wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar
-# 下载PP-OCRv2文本识别模型并解压
+# Download the PP-OCRv2 text recognition model and unzip it
 wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar
-# 下载超轻量级英文表格预测模型并解压
+# Download the ultra-lightweight English table structure model and unzip it
 wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
 cd ..
+```
+<a name="1.1"></a>
+### 1.1 layout analysis + table recognition
+```bash
 python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \
                          --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \
                          --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \
-                          --image_dir=../doc/table/1.png \
+                          --image_dir=./docs/table/1.png \
                          --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
-                          --output=../output/table \
+                          --output=../output \
                          --vis_font_path=../doc/fonts/simfang.ttf
 ```
-运行完成后，每张图片会在`output`字段指定的目录下的`talbe`目录下有一个同名目录，图片里的每个表格会存储为一个excel，图片区域会被裁剪之后保存下来，excel文件和图片名名为表格在图片里的坐标。
+After the operation is completed, each image will have a directory with the same name in the `structure` directory under the directory specified by the `output` field. Each table in the image will be stored as an excel, and the picture area will be cropped and saved. The filename of excel and picture is their coordinates in the image. Detailed results are stored in the `res.txt` file.
+<a name="1.2"></a>
+### 1.2 layout analysis
+```bash
+python3 predict_system.py --image_dir=./docs/table/1.png --table=false --ocr=false --output=../output/
+```
+After the operation is completed, each image will have a directory with the same name in the `structure` directory under the directory specified by the `output` field. Each picture in image will be cropped and saved. The filename of picture area is their coordinates in the image. Layout analysis results will be stored in the `res.txt` file
+<a name="1.3"></a>
+### 1.3 table recognition
+```bash
+python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \
+                          --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \
+                          --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \
+                          --image_dir=./docs/table/table.jpg \
+                          --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
+                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
+                          --output=../output \
+                          --vis_font_path=../doc/fonts/simfang.ttf \
+                          --layout=false
+```
+After the operation is completed, each image will have a directory with the same name in the `structure` directory under the directory specified by the `output` field. Each table in the image will be stored as an excel. The filename of excel is their coordinates in the image.
 <a name="2"></a>
 ## 2. DocVQA
@@ -36,9 +68,8 @@ python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_i
 ```bash
 cd ppstructure
-# 下载模型
+# download model
 mkdir inference && cd inference
-# 下载SER xfun 模型并解压
 wget https://paddleocr.bj.bcebos.com/pplayout/PP-Layout_v1.0_ser_pretrained.tar && tar xf PP-Layout_v1.0_ser_pretrained.tar
 cd ..
@@ -47,4 +78,4 @@ python3 predict_system.py --model_name_or_path=vqa/PP-Layout_v1.0_ser_pretrained
                          --image_dir=vqa/images/input/zh_val_0.jpg  \
                          --vis_font_path=../doc/fonts/simfang.ttf
 ```
-运行完成后，每张图片会在`output`字段指定的目录下的`vqa`目录下存放可视化之后的图片，图片名和输入图片名一致。
+After the operation is completed, each image will store the visualized image in the `vqa` directory under the directory specified by the `output` field, and the image name is the same as the input image name.
\ No newline at end of file
--- a/ppstructure/docs/models_list_en.md
+++ b/ppstructure/docs/models_list_en.md
-# PP-Structure 系列模型列表
+# PP-Structure Model list
- [1. 版面分析模型](#1)
+- [1. Layout Analysis](#1)
- [2. OCR和表格识别模型](#2)
+- [2. OCR and Table Recognition](#2)
    - [2.1 OCR](#21)
-    - [2.2 表格识别模型](#22)
+    - [2.2 Table Recognition](#22)
- [3. VQA模型](#3)
+- [3. VQA](#3)
- [4. KIE模型](#4)
+- [4. KIE](#4)
 <a name="1"></a>
-## 1. 版面分析模型
+## 1. Layout Analysis
-|模型名称|模型简介|下载地址|label_map|
+|model name| description                                                                                                                                             |download|label_map|
-| --- | --- | --- | --- |
+| --- |---------------------------------------------------------------------------------------------------------------------------------------------------------| --- | --- |
-| ppyolov2_r50vd_dcn_365e_publaynet | PubLayNet 数据集训练的版面分析模型，可以划分**文字、标题、表格、图片以及列表**5类区域 | [推理模型](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_publaynet.tar) / [训练模型](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_publaynet_pretrained.pdparams) |{0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"}|
+| ppyolov2_r50vd_dcn_365e_publaynet | The layout analysis model trained on the PubLayNet dataset, the model can recognition 5 types of areas such as **text, title, table, picture and list** | [inference model](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_publaynet.tar) / [trained model](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_publaynet_pretrained.pdparams) |{0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"}|
