Merge branch 'develop' into devddd

PPOCRLabel/Makefile

+# ex: set ts=8 noet:
+
+all: qt5 test
+
+test: testpy3
+
+testpy2:
+	python -m unittest discover tests
+
+testpy3:
+	python3 -m unittest discover tests
+
+qt4: qt4py2
+
+qt5: qt5py3
+
+qt4py2:
+	pyrcc4 -py2 -o libs/resources.py resources.qrc
+
+qt4py3:
+	pyrcc4 -py3 -o libs/resources.py resources.qrc
+
+qt5py3:
+	pyrcc5 -o libs/resources.py resources.qrc
+
+clean:
+	rm -rf ~/.labelImgSettings.pkl *.pyc dist labelImg.egg-info __pycache__ build
+
+pip_upload:
+	python3 setup.py upload
+
+long_description:
+	restview --long-description
+
+.PHONY: all

PPOCRLabel/README.md

@@ -24,11 +24,9 @@ python PPOCRLabel.py
 #### Ubuntu Linux
 
 ```
-sudo apt-get install pyqt5-dev-tools
-sudo apt-get install trash-cli
+pip3 install pyqt5
+pip3 install trash-cli
 cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
-sudo pip3 install -r requirements/requirements-linux-python3.txt
-make qt5py3
 python3 PPOCRLabel.py
 ```
 
@@ -38,7 +36,6 @@ pip3 install pyqt5
 pip3 uninstall opencv-python # 由于mac版本的opencv与pyqt有冲突，需先手动卸载opencv
 pip3 install opencv-contrib-python-headless # 安装headless版本的open-cv
 cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
-make qt5py3
 python3 PPOCRLabel.py
 ```
 
@@ -75,6 +72,20 @@ python3 PPOCRLabel.py
 |  rec_gt.txt   | 识别标签。可直接用于PPOCR识别模型训练。需用户手动点击菜单栏“PaddleOCR” - "保存识别结果"后产生。 |
 |   crop_img    |   识别数据。按照检测框切割后的图片。与rec_gt.txt同时产生。   |
 
+## 说明
+### 内置模型
+ - 默认模型：PPOCRLabel默认使用PaddleOCR中的中英文超轻量OCR模型，支持中英文与数字识别，多种语言检测。
+ - 模型语言切换：用户可通过菜单栏中 "PaddleOCR" - "选择模型" 切换内置模型语言，目前支持的语言包括法文、德文、韩文、日文。具体模型下载链接可参考[PaddleOCR模型列表](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/models_list.md).
+ - 自定义模型：用户可根据[自定义模型代码使用](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/whl.md#%E8%87%AA%E5%AE%9A%E4%B9%89%E6%A8%A1%E5%9E%8B)，通过修改PPOCRLabel.py中针对[PaddleOCR类的实例化](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/PPOCRLabel/PPOCRLabel.py#L110)替换成自己训练的模型
+
+### 错误提示
+- 如果同时使用whl包安装了paddleocr，其优先级大于通过paddleocr.py调用PaddleOCR类，whl包未更新时会导致程序异常。
+- PPOCRLabel**不支持对中文文件名**的图片进行自动标注。
+- 如果您在打开软件过程中出现**objc[XXXXX]**开头的错误，证明您的opencv版本太高，建议安装4.2版本：
+```
+pip install opencv-python==4.2.0.32
+```
+
 ### 参考资料
 
 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)

PPOCRLabel/README_en.md

@@ -26,11 +26,9 @@ python PPOCRLabel.py --lang en
 #### Ubuntu Linux
 
 ```
-sudo apt-get install pyqt5-dev-tools
-sudo apt-get install trash-cli
+pip3 install pyqt5
+pip3 install trash-cli
 cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
-sudo pip3 install -r requirements/requirements-linux-python3.txt
-make qt5py3
 python3 PPOCRLabel.py --lang en
 ```
 
@@ -40,7 +38,6 @@ pip3 install pyqt5
 pip3 uninstall opencv-python # Uninstall opencv manually as it conflicts with pyqt
 pip3 install opencv-contrib-python-headless # Install the headless version of opencv
 cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
-make qt5py3
 python3 PPOCRLabel.py --lang en
 ```
 
