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

applications/中文表格识别.md

+# 智能运营：通用中文表格识别
+
+- [1. 背景介绍](#1-背景介绍)
+- [2. 中文表格识别](#2-中文表格识别)
+- [2.1 环境准备](#21-环境准备)
+- [2.2 准备数据集](#22-准备数据集)
+    - [2.2.1 划分训练测试集](#221-划分训练测试集)
+    - [2.2.2 查看数据集](#222-查看数据集)
+- [2.3 训练](#23-训练)
+- [2.4 验证](#24-验证)
+- [2.5 训练引擎推理](#25-训练引擎推理)
+- [2.6 模型导出](#26-模型导出)
+- [2.7 预测引擎推理](#27-预测引擎推理)
+- [2.8 表格识别](#28-表格识别)
+- [3. 表格属性识别](#3-表格属性识别)
+- [3.1 代码、环境、数据准备](#31-代码环境数据准备)
+    - [3.1.1 代码准备](#311-代码准备)
+    - [3.1.2 环境准备](#312-环境准备)
+    - [3.1.3 数据准备](#313-数据准备)
+- [3.2 表格属性识别训练](#32-表格属性识别训练)
+- [3.3 表格属性识别推理和部署](#33-表格属性识别推理和部署)
+    - [3.3.1 模型转换](#331-模型转换)
+    - [3.3.2 模型推理](#332-模型推理)
+
+## 1. 背景介绍
+
+中文表格识别在金融行业有着广泛的应用，如保险理赔、财报分析和信息录入等领域。当前，金融行业的表格识别主要以手动录入为主，开发一种自动表格识别成为丞待解决的问题。
+![](https://ai-studio-static-online.cdn.bcebos.com/d1e7780f0c7745ada4be540decefd6288e4d59257d8141f6842682a4c05d28b6)
+
+
+在金融行业中，表格图像主要有清单类的单元格密集型表格，申请表类的大单元格表格，拍照表格和倾斜表格四种主要形式。
+
+![](https://ai-studio-static-online.cdn.bcebos.com/da82ae8ef8fd479aaa38e1049eb3a681cf020dc108fa458eb3ec79da53b45fd1)
+![](https://ai-studio-static-online.cdn.bcebos.com/5ffff2093a144a6993a75eef71634a52276015ee43a04566b9c89d353198c746)
+
+
+当前的表格识别算法不能很好的处理这些场景下的表格图像。在本例中，我们使用PP-Structurev2最新发布的表格识别模型SLANet来演示如何进行中文表格是识别。同时，为了方便作业流程，我们使用表格属性识别模型对表格图像的属性进行识别，对表格的难易程度进行判断，加快人工进行校对速度。
+
+本项目AI Studio链接：https://aistudio.baidu.com/aistudio/projectdetail/4588067
+
+## 2. 中文表格识别
+### 2.1 环境准备
+
+
+```python
+# 下载PaddleOCR代码
+! git clone -b dygraph https://gitee.com/paddlepaddle/PaddleOCR
+```
+
+
+```python
+# 安装PaddleOCR环境
+! pip install -r PaddleOCR/requirements.txt --force-reinstall
+! pip install protobuf==3.19
+```
+
+### 2.2 准备数据集
+
+本例中使用的数据集采用表格[生成工具](https://github.com/WenmuZhou/TableGeneration)制作。
+
+使用如下命令对数据集进行解压，并查看数据集大小
+
+
+```python
+! cd data/data165849 && tar -xf table_gen_dataset.tar && cd -
+! wc -l data/data165849/table_gen_dataset/gt.txt
+```
+
+#### 2.2.1 划分训练测试集
+
+使用下述命令将数据集划分为训练集和测试集, 这里将90%划分为训练集，10%划分为测试集
+
+
+```python
+import random
+with open('/home/aistudio/data/data165849/table_gen_dataset/gt.txt') as f:
+    lines = f.readlines()
+random.shuffle(lines)
+train_len = int(len(lines)*0.9)
+train_list = lines[:train_len]
+val_list = lines[train_len:]
+
+# 保存结果
+with open('/home/aistudio/train.txt','w',encoding='utf-8') as f:
+    f.writelines(train_list)
+with open('/home/aistudio/val.txt','w',encoding='utf-8') as f:
+    f.writelines(val_list)
+```
+
+划分完成后，数据集信息如下
+
+|类型|数量|图片地址|标注文件路径|
+|---|---|---|---|
+|训练集|18000|/home/aistudio/data/data165849/table_gen_dataset|/home/aistudio/train.txt|
+|测试集|2000|/home/aistudio/data/data165849/table_gen_dataset|/home/aistudio/val.txt|
+
+#### 2.2.2 查看数据集
+
+
+```python
+import cv2
+import os, json
+import numpy as np
+from matplotlib import pyplot as plt
+%matplotlib inline
+
+def parse_line(data_dir, line):
+    data_line = line.strip("\n")
+    info = json.loads(data_line)
+    file_name = info['filename']
+    cells = info['html']['cells'].copy()
+    structure = info['html']['structure']['tokens'].copy()
+
+    img_path = os.path.join(data_dir, file_name)
+    if not os.path.exists(img_path):
+        print(img_path)
+        return None
+    data = {
+        'img_path': img_path,
+        'cells': cells,
+        'structure': structure,
+        'file_name': file_name
+    }
+    return data
+
+def draw_bbox(img_path, points, color=(255, 0, 0), thickness=2):
+    if isinstance(img_path, str):
+        img_path = cv2.imread(img_path)
+    img_path = img_path.copy()
+    for point in points:
+        cv2.polylines(img_path, [point.astype(int)], True, color, thickness)
+    return img_path
+
+
+def rebuild_html(data):
+    html_code = data['structure']
+    cells = data['cells']
+    to_insert = [i for i, tag in enumerate(html_code) if tag in ('<td>', '>')]
+
+    for i, cell in zip(to_insert[::-1], cells[::-1]):
+        if cell['tokens']:
+            text = ''.join(cell['tokens'])
+            # skip empty text
+            sp_char_list = ['<b>', '</b>', '\u2028', ' ', '<i>', '</i>']
+            text_remove_style = skip_char(text, sp_char_list)
+            if len(text_remove_style) == 0:
+                continue
+            html_code.insert(i + 1, text)
+
+    html_code = ''.join(html_code)
+    return html_code
+
+
+def skip_char(text, sp_char_list):
+    """
+    skip empty cell
+    @param text: text in cell
+    @param sp_char_list: style char and special code
+    @return:
+    """
+    for sp_char in sp_char_list:
+        text = text.replace(sp_char, '')
+    return text
+
+save_dir = '/home/aistudio/vis'
+os.makedirs(save_dir, exist_ok=True)
+image_dir = '/home/aistudio/data/data165849/'
+html_str = '<table border="1">'
+
+# 解析标注信息并还原html表格
+data = parse_line(image_dir, val_list[0])
+
+img = cv2.imread(data['img_path'])
+img_name = ''.join(os.path.basename(data['file_name']).split('.')[:-1])
+img_save_name = os.path.join(save_dir, img_name)
+boxes = [np.array(x['bbox']) for x in data['cells']]
+show_img = draw_bbox(data['img_path'], boxes)
+cv2.imwrite(img_save_name + '_show.jpg', show_img)