-| ppyolov2_r50vd_dcn_365e_tableBank_word | TableBank Word 数据集训练的版面分析模型，只能检测表格 | [推理模型](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_tableBank_word.tar) | {0:"Table"}|
+| ppyolov2_r50vd_dcn_365e_tableBank_word | The layout analysis model trained on the TableBank Word dataset, the model can only detect tables                                                       | [inference model](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_tableBank_word.tar) | {0:"Table"}|
-| ppyolov2_r50vd_dcn_365e_tableBank_latex | TableBank Latex 数据集训练的版面分析模型，只能检测表格 | [推理模型](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_tableBank_latex.tar) | {0:"Table"}|
+| ppyolov2_r50vd_dcn_365e_tableBank_latex | The layout analysis model trained on the TableBank Latex dataset, the model can only detect tables                                                      | [inference model](https://paddle-model-ecology.bj.bcebos.com/model/layout-parser/ppyolov2_r50vd_dcn_365e_tableBank_latex.tar) | {0:"Table"}|
 <a name="2"></a>
-## 2. OCR和表格识别模型
+## 2. OCR and Table Recognition
 <a name="21"></a>
 ### 2.1 OCR
-|模型名称|模型简介|推理模型大小|下载地址|
+|model name| description | inference model size |download|
-| --- | --- | --- | --- |
+| --- |---|---| --- |
-|en_ppocr_mobile_v2.0_table_det|PubLayNet数据集训练的英文表格场景的文字检测|4.7M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_det_train.tar) |
+|en_ppocr_mobile_v2.0_table_det| Text detection model of English table scenes trained on PubTabNet dataset | 4.7M                |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_det_train.tar) |
-|en_ppocr_mobile_v2.0_table_rec|PubLayNet数据集训练的英文表格场景的文字识别|6.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_rec_train.tar) |
+|en_ppocr_mobile_v2.0_table_rec| Text recognition model of English table scenes trained on PubTabNet dataset | 6.9M                |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_rec_train.tar) |
-如需要使用其他OCR模型，可以在 [PP-OCR model_list](../../doc/doc_ch/models_list.md) 下载模型或者使用自己训练好的模型配置到 `det_model_dir`, `rec_model_dir`两个字段即可。
+If you need to use other OCR models, you can download the model in [PP-OCR model_list](../../doc/doc_ch/models_list.md) or use the model you trained yourself to configure to `det_model_dir`, `rec_model_dir` field.
 <a name="22"></a>
-### 2.2 表格识别模型
+### 2.2 Table Recognition
-|模型名称|模型简介|推理模型大小|下载地址|
+|model| description                                                                 |inference model size|download|
-| --- | --- | --- | --- |
+| --- |-----------------------------------------------------------------------------| --- | --- |
-|en_ppocr_mobile_v2.0_table_structure|PubLayNet数据集训练的英文表格场景的表格结构预测|18.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) |
+|en_ppocr_mobile_v2.0_table_structure| Table structure model for English table scenes trained on PubTabNet dataset |18.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) |
 <a name="3"></a>
-## 3. VQA模型
+## 3. VQA
-|模型名称|模型简介|推理模型大小|下载地址|
+|model| description                                                    |inference model size|download|
-| --- | --- | --- | --- |
+| --- |----------------------------------------------------------------| --- | --- |
-|ser_LayoutXLM_xfun_zh|基于LayoutXLM在xfun中文数据集上训练的SER模型|1.4G|[推理模型 coming soon]() / [训练模型](https://paddleocr.bj.bcebos.com/pplayout/re_LayoutXLM_xfun_zh.tar) |
+|ser_LayoutXLM_xfun_zh| SER model trained on xfun Chinese dataset based on LayoutXLM   |1.4G|[inference model coming soon]() / [trained model](https://paddleocr.bj.bcebos.com/pplayout/re_LayoutXLM_xfun_zh.tar) |
-|re_LayoutXLM_xfun_zh|基于LayoutXLM在xfun中文数据集上训练的RE模型|1.4G|[推理模型 coming soon]() / [训练模型](https://paddleocr.bj.bcebos.com/pplayout/ser_LayoutXLM_xfun_zh.tar) |
+|re_LayoutXLM_xfun_zh| Re model trained on xfun Chinese dataset based on LayoutXLM    |1.4G|[inference model coming soon]() / [trained model](https://paddleocr.bj.bcebos.com/pplayout/ser_LayoutXLM_xfun_zh.tar) |
-|ser_LayoutLMv2_xfun_zh|基于LayoutLMv2在xfun中文数据集上训练的SER模型|778M|[推理模型 coming soon]() / [训练模型](https://paddleocr.bj.bcebos.com/pplayout/ser_LayoutLMv2_xfun_zh.tar) |
+|ser_LayoutLMv2_xfun_zh| SER model trained on xfun Chinese dataset based on LayoutXLMv2 |778M|[inference model coming soon]() / [trained model](https://paddleocr.bj.bcebos.com/pplayout/ser_LayoutLMv2_xfun_zh.tar) |
-|re_LayoutLMv2_xfun_zh|基于LayoutLMv2在xfun中文数据集上训练的RE模型|765M|[推理模型 coming soon]() / [训练模型](https://paddleocr.bj.bcebos.com/pplayout/re_LayoutLMv2_xfun_zh.tar) |
+|re_LayoutLMv2_xfun_zh| Re model trained on xfun Chinese dataset based on LayoutXLMv2  |765M|[inference model coming soon]() / [trained model](https://paddleocr.bj.bcebos.com/pplayout/re_LayoutLMv2_xfun_zh.tar) |
-|ser_LayoutLM_xfun_zh|基于LayoutLM在xfun中文数据集上训练的SER模型|430M|[推理模型 coming soon]() / [训练模型](https://paddleocr.bj.bcebos.com/pplayout/ser_LayoutLM_xfun_zh.tar) |
+|ser_LayoutLM_xfun_zh| SER model trained on xfun Chinese dataset based on LayoutLM    |430M|[inference model coming soon]() / [trained model](https://paddleocr.bj.bcebos.com/pplayout/ser_LayoutLM_xfun_zh.tar) |
 <a name="4"></a>
-## 4. KIE模型
+## 4. KIE
-|模型名称|模型简介|模型大小|下载地址|
+|model|description|model size|download|
 | --- | --- | --- | --- |
-|SDMGR|关键信息提取模型|78M|[推理模型 coming soon]() / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/kie/kie_vgg16.tar)|