@@ -92,6 +89,14 @@ Therefore, if the recognition result has been manually changed before, it may ch
 |  rec_gt.txt   | The recognition label file, which can be directly used for PPOCR identification model training, is generated after the user clicks on the menu bar "PaddleOCR"-"Save recognition result". |
 |   crop_img    | The recognition data, generated at the same time with *rec_gt.txt* |
 
+
+### Built-in Model
+- Default model: PPOCRLabel uses the Chinese and English ultra-lightweight OCR model in PaddleOCR by default, supports Chinese, English and number recognition, and multiple language detection.
+- Model language switching: Changing the built-in model language is supportable by clicking "PaddleOCR"-"Choose OCR Model" in the menu bar. Currently supported languages​include French, German, Korean, and Japanese. 
+For specific model download links, please refer to [PaddleOCR Model List](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/models_list_en.md#multilingual-recognition-modelupdating)
+- Custom model: The model trained by users can be replaced by modifying PPOCRLabel.py in [PaddleOCR class instantiation](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/PPOCRLabel/PPOCRLabel.py#L110) referring [Custom Model Code](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/whl_en.md#use-custom-model)
+
+
 ## Related
 
 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)

PPOCRLabel/build-tools/.gitignore

-*.spec
-build
-dist
-pyinstaller
-python-2.*
-pywin32*
-virtual-wine
-venv_wine
-PyQt4-*
-lxml-*
-windows_v*
-linux_v*

PPOCRLabel/build-tools/README.md

-### Deploy to PyPI
-
-```
-cd [ROOT]
-sh build-tools/build-for-pypi.sh
-```
-
-### Build for Ubuntu
-
-```
-cd build-tools
-sh run-in-container.sh
-sh envsetup.sh
-sh build-ubuntu-binary.sh
-```
-
-### Build for Windows
-
-```
-cd build-tools
-sh run-in-container.sh
-sh envsetup.sh
-sh build-windows-binary.sh
-```
-
-### Build for macOS High Sierra
-```
-cd build-tools
-./build-for-macos.sh
-```
-
-Note: If there are some problems, try to
-```
-sudo rm -rf virtual-wne venv_wine
-```

PPOCRLabel/build-tools/build-for-macos.sh

-#!/bin/sh
-
-brew install python@2
-pip install --upgrade virtualenv
-
-# clone labelimg source
-rm -rf /tmp/labelImgSetup
-mkdir /tmp/labelImgSetup
-cd /tmp/labelImgSetup
-curl https://codeload.github.com/tzutalin/labelImg/zip/master --output labelImg.zip
-unzip labelImg.zip
-rm labelImg.zip
-
-# setup python3 space
-virtualenv --system-site-packages  -p python3 /tmp/labelImgSetup/labelImg-py3
-source /tmp/labelImgSetup/labelImg-py3/bin/activate
-cd labelImg-master
-
-# build labelImg app
-pip install py2app
-pip install PyQt5 lxml
-make qt5py3
-rm -rf build dist
-python setup.py py2app -A
-mv "/tmp/labelImgSetup/labelImg-master/dist/labelImg.app" /Applications
-# deactivate python3
-deactivate
-cd ../
-rm -rf /tmp/labelImgSetup
-echo 'DONE'

PPOCRLabel/build-tools/build-for-pypi.sh

-#!/bin/sh
-# Packaging and Release
-docker run --workdir=$(pwd)/ --volume="/home/$USER:/home/$USER" tzutalin/py2qt4 /bin/sh -c 'make qt4py2; make test;sudo python setup.py sdist;sudo python setup.py install'
-
-while true; do
-    read -p "Do you wish to deploy this to PyPI(twine upload dist/* or pip install dist/*)?" yn
-    case $yn in
-        [Yy]* ) docker run -it --rm --workdir=$(pwd)/ --volume="/home/$USER:/home/$USER" tzutalin/py2qt4; break;;
-        [Nn]* ) exit;;
-        * ) echo "Please answer yes or no.";;
-    esac
-done
-# python setup.py register
-# python setup.py sdist upload
-# Net pypi: twine upload dist/*
-
-# Test before upladoing: pip install dist/labelImg.tar.gz