+
+html = rebuild_html(data)
+html_str += html
+html_str += '</table>'
+
+# 显示标注的html字符串
+from IPython.core.display import display, HTML
+display(HTML(html_str))
+# 显示单元格坐标
+plt.figure(figsize=(15,15))
+plt.imshow(show_img)
+plt.show()
+```
+
+### 2.3 训练
+
+这里选用PP-Structurev2中的表格识别模型[SLANet](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/configs/table/SLANet.yml)
+
+SLANet是PP-Structurev2全新推出的表格识别模型，相比PP-Structurev1中TableRec-RARE，在速度不变的情况下精度提升4.7%。TEDS提升2%
+
+
+|算法|Acc|[TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src)|Speed|
+| --- | --- | --- | ---|
+| EDD<sup>[2]</sup> |x| 88.3% |x|
+| TableRec-RARE(ours) | 71.73%| 93.88% |779ms|
+| SLANet(ours) | 76.31%|    95.89%|766ms|
+
+进行训练之前先使用如下命令下载预训练模型
+
+
+```python
+# 进入PaddleOCR工作目录
+os.chdir('/home/aistudio/PaddleOCR')
+# 下载英文预训练模型
+! wget  -nc -P  ./pretrain_models/  https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_train.tar --no-check-certificate
+! cd ./pretrain_models/ && tar xf en_ppstructure_mobile_v2.0_SLANet_train.tar  && cd ../
+```
+
+使用如下命令即可启动训练，需要修改的配置有
+
+|字段|修改值|含义|
+|---|---|---|
+|Global.pretrained_model|./pretrain_models/en_ppstructure_mobile_v2.0_SLANet_train/best_accuracy.pdparams|指向英文表格预训练模型地址|
+|Global.eval_batch_step|562|模型多少step评估一次，一般设置为一个epoch总的step数|
+|Optimizer.lr.name|Const|学习率衰减器 |
+|Optimizer.lr.learning_rate|0.0005|学习率设为之前的0.05倍 |
+|Train.dataset.data_dir|/home/aistudio/data/data165849|指向训练集图片存放目录 |
+|Train.dataset.label_file_list|/home/aistudio/data/data165849/table_gen_dataset/train.txt|指向训练集标注文件 |
+|Train.loader.batch_size_per_card|32|训练时每张卡的batch_size |
+|Train.loader.num_workers|1|训练集多进程数据读取的进程数，在aistudio中需要设为1 |
+|Eval.dataset.data_dir|/home/aistudio/data/data165849|指向测试集图片存放目录 |
+|Eval.dataset.label_file_list|/home/aistudio/data/data165849/table_gen_dataset/val.txt|指向测试集标注文件 |
+|Eval.loader.batch_size_per_card|32|测试时每张卡的batch_size |
+|Eval.loader.num_workers|1|测试集多进程数据读取的进程数，在aistudio中需要设为1 |
+
+
+已经修改好的配置存储在 `/home/aistudio/SLANet_ch.yml`
+
+
+```python
+import os
+os.chdir('/home/aistudio/PaddleOCR')
+! python3 tools/train.py -c /home/aistudio/SLANet_ch.yml
+```
+
+大约在7个epoch后达到最高精度 97.49%
+
+### 2.4 验证
+
+训练完成后，可使用如下命令在测试集上评估最优模型的精度
+
+
+```python
+! python3 tools/eval.py -c /home/aistudio/SLANet_ch.yml -o Global.checkpoints=/home/aistudio/PaddleOCR/output/SLANet_ch/best_accuracy.pdparams
+```
+
+### 2.5 训练引擎推理
+使用如下命令可使用训练引擎对单张图片进行推理
+
+
+```python
+import os;os.chdir('/home/aistudio/PaddleOCR')
+! python3 tools/infer_table.py -c /home/aistudio/SLANet_ch.yml -o Global.checkpoints=/home/aistudio/PaddleOCR/output/SLANet_ch/best_accuracy.pdparams Global.infer_img=/home/aistudio/data/data165849/table_gen_dataset/img/no_border_18298_G7XZH93DDCMATGJQ8RW2.jpg
+```
+
+
+```python
+import cv2
+from matplotlib import pyplot as plt
+%matplotlib inline
+
+# 显示原图
+show_img = cv2.imread('/home/aistudio/data/data165849/table_gen_dataset/img/no_border_18298_G7XZH93DDCMATGJQ8RW2.jpg')
+plt.figure(figsize=(15,15))
+plt.imshow(show_img)
+plt.show()
+
+# 显示预测的单元格
+show_img = cv2.imread('/home/aistudio/PaddleOCR/output/infer/no_border_18298_G7XZH93DDCMATGJQ8RW2.jpg')
+plt.figure(figsize=(15,15))
+plt.imshow(show_img)
+plt.show()
+```
+
+### 2.6 模型导出
+
+使用如下命令可将模型导出为inference模型
+
+
+```python
+! python3 tools/export_model.py -c /home/aistudio/SLANet_ch.yml -o Global.checkpoints=/home/aistudio/PaddleOCR/output/SLANet_ch/best_accuracy.pdparams Global.save_inference_dir=/home/aistudio/SLANet_ch/infer
+```
+
+### 2.7 预测引擎推理
+使用如下命令可使用预测引擎对单张图片进行推理
+
+
+
+```python
+os.chdir('/home/aistudio/PaddleOCR/ppstructure')
+! python3 table/predict_structure.py \
+    --table_model_dir=/home/aistudio/SLANet_ch/infer \
+    --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
+    --image_dir=/home/aistudio/data/data165849/table_gen_dataset/img/no_border_18298_G7XZH93DDCMATGJQ8RW2.jpg \
+    --output=../output/inference
+```
+
+
+```python
+# 显示原图
+show_img = cv2.imread('/home/aistudio/data/data165849/table_gen_dataset/img/no_border_18298_G7XZH93DDCMATGJQ8RW2.jpg')
+plt.figure(figsize=(15,15))
+plt.imshow(show_img)
+plt.show()
+
+# 显示预测的单元格
+show_img = cv2.imread('/home/aistudio/PaddleOCR/output/inference/no_border_18298_G7XZH93DDCMATGJQ8RW2.jpg')
+plt.figure(figsize=(15,15))
+plt.imshow(show_img)
+plt.show()
+```
+
+### 2.8 表格识别
+
+在表格结构模型训练完成后，可结合OCR检测识别模型，对表格内容进行识别。
+
+首先下载PP-OCRv3文字检测识别模型
+
+
+```python
+# 下载PP-OCRv3文本检测识别模型并解压
+! wget  -nc -P  ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar --no-check-certificate
+! wget  -nc -P  ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar --no-check-certificate
+! cd ./inference/ && tar xf ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar  && cd ../
+```
+
+模型下载完成后，使用如下命令进行表格识别
+
+
+```python
+import os;os.chdir('/home/aistudio/PaddleOCR/ppstructure')
+! python3 table/predict_table.py \
+    --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \
+    --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer  \
+    --table_model_dir=/home/aistudio/SLANet_ch/infer \
+    --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
+    --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