+|SDMGR|Key Information Extraction Model|78M|[inference model coming soon]() / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/kie/kie_vgg16.tar)|
--- a/ppstructure/docs/quickstart.md
+++ b/ppstructure/docs/quickstart.md
@@ -4,10 +4,14 @@
 - [2. 便捷使用](#2)
    - [2.1 命令行使用](#21)
        - [2.1.1 版面分析+表格识别](#211)
-        - [2.1.2 DocVQA](#212)
+        - [2.1.2 版面分析](#212)
-    - [2.2 Python脚本使用](#22)
+        - [2.1.3 表格识别](#213)
+        - [2.1.4 DocVQA](#214)
+    - [2.2 代码使用](#22)
        - [2.2.1 版面分析+表格识别](#221)
-        - [2.2.2 DocVQA](#222)
+        - [2.2.2 版面分析](#222)
+        - [2.2.3 表格识别](#223)
+        - [2.2.4 DocVQA](#224)
    - [2.3 返回结果说明](#23)
        - [2.3.1 版面分析+表格识别](#231)
        - [2.3.2 DocVQA](#232)
@@ -18,8 +22,8 @@
 ## 1. 安装依赖包
 ```bash
-# 安装 paddleocr，推荐使用2.3.0.2+版本
+# 安装 paddleocr，推荐使用2.5+版本
-pip3 install "paddleocr>=2.3.0.2" 
+pip3 install "paddleocr>=2.5"
 # 安装 版面分析依赖包layoutparser（如不需要版面分析功能，可跳过）
 pip3 install -U https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
 # 安装 DocVQA依赖包paddlenlp（如不需要DocVQA功能，可跳过）
@@ -36,16 +40,28 @@ pip install paddlenlp
 <a name="211"></a>
 #### 2.1.1 版面分析+表格识别
 ```bash
-paddleocr --image_dir=../doc/table/1.png --type=structure
+paddleocr --image_dir=PaddleOCR/ppstructure/docs/table/1.png --type=structure
 ```
 <a name="212"></a>
-#### 2.1.2 DocVQA
+#### 2.1.2 版面分析
+```bash
+paddleocr --image_dir=PaddleOCR/ppstructure/docs/table/1.png --type=structure --table=false --ocr=false
+```
+<a name="213"></a>
+#### 2.1.3 表格识别
+```bash
+paddleocr --image_dir=PaddleOCR/ppstructure/docs/table/table.jpg --type=structure --layout=false
+```
+<a name="214"></a>
+#### 2.1.4 DocVQA
 请参考：[文档视觉问答](../vqa/README.md)。
 <a name="22"></a>
-### 2.2 Python脚本使用
+### 2.2 代码使用
 <a name="221"></a>
 #### 2.2.1 版面分析+表格识别
@@ -57,8 +73,8 @@ from paddleocr import PPStructure,draw_structure_result,save_structure_res
 table_engine = PPStructure(show_log=True)
-save_folder = './output/table'
+save_folder = './output'
-img_path = '../doc/table/1.png'
+img_path = 'PaddleOCR/ppstructure/docs/table/1.png'
 img = cv2.imread(img_path)
 result = table_engine(img)
 save_structure_res(result, save_folder,os.path.basename(img_path).split('.')[0])
@@ -69,7 +85,7 @@ for line in result:
 from PIL import Image
-font_path = '../doc/fonts/simfang.ttf' # PaddleOCR下提供字体包
+font_path = 'PaddleOCR/doc/fonts/simfang.ttf' # PaddleOCR下提供字体包
 image = Image.open(img_path).convert('RGB')
 im_show = draw_structure_result(image, result,font_path=font_path)
 im_show = Image.fromarray(im_show)
@@ -77,7 +93,49 @@ im_show.save('result.jpg')
 ```
 <a name="222"></a>
-#### 2.2.2 DocVQA
+#### 2.2.2 版面分析
+```python
+import os
+import cv2
+from paddleocr import PPStructure,save_structure_res
+table_engine = PPStructure(table=False, ocr=False, show_log=True)
+save_folder = './output'
+img_path = 'PaddleOCR/ppstructure/docs/table/1.png'
+img = cv2.imread(img_path)
+result = table_engine(img)
+save_structure_res(result, save_folder, os.path.basename(img_path).split('.')[0])
+for line in result:
+    line.pop('img')
+    print(line)
+```
+<a name="223"></a>
+#### 2.2.3 表格识别
+```python
+import os
+import cv2
+from paddleocr import PPStructure,save_structure_res
+table_engine = PPStructure(layout=False, show_log=True)
+save_folder = './output'
+img_path = 'PaddleOCR/ppstructure/docs/table/table.jpg'
+img = cv2.imread(img_path)
+result = table_engine(img)
+save_structure_res(result, save_folder, os.path.basename(img_path).split('.')[0])
+for line in result:
+    line.pop('img')
+    print(line)
+```
+<a name="224"></a>
+#### 2.2.4 DocVQA
 请参考：[文档视觉问答](../vqa/README.md)。
@@ -99,10 +157,10 @@ PP-Structure的返回结果为一个dict组成的list，示例如下
 dict 里各个字段说明如下
 | 字段            | 说明                                                                                                                                                                                                                                                                                                                                                                                            |
-| --------------- | -------------|
+| --------------- |-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-|type|图片区域的类型|
+|type| 图片区域的类型                                                                                                                                                                                                                                                                                                                                                                                       |
-|bbox|图片区域的在原图的坐标，分别[左上角x，左上角y，右下角x，右下角y]|
+|bbox| 图片区域的在原图的坐标，分别[左上角x，左上角y，右下角x，右下角y]                                                                                                                                                                                                                                                                                                                                                           |
-|res|图片区域的OCR或表格识别结果。<br> 表格: 表格的HTML字符串; <br> OCR: 一个包含各个单行文字的检测坐标和识别结果的元组|
+|res| 图片区域的OCR或表格识别结果。<br> 表格: 一个dict，字段说明如下<br>&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp; `html`: 表格的HTML字符串<br>&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp; 在代码使用模式下，前向传入return_ocr_result_in_table=True可以拿到表格中每个文本的检测识别结果，对应为如下字段: <br>&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp; `boxes`: 文本检测坐标<br>&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp; `rec_res`: 文本识别结果。<br> OCR: 一个包含各个单行文字的检测坐标和识别结果的元组 |