PPOCRLabel/build-tools/build-ubuntu-binary.sh

-#!/bin/bash
-### Ubuntu use pyinstall v3.0
-THIS_SCRIPT_PATH=`readlink -f $0`
-THIS_SCRIPT_DIR=`dirname ${THIS_SCRIPT_PATH}`
-cd pyinstaller
-git checkout v3.2
-cd ${THIS_SCRIPT_DIR}
-
-rm -r build
-rm -r dist
-rm labelImg.spec
-python pyinstaller/pyinstaller.py --hidden-import=xml \
-            --hidden-import=xml.etree \
-            --hidden-import=xml.etree.ElementTree \
-            --hidden-import=lxml.etree \
-             -D -F -n labelImg -c "../labelImg.py" -p ../libs -p ../
-
-FOLDER=$(git describe --abbrev=0 --tags)
-FOLDER="linux_"$FOLDER
-rm -rf "$FOLDER"
-mkdir "$FOLDER"
-cp dist/labelImg $FOLDER
-cp -rf ../data $FOLDER/data
-zip "$FOLDER.zip" -r $FOLDER

PPOCRLabel/build-tools/build-windows-binary.sh

-#!/bin/bash
-### Window requires pyinstall v2.1
-wine msiexec -i python-2.7.8.msi
-wine pywin32-218.win32-py2.7.exe
-wine PyQt4-4.11.4-gpl-Py2.7-Qt4.8.7-x32.exe
-wine lxml-3.7.3.win32-py2.7.exe
-
-THIS_SCRIPT_PATH=`readlink -f $0`
-THIS_SCRIPT_DIR=`dirname ${THIS_SCRIPT_PATH}`
-cd pyinstaller
-git checkout v2.1
-cd ${THIS_SCRIPT_DIR}
-echo ${THIS_SCRIPT_DIR}
-
-#. venv_wine/bin/activate
-rm -r build
-rm -r dist
-rm labelImg.spec
-
-wine c:/Python27/python.exe pyinstaller/pyinstaller.py --hidden-import=xml \
-            --hidden-import=xml.etree \
-            --hidden-import=xml.etree.ElementTree \
-            --hidden-import=lxml.etree \
-             -D -F -n labelImg -c "../labelImg.py" -p ../libs -p ../
-
-FOLDER=$(git describe --abbrev=0 --tags)
-FOLDER="windows_"$FOLDER
-rm -rf "$FOLDER"
-mkdir "$FOLDER"
-cp dist/labelImg.exe $FOLDER
-cp -rf ../data $FOLDER/data
-zip "$FOLDER.zip" -r $FOLDER