+    --image_dir=/home/aistudio/data/data165849/table_gen_dataset/img/no_border_18298_G7XZH93DDCMATGJQ8RW2.jpg \
+    --output=../output/table
+```
+
+
+```python
+# 显示原图
+show_img = cv2.imread('/home/aistudio/data/data165849/table_gen_dataset/img/no_border_18298_G7XZH93DDCMATGJQ8RW2.jpg')
+plt.figure(figsize=(15,15))
+plt.imshow(show_img)
+plt.show()
+
+# 显示预测结果
+from IPython.core.display import display, HTML
+display(HTML('<html><body><table><tr><td colspan="5">alleadersh</td><td rowspan="2">不贰过，推</td><td rowspan="2">从自己参与浙江数</td><td rowspan="2">。另一方</td></tr><tr><td>AnSha</td><td>自己越</td><td>共商共建工作协商</td><td>w.east </td><td>抓好改革试点任务</td></tr><tr><td>Edime</td><td>ImisesElec</td><td>怀天下”。</td><td></td><td>22.26 </td><td>31.61</td><td>4.30 </td><td>794.94</td></tr><tr><td rowspan="2">ip</td><td> Profundi</td><td>：2019年12月1</td><td>Horspro</td><td>444.48</td><td>2.41 </td><td>87</td><td>679.98</td></tr><tr><td> iehaiTrain</td><td>组长蒋蕊</td><td>Toafterdec</td><td>203.43</td><td>23.54 </td><td>4</td><td>4266.62</td></tr><tr><td>Tyint </td><td> roudlyRol</td><td>谢您的好意，我知道</td><td>ErChows</td><td></td><td>48.90</td><td>1031</td><td>6</td></tr><tr><td>NaFlint</td><td></td><td>一辈的</td><td>aterreclam</td><td>7823.86</td><td>9829.23</td><td>7.96 </td><td> 3068</td></tr><tr><td>家上下游企业，5</td><td>Tr</td><td>景象。当地球上的我们</td><td>Urelaw</td><td>799.62</td><td>354.96</td><td>12.98</td><td>33 </td></tr><tr><td>赛事（</td><td> uestCh</td><td>复制的业务模式并</td><td>Listicjust</td><td>9.23</td><td></td><td>92</td><td>53.22</td></tr><tr><td> Ca</td><td> Iskole</td><td>扶贫"之名引导</td><td> Papua </td><td>7191.90</td><td>1.65</td><td>3.62</td><td>48</td></tr><tr><td rowspan="2">避讳</td><td>ir</td><td>但由于</td><td>Fficeof</td><td>0.22</td><td>6.37</td><td>7.17</td><td>3397.75</td></tr><tr><td>ndaTurk</td><td>百处遗址</td><td>gMa</td><td>1288.34</td><td>2053.66</td><td>2.29</td><td>885.45</td></tr></table></body></html>'))
+```
+
+## 3. 表格属性识别
+### 3.1 代码、环境、数据准备
+#### 3.1.1 代码准备
+首先，我们需要准备训练表格属性的代码，PaddleClas集成了PULC方案，该方案可以快速获得一个在CPU上用时2ms的属性识别模型。PaddleClas代码可以clone下载得到。获取方式如下：
+
+
+
+```python
+! git clone -b develop https://gitee.com/paddlepaddle/PaddleClas
+```
+
+#### 3.1.2 环境准备
+其次，我们需要安装训练PaddleClas相关的依赖包
+
+
+```python
+! pip install -r PaddleClas/requirements.txt --force-reinstall
+! pip install protobuf==3.20.0
+```
+
+
+#### 3.1.3 数据准备
+
+最后，准备训练数据。在这里，我们一共定义了表格的6个属性，分别是表格来源、表格数量、表格颜色、表格清晰度、表格有无干扰、表格角度。其可视化如下：
+
+![](https://user-images.githubusercontent.com/45199522/190587903-ccdfa6fb-51e8-42de-b08b-a127cb04e304.png)
+
+这里，我们提供了一个表格属性的demo子集，可以快速迭代体验。下载方式如下：
+
+
+```python
+%cd PaddleClas/dataset
+!wget https://paddleclas.bj.bcebos.com/data/PULC/table_attribute.tar
+!tar -xf table_attribute.tar
+%cd ../PaddleClas/dataset
+%cd ../
+```
+
+### 3.2 表格属性识别训练
+表格属性训练整体pipelinie如下：
+
+![](https://user-images.githubusercontent.com/45199522/190599426-3415b38e-e16e-4e68-9253-2ff531b1b5ca.png)
+
+1.训练过程中，图片经过预处理之后，送入到骨干网络之中，骨干网络将抽取表格图片的特征，最终该特征连接输出的FC层，FC层经过Sigmoid激活函数后和真实标签做交叉熵损失函数，优化器通过对该损失函数做梯度下降来更新骨干网络的参数，经过多轮训练后，骨干网络的参数可以对为止图片做很好的预测；
+
+2.推理过程中，图片经过预处理之后，送入到骨干网络之中，骨干网络加载学习好的权重后对该表格图片做出预测，预测的结果为一个6维向量，该向量中的每个元素反映了每个属性对应的概率值，通过对该值进一步卡阈值之后，得到最终的输出，最终的输出描述了该表格的6个属性。
+
+当准备好相关的数据之后，可以一键启动表格属性的训练，训练代码如下：
+
+
+```python
+
+!python tools/train.py -c ./ppcls/configs/PULC/table_attribute/PPLCNet_x1_0.yaml -o Global.device=cpu -o Global.epochs=10
+```
+
+### 3.3 表格属性识别推理和部署
+#### 3.3.1 模型转换
+当训练好模型之后，需要将模型转换为推理模型进行部署。转换脚本如下：
+
+
+```python
+!python tools/export_model.py -c ppcls/configs/PULC/table_attribute/PPLCNet_x1_0.yaml -o Global.pretrained_model=output/PPLCNet_x1_0/best_model
+```
+
+执行以上命令之后，会在当前目录上生成`inference`文件夹，该文件夹中保存了当前精度最高的推理模型。
+
+#### 3.3.2 模型推理
+安装推理需要的paddleclas包, 此时需要通过下载安装paddleclas的develop的whl包
+
+
+
+```python
+!pip install https://paddleclas.bj.bcebos.com/whl/paddleclas-0.0.0-py3-none-any.whl
+```
+
+进入`deploy`目录下即可对模型进行推理
+
+
+```python
+%cd deploy/
+```
+
+推理命令如下：
+
+
+```python
+!python python/predict_cls.py -c configs/PULC/table_attribute/inference_table_attribute.yaml -o Global.inference_model_dir="../inference" -o Global.infer_imgs="../dataset/table_attribute/Table_val/val_9.jpg"
+!python python/predict_cls.py -c configs/PULC/table_attribute/inference_table_attribute.yaml -o Global.inference_model_dir="../inference" -o Global.infer_imgs="../dataset/table_attribute/Table_val/val_3253.jpg"
+```
+
+推理的表格图片：
+
+![](https://user-images.githubusercontent.com/45199522/190596141-74f4feda-b082-46d7-908d-b0bd5839b430.png)
+
+预测结果如下：
+```
+val_9.jpg:	 {'attributes': ['Scanned', 'Little', 'Black-and-White', 'Clear', 'Without-Obstacles', 'Horizontal'], 'output': [1, 1, 1, 1, 1, 1]}
+```
+
+
+推理的表格图片：
+
+![](https://user-images.githubusercontent.com/45199522/190597086-2e685200-22d0-4042-9e46-f61f24e02e4e.png)
+
+预测结果如下：
+```
+val_3253.jpg:	 {'attributes': ['Photo', 'Little', 'Black-and-White', 'Blurry', 'Without-Obstacles', 'Tilted'], 'output': [0, 1, 1, 0, 1, 0]}
+```
+
+对比两张图片可以发现，第一张图片比较清晰，表格属性的结果也偏向于比较容易识别，我们可以更相信表格识别的结果，第二张图片比较模糊，且存在倾斜现象，表格识别可能存在错误，需要我们人工进一步校验。通过表格的属性识别能力，可以进一步将“人工”和“智能”很好的结合起来，为表格识别能力的落地的精度提供保障。