 运行完成后，每张图片会在`output`字段指定的目录下有一个同名目录，图片里的每个表格会存储为一个excel，图片区域会被裁剪之后保存下来，excel文件和图片名为表格在图片里的坐标。
@@ -123,7 +181,7 @@ dict 里各个字段说明如下
 ### 2.4 参数说明
 | 字段                   | 说明                                                                                                                                                 | 默认值                                                     |
-| --------------- | ---------------------------------------- | ------------------------------------------- |
+|----------------------|----------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------|
 | output               | excel和识别结果保存的地址                                                                                                                                    | ./output/table                                          |
 | table_max_len        | 表格结构模型预测时，图像的长边resize尺度                                                                                                                            | 488                                                     |
 | table_model_dir      | 表格结构模型 inference 模型地址                                                                                                                              | None                                                    |
@@ -133,6 +191,8 @@ dict 里各个字段说明如下
 | model_name_or_path   | VQA SER模型地址                                                                                                                                        | None                                                    |
 | max_seq_length       | VQA SER模型最大支持token长度                                                                                                                               | 512                                                     |
 | label_map_path       | VQA SER 标签文件地址                                                                                                                                     | ./vqa/labels/labels_ser.txt                             |
-| mode | pipeline预测模式，structure: 版面分析+表格识别; VQA: SER文档信息抽取              | structure |
+| layout               | 前向中是否执行版面分析                                                                                                                                        | True                                                    |
+| table                | 前向中是否执行表格识别                                                                                                                                        | True                                                    |
+| ocr                  | 对于版面分析中的非表格区域，是否执行ocr。当layout为False时会被自动设置为False                                                                                                  | True                                                    |
 大部分参数和PaddleOCR whl包保持一致，见 [whl包文档](../../doc/doc_ch/whl.md)
--- a/ppstructure/docs/quickstart_en.md
+++ b/ppstructure/docs/quickstart_en.md
-# PP-Structure 快速开始
+# PP-Structure Quick Start
- [1. 安装依赖包](#1)
+- [1. Install package](#1)
- [2. 便捷使用](#2)
+- [2. Use](#2)
-    - [2.1 命令行使用](#21)
+    - [2.1 Use by command line](#21)
-        - [2.1.1 版面分析+表格识别](#211)
+        - [2.1.1 layout analysis + table recognition](#211)
-        - [2.1.2 DocVQA](#212)
+        - [2.1.2 layout analysis](#212)
-    - [2.2 Python脚本使用](#22)
+        - [2.1.3 table recognition](#213)
-        - [2.2.1 版面分析+表格识别](#221)
+        - [2.1.4 DocVQA](#214)
-        - [2.2.2 DocVQA](#222)
+    - [2.2 Use by code](#22)
-    - [2.3 返回结果说明](#23)
+        - [2.2.1 layout analysis + table recognition](#221)
-        - [2.3.1 版面分析+表格识别](#231)
+        - [2.2.2 layout analysis](#222)
+        - [2.2.3 table recognition](#223)
+        - [2.2.4 DocVQA](#224)
+    - [2.3 Result description](#23)
+        - [2.3.1 layout analysis + table recognition](#231)
        - [2.3.2 DocVQA](#232)
-    - [2.4 参数说明](#24)
+    - [2.4 Parameter Description](#24)
 <a name="1"></a>
-## 1. 安装依赖包
+## 1. Install package
 ```bash
-# 安装 paddleocr，推荐使用2.3.0.2+版本
+# Install paddleocr, version 2.5+ is recommended
-pip3 install "paddleocr>=2.3.0.2" 
+pip3 install "paddleocr>=2.5"
-# 安装 版面分析依赖包layoutparser（如不需要版面分析功能，可跳过）
+# Install layoutparser (if you do not use the layout analysis, you can skip it)
 pip3 install -U https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
-# 安装 DocVQA依赖包paddlenlp（如不需要DocVQA功能，可跳过）
+# Install the DocVQA dependency package paddlenlp (if you do not use the DocVQA, you can skip it)
 pip install paddlenlp
 ```
 <a name="2"></a>
-## 2. 便捷使用
+## 2. Use
 <a name="21"></a>
-### 2.1 命令行使用  
+### 2.1 Use by command line
 <a name="211"></a>
-#### 2.1.1 版面分析+表格识别
+#### 2.1.1 layout analysis + table recognition
 ```bash
-paddleocr --image_dir=../doc/table/1.png --type=structure
+paddleocr --image_dir=PaddleOCR/ppstructure/docs/table/1.png --type=structure
 ```
 <a name="212"></a>
-#### 2.1.2 DocVQA
+#### 2.1.2 layout analysis
+```bash
+paddleocr --image_dir=PaddleOCR/ppstructure/docs/table/1.png --type=structure --table=false --ocr=false
+```
+<a name="213"></a>
+#### 2.1.3 table recognition
+```bash
+paddleocr --image_dir=PaddleOCR/ppstructure/docs/table/table.jpg --type=structure --layout=false
+```
-请参考：[文档视觉问答](../vqa/README.md)。
+<a name="214"></a>
+#### 2.1.4 DocVQA
+Please refer to: [Documentation Visual Q&A](../vqa/README.md) .
 <a name="22"></a>
-### 2.2 Python脚本使用
+### 2.2 Use by code
 <a name="221"></a>
-#### 2.2.1 版面分析+表格识别
+#### 2.2.1 layout analysis + table recognition
 ```python
 import os
@@ -57,8 +73,8 @@ from paddleocr import PPStructure,draw_structure_result,save_structure_res
 table_engine = PPStructure(show_log=True)
-save_folder = './output/table'
+save_folder = './output'
-img_path = '../doc/table/1.png'
+img_path = 'PaddleOCR/ppstructure/docs/table/1.png'
 img = cv2.imread(img_path)
 result = table_engine(img)
 save_structure_res(result, save_folder,os.path.basename(img_path).split('.')[0])
@@ -69,7 +85,7 @@ for line in result:
 from PIL import Image
-font_path = '../doc/fonts/simfang.ttf' # PaddleOCR下提供字体包
+font_path = 'PaddleOCR/doc/fonts/simfang.ttf' # PaddleOCR下提供字体包
 image = Image.open(img_path).convert('RGB')
 im_show = draw_structure_result(image, result,font_path=font_path)
 im_show = Image.fromarray(im_show)
@@ -77,16 +93,59 @@ im_show.save('result.jpg')
 ```
 <a name="222"></a>
-#### 2.2.2 DocVQA
+#### 2.2.2 layout analysis
+```python
+import os
+import cv2
+from paddleocr import PPStructure,save_structure_res
+table_engine = PPStructure(table=False, ocr=False, show_log=True)
+save_folder = './output'
+img_path = 'PaddleOCR/ppstructure/docs/table/1.png'
+img = cv2.imread(img_path)
+result = table_engine(img)
+save_structure_res(result, save_folder, os.path.basename(img_path).split('.')[0])
+for line in result:
+    line.pop('img')
+    print(line)
+```
+<a name="223"></a>
+#### 2.2.3 table recognition
+```python
+import os
+import cv2
+from paddleocr import PPStructure,save_structure_res
+table_engine = PPStructure(layout=False, show_log=True)
+save_folder = './output'
+img_path = 'PaddleOCR/ppstructure/docs/table/table.jpg'
+img = cv2.imread(img_path)
+result = table_engine(img)
+save_structure_res(result, save_folder, os.path.basename(img_path).split('.')[0])
-请参考：[文档视觉问答](../vqa/README.md)。
+for line in result:
+    line.pop('img')
+    print(line)
+```
+<a name="224"></a>
+#### 2.2.4 DocVQA
+Please refer to: [Documentation Visual Q&A](../vqa/README.md) .
 <a name="23"></a>
-### 2.3 返回结果说明
+### 2.3 Result description
-PP-Structure的返回结果为一个dict组成的list，示例如下
+The return of PP-Structure is a list of dicts, the example is as follows:
 <a name="231"></a>
-#### 2.3.1 版面分析+表格识别
+#### 2.3.1 layout analysis + table recognition
 ```shell
 [
  {   'type': 'Text',
@@ -96,43 +155,44 @@ PP-Structure的返回结果为一个dict组成的list，示例如下
  }
 ]
 ```
-dict 里各个字段说明如下
+Each field in dict is described as follows:
-| 字段            | 说明           |
-| --------------- | -------------|
-|type|图片区域的类型|
-|bbox|图片区域的在原图的坐标，分别[左上角x，左上角y，右下角x，右下角y]|
-|res|图片区域的OCR或表格识别结果。<br> 表格: 表格的HTML字符串; <br> OCR: 一个包含各个单行文字的检测坐标和识别结果的元组|
-运行完成后，每张图片会在`output`字段指定的目录下有一个同名目录，图片里的每个表格会存储为一个excel，图片区域会被裁剪之后保存下来，excel文件和图片名为表格在图片里的坐标。
+| field            | description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| --------------- |--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+|type| Type of image area.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+|bbox| The coordinates of the image area in the original image, respectively [upper left corner x, upper left corner y, lower right corner x, lower right corner y].                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
+|res| OCR or table recognition result of the image area. <br> table: a dict with field descriptions as follows: <br>&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp; `html`: html str of table.<br>&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp; In the code usage mode, set return_ocr_result_in_table=True whrn call can get the detection and recognition results of each text in the table area, corresponding to the following fields: <br>&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp; `boxes`: text detection boxes.<br>&emsp;&emsp;&emsp;&emsp;&emsp;&emsp;&emsp; `rec_res`: text recognition results.<br> OCR: A tuple containing the detection boxes and recognition results of each single text. |
+After the recognition is completed, each image will have a directory with the same name under the directory specified by the `output` field. Each table in the image will be stored as an excel, and the picture area will be cropped and saved. The filename of  excel and picture is their coordinates in the image.