configs/rec/rec_r31_robustscanner.yml

@@ -12,7 +12,7 @@ Global:
   checkpoints: 
   save_inference_dir:
   use_visualdl: False
-  infer_img: ./inference/rec_inference
+  infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
   character_dict_path: ppocr/utils/dict90.txt
   max_text_length: &max_text_length 40

configs/rec/rec_r32_gaspin_bilstm_att.yml

@@ -12,7 +12,7 @@ Global:
   checkpoints:
   save_inference_dir:
   use_visualdl: False
-  infer_img: doc/imgs_words/ch/word_1.jpg
+  infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
   character_dict_path: ./ppocr/utils/dict/spin_dict.txt
   max_text_length: 25

configs/table/table_mv3.yml

@@ -43,7 +43,6 @@ Architecture:
   Head:
     name: TableAttentionHead
     hidden_size: 256
-    loc_type: 2
     max_text_length: *max_text_length
     loc_reg_num: &loc_reg_num 4
 

doc/doc_ch/algorithm_overview.md

@@ -101,11 +101,10 @@ PaddleOCR将**持续新增**支持OCR领域前沿算法与模型，**欢迎广
 |ViTSTR|ViTSTR| 79.82% | rec_vitstr_none_ce | [训练模型](https://paddleocr.bj.bcebos.com/rec_vitstr_none_ce_train.tar) |
 |ABINet|Resnet45| 90.75% | rec_r45_abinet | [训练模型](https://paddleocr.bj.bcebos.com/rec_r45_abinet_train.tar) |
 |VisionLAN|Resnet45| 90.30% | rec_r45_visionlan | [训练模型](https://paddleocr.bj.bcebos.com/rec_r45_visionlan_train.tar) |
-|SPIN|ResNet32| 90.00% | rec_r32_gaspin_bilstm_att | coming soon |
-|RobustScanner|ResNet31| 87.77% | rec_r31_robustscanner | coming soon |
+|SPIN|ResNet32| 90.00% | rec_r32_gaspin_bilstm_att | [训练模型](https://paddleocr.bj.bcebos.com/contribution/rec_r32_gaspin_bilstm_att.tar) |
+|RobustScanner|ResNet31| 87.77% | rec_r31_robustscanner | [训练模型](https://paddleocr.bj.bcebos.com/contribution/rec_r31_robustscanner.tar)|
 |RFL|ResNetRFL| 88.63% | rec_resnet_rfl_att | [训练模型](https://paddleocr.bj.bcebos.com/contribution/rec_resnet_rfl.tar) |
 
-
 <a name="2"></a>
 
 ## 2. 端到端算法

doc/doc_ch/algorithm_rec_robustscanner.md

@@ -26,7 +26,7 @@ Zhang
 
 |模型|骨干网络|配置文件|Acc|下载链接|
 | --- | --- | --- | --- | --- |
-|RobustScanner|ResNet31|[rec_r31_robustscanner.yml](../../configs/rec/rec_r31_robustscanner.yml)|87.77%|coming soon|
+|RobustScanner|ResNet31|[rec_r31_robustscanner.yml](../../configs/rec/rec_r31_robustscanner.yml)|87.77%|[训练模型](https://paddleocr.bj.bcebos.com/contribution/rec_r31_robustscanner.tar)|
 
 注：除了使用MJSynth和SynthText两个文字识别数据集外，还加入了[SynthAdd](https://pan.baidu.com/share/init?surl=uV0LtoNmcxbO-0YA7Ch4dg)数据（提取码：627x），和部分真实数据，具体数据细节可以参考论文。
 

doc/doc_ch/algorithm_rec_spin.md

@@ -26,7 +26,7 @@ SPIN收录于AAAI2020。主要用于OCR识别任务。在任意形状文本识
 
 |模型|骨干网络|配置文件|Acc|下载链接|
 | --- | --- | --- | --- | --- |
-|SPIN|ResNet32|[rec_r32_gaspin_bilstm_att.yml](../../configs/rec/rec_r32_gaspin_bilstm_att.yml)|90.0%|coming soon|
+|SPIN|ResNet32|[rec_r32_gaspin_bilstm_att.yml](../../configs/rec/rec_r32_gaspin_bilstm_att.yml)|90.0%|[训练模型](https://paddleocr.bj.bcebos.com/contribution/rec_r32_gaspin_bilstm_att.tar)|
 
 
 <a name="2"></a>

doc/doc_ch/inference_args.md

@@ -7,6 +7,7 @@
 | 参数名称 | 类型 | 默认值 | 含义 |
 | :--: | :--: | :--: | :--: |
 |  image_dir | str | 无，必须显式指定 | 图像或者文件夹路径 |
+|  page_num | int | 0 | 当输入类型为pdf文件时有效，指定预测前面page_num页，默认预测所有页 |
 |  vis_font_path | str | "./doc/fonts/simfang.ttf" | 用于可视化的字体路径 |
 |  drop_score | float | 0.5 | 识别得分小于该值的结果会被丢弃，不会作为返回结果 |
 |  use_pdserving | bool | False | 是否使用Paddle Serving进行预测 |