  ```
  /output/table/1/
    └─ res.txt
-    └─ [454, 360, 824, 658].xlsx  表格识别结果
+    └─ [454, 360, 824, 658].xlsx        table recognition result
-    └─ [16, 2, 828, 305].jpg			被裁剪出的图片区域
+    └─ [16, 2, 828, 305].jpg            picture in Image
-    └─ [17, 361, 404, 711].xlsx		表格识别结果
+    └─ [17, 361, 404, 711].xlsx        table recognition result
  ```
 <a name="232"></a>
 #### 2.3.2 DocVQA
-请参考：[文档视觉问答](../vqa/README.md)。
+Please refer to: [Documentation Visual Q&A](../vqa/README.md) .
 <a name="24"></a>
-### 2.4 参数说明
+### 2.4 Parameter Description
-| 字段            | 说明                                     | 默认值                                      |
+| field                | description                                                                                                                                                                                                                                                      | default                                                 |
-| --------------- | ---------------------------------------- | ------------------------------------------- |
+|----------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------|
-| output          | excel和识别结果保存的地址                | ./output/table                              |
+| output               | The save path of result                                                                                                                                                                                                                                          | ./output/table                                          |
-| table_max_len   | 表格结构模型预测时，图像的长边resize尺度 | 488                                         |
+| table_max_len        | When the table structure model predicts, the long side of the image                                                                                                                                                                                              | 488                                                     |
-| table_model_dir | 表格结构模型 inference 模型地址          | None                                        |
+| table_model_dir      | the path of table structure model                                                                                                                                                                                                                                | None                                                    |
-| table_char_dict_path | 表格结构模型所用字典地址                 | ../ppocr/utils/dict/table_structure_dict.txt |
+| table_char_dict_path | the dict path of table structure model                                                                                                                                                                                                                           | ../ppocr/utils/dict/table_structure_dict.txt            |
-| layout_path_model | 版面分析模型模型地址，可以为在线地址或者本地地址，当为本地地址时，需要指定 layout_label_map, 命令行模式下可通过--layout_label_map='{0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"}' 指定              | lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config |
+| layout_path_model    | The model path of the layout analysis model, which can be an online address or a local path. When it is a local path, layout_label_map needs to be set. In command line mode, use --layout_label_map='{0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"}' | lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config |
-| layout_label_map | 版面分析模型模型label映射字典                 | None |
+| layout_label_map     | Layout analysis model model label mapping dictionary path                                                                                                                                                                                                        | None                                                    |
-| model_name_or_path | VQA SER模型地址                | None |
+| model_name_or_path   | the model path of VQA SER model                                                                                                                                                                                                                                  | None                                                    |
-| max_seq_length | VQA SER模型最大支持token长度              | 512 |
+| max_seq_length       | the max token length of VQA SER model                                                                                                                                                                                                                            | 512                                                     |
-| label_map_path | VQA SER 标签文件地址              | ./vqa/labels/labels_ser.txt |
+| label_map_path       | the label path of VQA SER model                                                                                                                                                                                                                                  | ./vqa/labels/labels_ser.txt                             |
-| mode | pipeline预测模式，structure: 版面分析+表格识别; VQA: SER文档信息抽取              | structure |
+| layout               | Whether to perform layout analysis in forward                                                                                                                                                                                                                    | True                                                    |
+| table                | Whether to perform table recognition in forward                                                                                                                                                                                                                  | True                                                    |
-大部分参数和PaddleOCR whl包保持一致，见 [whl包文档](../../doc/doc_ch/whl.md)
+| ocr                  | Whether to perform ocr for non-table areas in layout analysis. When layout is False, it will be automatically set to False                                                                                                                                                                                                                 | True                                                    |
+Most of the parameters are consistent with the PaddleOCR whl package, see [whl package documentation](../../doc/doc_en/whl.md)
--- a/ppstructure/predict_system.py
+++ b/ppstructure/predict_system.py
@@ -23,9 +23,10 @@ sys.path.append(os.path.abspath(os.path.join(__dir__, '..')))
 os.environ["FLAGS_allocator_strategy"] = 'auto_growth'
 import cv2
 import json
-import numpy as np
 import time
 import logging
+from copy import deepcopy
+from attrdict import AttrDict
 from ppocr.utils.utility import get_image_file_list, check_and_read_gif
 from ppocr.utils.logging import get_logger
@@ -40,16 +41,18 @@ class StructureSystem(object):
    def __init__(self, args):
        self.mode = args.mode
        if self.mode == 'structure':
-            import layoutparser as lp
-            # args.det_limit_type = 'resize_long'
-            args.drop_score = 0
            if not args.show_log:
                logger.setLevel(logging.INFO)
-            self.text_system = TextSystem(args)
+            if args.layout == False and args.ocr == True:
-            self.table_system = TableSystem(args,
+                args.ocr = False
-                                            self.text_system.text_detector,
+                logger.warning(
-                                            self.text_system.text_recognizer)
+                    "When args.layout is false, args.ocr is automatically set to false"
+                )
+            args.drop_score = 0
+            # init layout and ocr model
+            self.text_system = None
+            if args.layout:
+                import layoutparser as lp
                config_path = None
                model_path = None
                if os.path.isdir(args.layout_path_model):
@@ -64,29 +67,50 @@ class StructureSystem(object):
                    enable_mkldnn=args.enable_mkldnn,
                    enforce_cpu=not args.use_gpu,
                    thread_num=args.cpu_threads)
-            self.use_angle_cls = args.use_angle_cls
+                if args.ocr:
-            self.drop_score = args.drop_score
+                    self.text_system = TextSystem(args)
+            else:
+                self.table_layout = None
+            if args.table:
+                if self.text_system is not None:
+                    self.table_system = TableSystem(
+                        args, self.text_system.text_detector,
+                        self.text_system.text_recognizer)
+                else:
+                    self.table_system = TableSystem(args)
+            else:
+                self.table_system = None
        elif self.mode == 'vqa':
            raise NotImplementedError
-    def __call__(self, img):
+    def __call__(self, img, return_ocr_result_in_table=False):
        if self.mode == 'structure':
            ori_im = img.copy()
+            if self.table_layout is not None:
                layout_res = self.table_layout.detect(img[..., ::-1])
+            else:
+                h, w = ori_im.shape[:2]
+                layout_res = [AttrDict(coordinates=[0, 0, w, h], type='Table')]
            res_list = []
            for region in layout_res:
+                res = ''
                x1, y1, x2, y2 = region.coordinates
                x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
                roi_img = ori_im[y1:y2, x1:x2, :]
                if region.type == 'Table':
-                    res = self.table_system(roi_img)
+                    if self.table_system is not None:
+                        res = self.table_system(roi_img,
+                                                return_ocr_result_in_table)
                else:
+                    if self.text_system is not None:
                        filter_boxes, filter_rec_res = self.text_system(roi_img)
                        # remove style char
                        style_token = [
                            '<strike>', '<strike>', '<sup>', '</sub>', '<b>',
-                        '</b>', '<sub>', '</sup>', '<overline>', '</overline>',
+                            '</b>', '<sub>', '</sup>', '<overline>',
-                        '<underline>', '</underline>', '<i>', '</i>'
+                            '</overline>', '<underline>', '</underline>', '<i>',
+                            '</i>'
                        ]
                        res = []
                        for box, rec_res in zip(filter_boxes, filter_rec_res):
@@ -106,31 +130,33 @@ class StructureSystem(object):
                    'img': roi_img,
                    'res': res
                })
+            return res_list
        elif self.mode == 'vqa':
            raise NotImplementedError
-        return res_list
+        return None
 def save_structure_res(res, save_folder, img_name):
    excel_save_folder = os.path.join(save_folder, img_name)
    os.makedirs(excel_save_folder, exist_ok=True)
+    res_cp = deepcopy(res)
    # save res
    with open(
            os.path.join(excel_save_folder, 'res.txt'), 'w',
            encoding='utf8') as f:
-        for region in res:
+        for region in res_cp:
-            if region['type'] == 'Table':
+            roi_img = region.pop('img')
+            f.write('{}\n'.format(json.dumps(region)))
+            if region['type'] == 'Table' and len(region[
+                    'res']) > 0 and 'html' in region['res']:
                excel_path = os.path.join(excel_save_folder,
                                          '{}.xlsx'.format(region['bbox']))
-                to_excel(region['res'], excel_path)
+                to_excel(region['res']['html'], excel_path)
            elif region['type'] == 'Figure':
-                roi_img = region['img']
                img_path = os.path.join(excel_save_folder,
                                        '{}.jpg'.format(region['bbox']))
                cv2.imwrite(img_path, roi_img)
-            else:
-                for text_result in region['res']:
-                    f.write('{}\n'.format(json.dumps(text_result)))
 def main(args):

--- a/ppstructure/table/README.md
+++ b/ppstructure/table/README.md
@@ -51,7 +51,7 @@ wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_tab
 wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
 cd ..
 # run
-python3 table/predict_table.py --det_model_dir=inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=inference/en_ppocr_mobile_v2.0_table_rec_infer --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer --image_dir=../doc/table/table.jpg --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --det_limit_side_len=736 --det_limit_type=min --output ../output/table
+python3 table/predict_table.py --det_model_dir=inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=inference/en_ppocr_mobile_v2.0_table_rec_infer --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer --image_dir=./docs/table/table.jpg --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --det_limit_side_len=736 --det_limit_type=min --output ./output/table
 ```
 Note: The above model is trained on the PubLayNet dataset and only supports English scanning scenarios. If you need to identify other scenarios, you need to train the model yourself and replace the three fields `det_model_dir`, `rec_model_dir`, `table_model_dir`.

--- a/ppstructure/table/README_ch.md
+++ b/ppstructure/table/README_ch.md
@@ -61,7 +61,7 @@ wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_tab
 wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
 cd ..