doc/doc_en/algorithm_overview_en.md

@@ -98,8 +98,8 @@ Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation r
 |ViTSTR|ViTSTR| 79.82% | rec_vitstr_none_ce | [trained model](https://paddleocr.bj.bcebos.com/rec_vitstr_none_none_train.tar) |
 |ABINet|Resnet45| 90.75% | rec_r45_abinet | [trained model](https://paddleocr.bj.bcebos.com/rec_r45_abinet_train.tar) |
 |VisionLAN|Resnet45| 90.30% | rec_r45_visionlan | [trained model](https://paddleocr.bj.bcebos.com/rec_r45_visionlan_train.tar) |
-|SPIN|ResNet32| 90.00% | rec_r32_gaspin_bilstm_att | coming soon |
-|RobustScanner|ResNet31| 87.77% | rec_r31_robustscanner | coming soon |
+|SPIN|ResNet32| 90.00% | rec_r32_gaspin_bilstm_att | [trained model](https://paddleocr.bj.bcebos.com/contribution/rec_r32_gaspin_bilstm_att.tar) |
+|RobustScanner|ResNet31| 87.77% | rec_r31_robustscanner | [trained model](https://paddleocr.bj.bcebos.com/contribution/rec_r31_robustscanner.tar)|
 |RFL|ResNetRFL| 88.63% | rec_resnet_rfl_att | [trained model](https://paddleocr.bj.bcebos.com/contribution/rec_resnet_rfl.tar) |
 
 <a name="2"></a>

doc/doc_en/algorithm_rec_robustscanner_en.md

@@ -26,7 +26,7 @@ Using MJSynth and SynthText two text recognition datasets for training, and eval
 
 |Model|Backbone|config|Acc|Download link|
 | --- | --- | --- | --- | --- |
-|RobustScanner|ResNet31|[rec_r31_robustscanner.yml](../../configs/rec/rec_r31_robustscanner.yml)|87.77%|coming soon|
+|RobustScanner|ResNet31|[rec_r31_robustscanner.yml](../../configs/rec/rec_r31_robustscanner.yml)|87.77%|[trained model](https://paddleocr.bj.bcebos.com/contribution/rec_r31_robustscanner.tar)|
 
 Note:In addition to using the two text recognition datasets MJSynth and SynthText, [SynthAdd](https://pan.baidu.com/share/init?surl=uV0LtoNmcxbO-0YA7Ch4dg) data (extraction code: 627x), and some real data are used in training, the specific data details can refer to the paper.
 

doc/doc_en/algorithm_rec_spin_en.md

@@ -25,7 +25,7 @@ Using MJSynth and SynthText two text recognition datasets for training, and eval
 
 |Model|Backbone|config|Acc|Download link|
 | --- | --- | --- | --- | --- |
-|SPIN|ResNet32|[rec_r32_gaspin_bilstm_att.yml](../../configs/rec/rec_r32_gaspin_bilstm_att.yml)|90.0%|coming soon|
+|SPIN|ResNet32|[rec_r32_gaspin_bilstm_att.yml](../../configs/rec/rec_r32_gaspin_bilstm_att.yml)|90.0%|[trained model](https://paddleocr.bj.bcebos.com/contribution/rec_r32_gaspin_bilstm_att.tar) |
 
 
 <a name="2"></a>

doc/doc_en/inference_args_en.md

@@ -7,6 +7,7 @@ When using PaddleOCR for model inference, you can customize the modification par
 | parameters | type | default | implication |
 | :--: | :--: | :--: | :--: |
 |  image_dir | str | None, must be specified explicitly | Image or folder path |
+|  page_num | int | 0 | Valid when the input type is pdf file, specify to predict the previous page_num pages, all pages are predicted by default |
 |  vis_font_path | str | "./doc/fonts/simfang.ttf" | font path for visualization |
 |  drop_score | float | 0.5 | Results with a recognition score less than this value will be discarded and will not be returned as results |
 |  use_pdserving | bool | False | Whether to use Paddle Serving for prediction |

paddleocr.py

@@ -480,10 +480,11 @@ class PaddleOCR(predict_system.TextSystem):
             params.rec_image_shape = "3, 48, 320"
         else:
             params.rec_image_shape = "3, 32, 320"
-        # download model
-        maybe_download(params.det_model_dir, det_url)
-        maybe_download(params.rec_model_dir, rec_url)
-        maybe_download(params.cls_model_dir, cls_url)
+        # download model if using paddle infer
+        if not params.use_onnx:
+            maybe_download(params.det_model_dir, det_url)
+            maybe_download(params.rec_model_dir, rec_url)
+            maybe_download(params.cls_model_dir, cls_url)
 
         if params.det_algorithm not in SUPPORT_DET_MODEL:
             logger.error('det_algorithm must in {}'.format(SUPPORT_DET_MODEL))

ppocr/modeling/heads/table_att_head.py

@@ -16,6 +16,7 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
+import math
 import paddle
 import paddle.nn as nn
 from paddle import ParamAttr
@@ -42,7 +43,6 @@ class TableAttentionHead(nn.Layer):
     def __init__(self,
                  in_channels,
                  hidden_size,
-                 loc_type,
                  in_max_len=488,
                  max_text_length=800,
                  out_channels=30,
@@ -57,20 +57,16 @@ class TableAttentionHead(nn.Layer):
         self.structure_attention_cell = AttentionGRUCell(
             self.input_size, hidden_size, self.out_channels, use_gru=False)
         self.structure_generator = nn.Linear(hidden_size, self.out_channels)
-        self.loc_type = loc_type
         self.in_max_len = in_max_len
 
-        if self.loc_type == 1:
-            self.loc_generator = nn.Linear(hidden_size, 4)
+        if self.in_max_len == 640:
+            self.loc_fea_trans = nn.Linear(400, self.max_text_length + 1)
+        elif self.in_max_len == 800:
+            self.loc_fea_trans = nn.Linear(625, self.max_text_length + 1)
         else:
-            if self.in_max_len == 640:
-                self.loc_fea_trans = nn.Linear(400, self.max_text_length + 1)
-            elif self.in_max_len == 800:
-                self.loc_fea_trans = nn.Linear(625, self.max_text_length + 1)
-            else:
-                self.loc_fea_trans = nn.Linear(256, self.max_text_length + 1)
-            self.loc_generator = nn.Linear(self.input_size + hidden_size,
-                                           loc_reg_num)
+            self.loc_fea_trans = nn.Linear(256, self.max_text_length + 1)
+        self.loc_generator = nn.Linear(self.input_size + hidden_size,
+                                       loc_reg_num)
 
     def _char_to_onehot(self, input_char, onehot_dim):
         input_ont_hot = F.one_hot(input_char, onehot_dim)
@@ -80,16 +76,13 @@ class TableAttentionHead(nn.Layer):
         # if and else branch are both needed when you want to assign a variable
         # if you modify the var in just one branch, then the modification will not work.
         fea = inputs[-1]
-        if len(fea.shape) == 3:
-            pass
-        else:
-            last_shape = int(np.prod(fea.shape[2:]))  # gry added
-            fea = paddle.reshape(fea, [fea.shape[0], fea.shape[1], last_shape])
-            fea = fea.transpose([0, 2, 1])  # (NTC)(batch, width, channels)
+        last_shape = int(np.prod(fea.shape[2:]))  # gry added
+        fea = paddle.reshape(fea, [fea.shape[0], fea.shape[1], last_shape])
+        fea = fea.transpose([0, 2, 1])  # (NTC)(batch, width, channels)
         batch_size = fea.shape[0]
 
         hidden = paddle.zeros((batch_size, self.hidden_size))
-        output_hiddens = []
+        output_hiddens = paddle.zeros((batch_size, self.max_text_length + 1, self.hidden_size))
         if self.training and targets is not None:
             structure = targets[0]
             for i in range(self.max_text_length + 1):
@@ -97,7 +90,8 @@ class TableAttentionHead(nn.Layer):
                     structure[:, i], onehot_dim=self.out_channels)
                 (outputs, hidden), alpha = self.structure_attention_cell(
                     hidden, fea, elem_onehots)
-                output_hiddens.append(paddle.unsqueeze(outputs, axis=1))
+                output_hiddens[:, i, :] = outputs
+                # output_hiddens.append(paddle.unsqueeze(outputs, axis=1))
             output = paddle.concat(output_hiddens, axis=1)
             structure_probs = self.structure_generator(output)
             if self.loc_type == 1:
@@ -118,30 +112,25 @@ class TableAttentionHead(nn.Layer):
             outputs = None
             alpha = None
             max_text_length = paddle.to_tensor(self.max_text_length)
-            i = 0
-            while i < max_text_length + 1:
+            for i in range(max_text_length + 1):
                 elem_onehots = self._char_to_onehot(
                     temp_elem, onehot_dim=self.out_channels)
                 (outputs, hidden), alpha = self.structure_attention_cell(
                     hidden, fea, elem_onehots)
-                output_hiddens.append(paddle.unsqueeze(outputs, axis=1))
+                output_hiddens[:, i, :] = outputs
+                # output_hiddens.append(paddle.unsqueeze(outputs, axis=1))
                 structure_probs_step = self.structure_generator(outputs)
                 temp_elem = structure_probs_step.argmax(axis=1, dtype="int32")
-                i += 1
 
-            output = paddle.concat(output_hiddens, axis=1)
+            output = output_hiddens
             structure_probs = self.structure_generator(output)
             structure_probs = F.softmax(structure_probs)
-            if self.loc_type == 1:
-                loc_preds = self.loc_generator(output)
-                loc_preds = F.sigmoid(loc_preds)
-            else:
-                loc_fea = fea.transpose([0, 2, 1])
-                loc_fea = self.loc_fea_trans(loc_fea)
-                loc_fea = loc_fea.transpose([0, 2, 1])
-                loc_concat = paddle.concat([output, loc_fea], axis=2)
-                loc_preds = self.loc_generator(loc_concat)
-                loc_preds = F.sigmoid(loc_preds)
+            loc_fea = fea.transpose([0, 2, 1])
+            loc_fea = self.loc_fea_trans(loc_fea)
+            loc_fea = loc_fea.transpose([0, 2, 1])
+            loc_concat = paddle.concat([output, loc_fea], axis=2)
+            loc_preds = self.loc_generator(loc_concat)
+            loc_preds = F.sigmoid(loc_preds)
         return {'structure_probs': structure_probs, 'loc_preds': loc_preds}
 
 

ppstructure/table/README.md

@@ -114,7 +114,7 @@ python3 table/eval_table.py \
     --det_model_dir=path/to/det_model_dir \
     --rec_model_dir=path/to/rec_model_dir \
     --table_model_dir=path/to/table_model_dir \
-    --image_dir=../doc/table/1.png \
+    --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 \
@@ -145,6 +145,7 @@ python3 table/eval_table.py \
     --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
     --det_limit_side_len=736 \
     --det_limit_type=min \
+    --rec_image_shape=3,32,320 \
     --gt_path=path/to/gt.txt
 ```
 

ppstructure/table/README_ch.md

@@ -118,7 +118,7 @@ python3 table/eval_table.py \
     --det_model_dir=path/to/det_model_dir \
     --rec_model_dir=path/to/rec_model_dir \
     --table_model_dir=path/to/table_model_dir \
-    --image_dir=../doc/table/1.png \
+    --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 \
@@ -149,6 +149,7 @@ python3 table/eval_table.py \
     --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
     --det_limit_side_len=736 \
     --det_limit_type=min \
+    --rec_image_shape=3,32,320 \
     --gt_path=path/to/gt.txt
 ```
 

requirements.txt

@@ -15,3 +15,4 @@ premailer
 openpyxl
 attrdict
 Polygon3
+PyMuPDF==1.18.7

test_tipc/configs/en_table_structure/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

+===========================paddle2onnx_params===========================
+model_name:en_table_structure
+python:python3.7
+2onnx: paddle2onnx
+--det_model_dir:./inference/en_ppocr_mobile_v2.0_table_structure_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_save_file:./inference/en_ppocr_mobile_v2.0_table_structure_infer/model.onnx
+--rec_model_dir:
+--rec_save_file:
+--opset_version:10
+--enable_onnx_checker:True
+inference:ppstructure/table/predict_structure.py --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt
+--use_gpu:True|False
+--det_model_dir:
+--rec_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
\ No newline at end of file

test_tipc/configs/layoutxlm_ser/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:layoutxlm_ser
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=17
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=4|whole_train_whole_infer=8
+Architecture.Backbone.checkpoints:null
+train_model_name:latest
+train_infer_img_dir:ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Architecture.Backbone.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:null
+infer_export:null
+infer_quant:False
+inference:ppstructure/kie/predict_kie_token_ser.py  --kie_algorithm=LayoutXLM  --ser_dict_path=train_data/XFUND/class_list_xfun.txt --output=output
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--ser_model_dir:
+--image_dir:./ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,224,224]}]

test_tipc/configs/layoutxlm_ser/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:layoutxlm_ser
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=17
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=4|whole_train_whole_infer=8
+Architecture.Backbone.checkpoints:null
+train_model_name:latest
+train_infer_img_dir:ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o Global.print_batch_step=1 Global.eval_batch_step=[1000,1000] Train.loader.shuffle=false
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Architecture.Backbone.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:null
+infer_export:null
+infer_quant:False
+inference:ppstructure/kie/predict_kie_token_ser.py  --kie_algorithm=LayoutXLM  --ser_dict_path=train_data/XFUND/class_list_xfun.txt --output=output
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--ser_model_dir:
+--image_dir:./ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,224,224]}]

test_tipc/configs/slanet/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

+===========================paddle2onnx_params===========================
+model_name:slanet
+python:python3.7
+2onnx: paddle2onnx
+--det_model_dir:./inference/ch_ppstructure_mobile_v2.0_SLANet_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_save_file:./inference/ch_ppstructure_mobile_v2.0_SLANet_infer/model.onnx
+--rec_model_dir:
+--rec_save_file:
+--opset_version:10
+--enable_onnx_checker:True
+inference:ppstructure/table/predict_structure.py --table_char_dict_path=./ppocr/utils/dict/table_structure_dict_ch.txt
+--use_gpu:True|False
+--det_model_dir:
+--rec_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
\ No newline at end of file