 # 执行预测
-python3 table/predict_table.py --det_model_dir=inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=inference/en_ppocr_mobile_v2.0_table_rec_infer --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer --image_dir=../doc/table/table.jpg --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --det_limit_side_len=736 --det_limit_type=min --output ../output/table
+python3 table/predict_table.py --det_model_dir=inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=inference/en_ppocr_mobile_v2.0_table_rec_infer --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer --image_dir=./docs/table/table.jpg --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --det_limit_side_len=736 --det_limit_type=min --output ./output/table
 ```
 运行完成后，每张图片的excel表格会保存到output字段指定的目录下

--- a/ppstructure/table/predict_table.py
+++ b/ppstructure/table/predict_table.py
@@ -54,16 +54,20 @@ def expand(pix, det_box, shape):
 class TableSystem(object):
    def __init__(self, args, text_detector=None, text_recognizer=None):
-        self.text_detector = predict_det.TextDetector(args) if text_detector is None else text_detector
+        self.text_detector = predict_det.TextDetector(
-        self.text_recognizer = predict_rec.TextRecognizer(args) if text_recognizer is None else text_recognizer
+            args) if text_detector is None else text_detector
+        self.text_recognizer = predict_rec.TextRecognizer(
+            args) if text_recognizer is None else text_recognizer
        self.table_structurer = predict_strture.TableStructurer(args)
-    def __call__(self, img):
+    def __call__(self, img, return_ocr_result_in_table=False):
+        result = dict()
        ori_im = img.copy()
        structure_res, elapse = self.table_structurer(copy.deepcopy(img))
        dt_boxes, elapse = self.text_detector(copy.deepcopy(img))
        dt_boxes = sorted_boxes(dt_boxes)
+        if return_ocr_result_in_table:
+            result['boxes'] = [x.tolist() for x in dt_boxes]
        r_boxes = []
        for box in dt_boxes:
            x_min = box[:, 0].min() - 1
@@ -88,14 +92,17 @@ class TableSystem(object):
        rec_res, elapse = self.text_recognizer(img_crop_list)
        logger.debug("rec_res num  : {}, elapse : {}".format(
            len(rec_res), elapse))
+        if return_ocr_result_in_table:
+            result['rec_res'] = rec_res
        pred_html, pred = self.rebuild_table(structure_res, dt_boxes, rec_res)
-        return pred_html
+        result['html'] = pred_html
+        return result
    def rebuild_table(self, structure_res, dt_boxes, rec_res):
        pred_structures, pred_bboxes = structure_res
        matched_index = self.match_result(dt_boxes, pred_bboxes)
-        pred_html, pred = self.get_pred_html(pred_structures, matched_index, rec_res)
+        pred_html, pred = self.get_pred_html(pred_structures, matched_index,
+                                             rec_res)
        return pred_html, pred
    def match_result(self, dt_boxes, pred_bboxes):
@@ -104,11 +111,13 @@ class TableSystem(object):
            # gt_box = [np.min(gt_box[:, 0]), np.min(gt_box[:, 1]), np.max(gt_box[:, 0]), np.max(gt_box[:, 1])]
            distances = []
            for j, pred_box in enumerate(pred_bboxes):
-                distances.append(
+                distances.append((distance(gt_box, pred_box),
-                    (distance(gt_box, pred_box), 1. - compute_iou(gt_box, pred_box)))  # 获取两两cell之间的L1距离和 1- IOU
+                                  1. - compute_iou(gt_box, pred_box)
+                                  ))  # 获取两两cell之间的L1距离和 1- IOU
            sorted_distances = distances.copy()
            # 根据距离和IOU挑选最"近"的cell
-            sorted_distances = sorted(sorted_distances, key=lambda item: (item[1], item[0]))
+            sorted_distances = sorted(
+                sorted_distances, key=lambda item: (item[1], item[0]))
            if distances.index(sorted_distances[0]) not in matched.keys():
                matched[distances.index(sorted_distances[0])] = [i]
            else:
@@ -122,7 +131,8 @@ class TableSystem(object):
            if '</td>' in tag:
                if td_index in matched_index.keys():
                    b_with = False
-                    if '<b>' in ocr_contents[matched_index[td_index][0]] and len(matched_index[td_index]) > 1:
+                    if '<b>' in ocr_contents[matched_index[td_index][
+                            0]] and len(matched_index[td_index]) > 1:
                        b_with = True
                        end_html.extend('<b>')
                    for i, td_index_index in enumerate(matched_index[td_index]):
@@ -138,7 +148,8 @@ class TableSystem(object):
                                content = content[:-4]
                            if len(content) == 0:
                                continue
-                            if i != len(matched_index[td_index]) - 1 and ' ' != content[-1]:
+                            if i != len(matched_index[
+                                    td_index]) - 1 and ' ' != content[-1]:
                                content += ' '
                        end_html.extend(content)
                    if b_with:
@@ -187,18 +198,19 @@ def main(args):
    for i, image_file in enumerate(image_file_list):
        logger.info("[{}/{}] {}".format(i, img_num, image_file))
        img, flag = check_and_read_gif(image_file)
-        excel_path = os.path.join(args.output, os.path.basename(image_file).split('.')[0] + '.xlsx')
+        excel_path = os.path.join(
+            args.output, os.path.basename(image_file).split('.')[0] + '.xlsx')
        if not flag:
            img = cv2.imread(image_file)
        if img is None:
            logger.error("error in loading image:{}".format(image_file))
            continue
        starttime = time.time()
-        pred_html = text_sys(img)
+        pred_res = text_sys(img)
+        pred_html = pred_res['html']
+        logger.info(pred_html)
        to_excel(pred_html, excel_path)
        logger.info('excel saved to {}'.format(excel_path))
-        logger.info(pred_html)
        elapse = time.time() - starttime
        logger.info("Predict time : {:.3f}s".format(elapse))