test_tipc/configs/slanet/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:slanet
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:./pretrain_models/en_ppstructure_mobile_v2.0_SLANet_train/best_accuracy
+train_model_name:latest
+train_infer_img_dir:./ppstructure/docs/table/table.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/slanet/SLANet.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/slanet/SLANet.yml -o
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/en_ppstructure_mobile_v2.0_SLANet_train
+infer_export:null
+infer_quant:False
+inference:ppstructure/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  --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,488,488]}]

test_tipc/prepare.sh

@@ -700,10 +700,18 @@ if [ ${MODE} = "cpp_infer" ];then
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar  --no-check-certificate
         cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar && tar xf ch_det_data_50.tar && cd ../
     elif [[ ${model_name} =~ "en_table_structure" ]];then
-        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar --no-check-certificate
         wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
         wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
-        cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
+
+        cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar
+        if [ ${model_name} == "en_table_structure" ]; then
+            wget -nc https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar --no-check-certificate
+            tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
+        elif [ ${model_name} == "en_table_structure_PACT" ]; then
+            wget -nc https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_slim_infer.tar --no-check-certificate
+            tar xf en_ppocr_mobile_v2.0_table_structure_slim_infer.tar
+        fi
+        cd ../
     elif [[ ${model_name} =~ "slanet" ]];then
         wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar --no-check-certificate
         wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar --no-check-certificate
@@ -791,6 +799,12 @@ if [ ${MODE} = "paddle2onnx_infer" ];then
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar --no-check-certificate
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar --no-check-certificate
         cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar && cd ../
+    elif [[ ${model_name} =~ "slanet" ]];then
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar --no-check-certificate
+        cd ./inference/ && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar && cd ../
+    elif [[ ${model_name} =~ "en_table_structure" ]];then
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar --no-check-certificate
+        cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar && cd ../
     fi
     
     # wget data

test_tipc/test_paddle2onnx.sh

@@ -105,6 +105,19 @@ function func_paddle2onnx(){
         eval $trans_model_cmd
         last_status=${PIPESTATUS[0]}
         status_check $last_status "${trans_model_cmd}" "${status_log}" "${model_name}" "${trans_rec_log}"
+    elif [ ${model_name} = "slanet" ] || [ ${model_name} = "en_table_structure" ]; then
+        # trans det
+        set_dirname=$(func_set_params "--model_dir" "${det_infer_model_dir_value}")
+        set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}")
+        set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}")
+        set_save_model=$(func_set_params "--save_file" "${det_save_file_value}")
+        set_opset_version=$(func_set_params "${opset_version_key}" "${opset_version_value}")
+        set_enable_onnx_checker=$(func_set_params "${enable_onnx_checker_key}" "${enable_onnx_checker_value}")
+        trans_det_log="${LOG_PATH}/trans_model_det.log"
+        trans_model_cmd="${padlle2onnx_cmd} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_save_model} ${set_opset_version} ${set_enable_onnx_checker} --enable_dev_version=True > ${trans_det_log} 2>&1 "
+        eval $trans_model_cmd
+        last_status=${PIPESTATUS[0]}
+        status_check $last_status "${trans_model_cmd}" "${status_log}" "${model_name}" "${trans_det_log}" 
     fi
 
     # python inference
@@ -117,7 +130,7 @@ function func_paddle2onnx(){
                 set_det_model_dir=$(func_set_params "${det_model_key}" "${det_save_file_value}")
                 set_rec_model_dir=$(func_set_params "${rec_model_key}" "${rec_save_file_value}")
                 infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_det_model_dir} ${set_rec_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
-            elif [[ ${model_name} =~ "det" ]]; then
+            elif [[ ${model_name} =~ "det" ]] || [ ${model_name} = "slanet" ] || [ ${model_name} = "en_table_structure" ]; then
                 set_det_model_dir=$(func_set_params "${det_model_key}" "${det_save_file_value}")
                 infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_det_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
             elif [[ ${model_name} =~ "rec" ]]; then
@@ -136,7 +149,7 @@ function func_paddle2onnx(){
                 set_det_model_dir=$(func_set_params "${det_model_key}" "${det_save_file_value}")
                 set_rec_model_dir=$(func_set_params "${rec_model_key}" "${rec_save_file_value}")
                 infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_det_model_dir} ${set_rec_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
-            elif [[ ${model_name} =~ "det" ]]; then
+            elif [[ ${model_name} =~ "det" ]]|| [ ${model_name} = "slanet" ] || [ ${model_name} = "en_table_structure" ]; then
                 set_det_model_dir=$(func_set_params "${det_model_key}" "${det_save_file_value}")
                 infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_det_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
             elif [[ ${model_name} =~ "rec" ]]; then

tools/infer/predict_det.py

@@ -282,44 +282,67 @@ if __name__ == "__main__":
     args = utility.parse_args()
     image_file_list = get_image_file_list(args.image_dir)
     text_detector = TextDetector(args)
-    count = 0
     total_time = 0
-    draw_img_save = "./inference_results"
+    draw_img_save_dir = args.draw_img_save_dir
+    os.makedirs(draw_img_save_dir, exist_ok=True)
 
     if args.warmup:
         img = np.random.uniform(0, 255, [640, 640, 3]).astype(np.uint8)
         for i in range(2):
             res = text_detector(img)
 
-    if not os.path.exists(draw_img_save):
-        os.makedirs(draw_img_save)
     save_results = []
-    for image_file in image_file_list:
-        img, flag, _ = check_and_read(image_file)
-        if not flag:
+    for idx, image_file in enumerate(image_file_list):
+        img, flag_gif, flag_pdf = check_and_read(image_file)
+        if not flag_gif and not flag_pdf:
             img = cv2.imread(image_file)
-        if img is None:
-            logger.info("error in loading image:{}".format(image_file))
-            continue
-        st = time.time()
-        dt_boxes, _ = text_detector(img)
-        elapse = time.time() - st
-        if count > 0:
+        if not flag_pdf:
+            if img is None:
+                logger.debug("error in loading image:{}".format(image_file))
+                continue
+            imgs = [img]
+        else:
+            page_num = args.page_num
+            if page_num > len(img) or page_num == 0:
+                page_num = len(img)
+            imgs = img[:page_num]
+        for index, img in enumerate(imgs):
+            st = time.time()
+            dt_boxes, _ = text_detector(img)
+            elapse = time.time() - st
             total_time += elapse
-        count += 1
-        save_pred = os.path.basename(image_file) + "\t" + str(
-            json.dumps([x.tolist() for x in dt_boxes])) + "\n"
-        save_results.append(save_pred)
-        logger.info(save_pred)
-        logger.info("The predict time of {}: {}".format(image_file, elapse))
-        src_im = utility.draw_text_det_res(dt_boxes, image_file)
-        img_name_pure = os.path.split(image_file)[-1]
-        img_path = os.path.join(draw_img_save,
-                                "det_res_{}".format(img_name_pure))
-        cv2.imwrite(img_path, src_im)
-        logger.info("The visualized image saved in {}".format(img_path))
+            if len(imgs) > 1:
+                save_pred = os.path.basename(image_file) + '_' + str(
+                    index) + "\t" + str(
+                        json.dumps([x.tolist() for x in dt_boxes])) + "\n"
+            else:
+                save_pred = os.path.basename(image_file) + "\t" + str(
+                    json.dumps([x.tolist() for x in dt_boxes])) + "\n"
+            save_results.append(save_pred)
+            logger.info(save_pred)
+            if len(imgs) > 1:
+                logger.info("{}_{} The predict time of {}: {}".format(
+                    idx, index, image_file, elapse))
+            else:
+                logger.info("{} The predict time of {}: {}".format(
+                    idx, image_file, elapse))
+
+            src_im = utility.draw_text_det_res(dt_boxes, img)
+
+            if flag_gif:
+                save_file = image_file[:-3] + "png"
+            elif flag_pdf:
+                save_file = image_file.replace('.pdf',
+                                               '_' + str(index) + '.png')
+            else:
+                save_file = image_file
+            img_path = os.path.join(
+                draw_img_save_dir,
+                "det_res_{}".format(os.path.basename(save_file)))
+            cv2.imwrite(img_path, src_im)
+            logger.info("The visualized image saved in {}".format(img_path))
 
-    with open(os.path.join(draw_img_save, "det_results.txt"), 'w') as f:
+    with open(os.path.join(draw_img_save_dir, "det_results.txt"), 'w') as f:
         f.writelines(save_results)
         f.close()
     if args.benchmark:

tools/infer/predict_system.py

@@ -159,50 +159,75 @@ def main(args):
     count = 0
     for idx, image_file in enumerate(image_file_list):
 
-        img, flag, _ = check_and_read(image_file)
-        if not flag:
+        img, flag_gif, flag_pdf = check_and_read(image_file)
+        if not flag_gif and not flag_pdf:
             img = cv2.imread(image_file)
-        if img is None:
-            logger.debug("error in loading image:{}".format(image_file))
-            continue
-        starttime = time.time()
-        dt_boxes, rec_res, time_dict = text_sys(img)
-        elapse = time.time() - starttime
-        total_time += elapse
-
-        logger.debug(
-            str(idx) + "  Predict time of %s: %.3fs" % (image_file, elapse))
-        for text, score in rec_res:
-            logger.debug("{}, {:.3f}".format(text, score))
-
-        res = [{
-            "transcription": rec_res[idx][0],
-            "points": np.array(dt_boxes[idx]).astype(np.int32).tolist(),
-        } for idx in range(len(dt_boxes))]
-        save_pred = os.path.basename(image_file) + "\t" + json.dumps(
-            res, ensure_ascii=False) + "\n"
-        save_results.append(save_pred)
-
-        if is_visualize:
-            image = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
-            boxes = dt_boxes
-            txts = [rec_res[i][0] for i in range(len(rec_res))]
-            scores = [rec_res[i][1] for i in range(len(rec_res))]
-
-            draw_img = draw_ocr_box_txt(
-                image,
-                boxes,
-                txts,
-                scores,
-                drop_score=drop_score,
-                font_path=font_path)
-            if flag:
-                image_file = image_file[:-3] + "png"
-            cv2.imwrite(
-                os.path.join(draw_img_save_dir, os.path.basename(image_file)),
-                draw_img[:, :, ::-1])
-            logger.debug("The visualized image saved in {}".format(
-                os.path.join(draw_img_save_dir, os.path.basename(image_file))))
+        if not flag_pdf:
+            if img is None:
+                logger.debug("error in loading image:{}".format(image_file))
+                continue
+            imgs = [img]
+        else:
+            page_num = args.page_num
+            if page_num > len(img) or page_num == 0:
+                page_num = len(img)
+            imgs = img[:page_num]
+        for index, img in enumerate(imgs):
+            starttime = time.time()
+            dt_boxes, rec_res, time_dict = text_sys(img)
+            elapse = time.time() - starttime
+            total_time += elapse
+            if len(imgs) > 1:
+                logger.debug(
+                    str(idx) + '_' + str(index) + "  Predict time of %s: %.3fs"
+                    % (image_file, elapse))
+            else:
+                logger.debug(
+                    str(idx) + "  Predict time of %s: %.3fs" % (image_file,
+                                                                elapse))
+            for text, score in rec_res:
+                logger.debug("{}, {:.3f}".format(text, score))
+
+            res = [{
+                "transcription": rec_res[i][0],
+                "points": np.array(dt_boxes[i]).astype(np.int32).tolist(),
+            } for i in range(len(dt_boxes))]
+            if len(imgs) > 1:
+                save_pred = os.path.basename(image_file) + '_' + str(
+                    index) + "\t" + json.dumps(
+                        res, ensure_ascii=False) + "\n"
+            else:
+                save_pred = os.path.basename(image_file) + "\t" + json.dumps(
+                    res, ensure_ascii=False) + "\n"
+            save_results.append(save_pred)
+
+            if is_visualize:
+                image = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
+                boxes = dt_boxes
+                txts = [rec_res[i][0] for i in range(len(rec_res))]
+                scores = [rec_res[i][1] for i in range(len(rec_res))]
+
+                draw_img = draw_ocr_box_txt(
+                    image,
+                    boxes,
+                    txts,
+                    scores,
+                    drop_score=drop_score,
+                    font_path=font_path)
+                if flag_gif:
+                    save_file = image_file[:-3] + "png"
+                elif flag_pdf:
+                    save_file = image_file.replace('.pdf',
+                                                   '_' + str(index) + '.png')
+                else:
+                    save_file = image_file
+                cv2.imwrite(
+                    os.path.join(draw_img_save_dir,
+                                 os.path.basename(save_file)),
+                    draw_img[:, :, ::-1])
+                logger.debug("The visualized image saved in {}".format(
+                    os.path.join(draw_img_save_dir, os.path.basename(
+                        save_file))))
 
     logger.info("The predict total time is {}".format(time.time() - _st))
     if args.benchmark:

tools/infer/utility.py

@@ -45,6 +45,7 @@ def init_args():
 
     # params for text detector
     parser.add_argument("--image_dir", type=str)
+    parser.add_argument("--page_num", type=int, default=0)
     parser.add_argument("--det_algorithm", type=str, default='DB')
     parser.add_argument("--det_model_dir", type=str)
     parser.add_argument("--det_limit_side_len", type=float, default=960)
@@ -337,12 +338,11 @@ def draw_e2e_res(dt_boxes, strs, img_path):
     return src_im
 
 
-def draw_text_det_res(dt_boxes, img_path):
-    src_im = cv2.imread(img_path)
+def draw_text_det_res(dt_boxes, img):
     for box in dt_boxes:
         box = np.array(box).astype(np.int32).reshape(-1, 2)
-        cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
-    return src_im
+        cv2.polylines(img, [box], True, color=(255, 255, 0), thickness=2)
+    return img
 
 
 def resize_img(img, input_size=600):