PPOCRLabel/build-tools/envsetup.sh

-#!/bin/sh
-
-THIS_SCRIPT_PATH=`readlink -f $0`
-THIS_SCRIPT_DIR=`dirname ${THIS_SCRIPT_PATH}`
-#OS Ubuntu 14.04
-### Common packages for linux/windows
-if [ ! -e "pyinstaller" ]; then
-    git clone https://github.com/pyinstaller/pyinstaller
-    cd pyinstaller
-    git checkout v2.1 -b v2.1
-    cd ${THIS_SCRIPT_DIR}
-fi
-
-echo "Going to clone and download packages for building windows"
-#Pacakges
-#>  pyinstaller (2.1)
-#>  wine (1.6.2)
-#>  virtual-wine (0.1)
-#>  python-2.7.8.msi
-#>  pywin32-218.win32-py2.7.exe
-
-## tool to install on Ubuntu
-#$ sudo apt-get install wine
-
-### Clone a repo to create virtual wine env
-if [ ! -e "virtual-wine" ]; then
-	git clone https://github.com/htgoebel/virtual-wine.git
-fi
-
-apt-get install scons
-### Create virtual env
-rm -rf venv_wine
-./virtual-wine/vwine-setup venv_wine
-#### Active virutal env
-. venv_wine/bin/activate
-
-### Use wine to install packages to virtual env
-if [ ! -e "python-2.7.8.msi" ]; then
-    wget "https://www.python.org/ftp/python/2.7.8/python-2.7.8.msi"
-fi
-
-if [ ! -e "pywin32-218.win32-py2.7.exe" ]; then
-    wget "http://nchc.dl.sourceforge.net/project/pywin32/pywin32/Build%20218/pywin32-218.win32-py2.7.exe"
-fi
-
-if [ ! -e "PyQt4-4.11.4-gpl-Py2.7-Qt4.8.7-x32.exe" ]; then
-    wget "http://nchc.dl.sourceforge.net/project/pyqt/PyQt4/PyQt-4.11.4/PyQt4-4.11.4-gpl-Py2.7-Qt4.8.7-x32.exe"
-fi
-
-if [ ! -e "lxml-3.7.3.win32-py2.7.exe" ]; then
-    wget "https://pypi.python.org/packages/a3/f6/a28c5cf63873f6c55a3eb7857b736379229b85ba918261d2e88cf886905e/lxml-3.7.3.win32-py2.7.exe#md5=a0f746355876aca4ca5371cb0f1d13ce"
-fi
-

PPOCRLabel/build-tools/run-in-container.sh

-#!/bin/sh
-docker run -it \
-    --user $(id -u) \
-    -e DISPLAY=unix$DISPLAY \
-    --workdir=$(pwd) \
-    --volume="/home/$USER:/home/$USER" \
-    --volume="/etc/group:/etc/group:ro" \
-    --volume="/etc/passwd:/etc/passwd:ro" \
-    --volume="/etc/shadow:/etc/shadow:ro" \
-    --volume="/etc/sudoers.d:/etc/sudoers.d:ro" \
-    -v /tmp/.X11-unix:/tmp/.X11-unix \
-    tzutalin/py2qt4
-

doc/doc_ch/whl.md

@@ -4,6 +4,8 @@
 
 ### 安装whl包
 
+首先需要参照[安装文档](installation.md)安装paddlepaddle，然后开始安装paddleocr package
+
 pip安装
 ```bash
 pip install paddleocr
@@ -166,7 +168,7 @@ paddleocr -h
 
 * 检测+分类+识别全流程
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --use_angle_cls true --cls true
+paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --use_angle_cls true
 ```
 结果是一个list，每个item包含了文本框，文字和识别置信度
 ```bash
@@ -190,7 +192,7 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg
 
 * 分类+识别
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --use_angle_cls true --cls true --det false
+paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --use_angle_cls true --det false
 ```
 
 结果是一个list，每个item只包含识别结果和识别置信度
@@ -222,7 +224,7 @@ paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --det false
 
 * 单独执行分类
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --use_angle_cls true --cls true --det false --rec false
+paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --use_angle_cls true --det false --rec false
 ```
 
 结果是一个list，每个item只包含分类结果和分类置信度
@@ -258,7 +260,7 @@ im_show.save('result.jpg')
 ### 通过命令行使用
 
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_dir} --rec_model_dir {your_rec_model_dir} --rec_char_dict_path {your_rec_char_dict_path} --cls_model_dir {your_cls_model_dir} --use_angle_cls true --cls true
+paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_dir} --rec_model_dir {your_rec_model_dir} --rec_char_dict_path {your_rec_char_dict_path} --cls_model_dir {your_cls_model_dir} --use_angle_cls true
 ```
 
 ## 参数说明
@@ -295,4 +297,4 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_
 | lang                     | 模型语言类型,目前支持 中文(ch)和英文(en)                                                                                                                                                                                                  | ch                    |
 | det                     | 前向时使用启动检测                                                                                                                                                                                                   | TRUE                    |
 | rec                     | 前向时是否启动识别                                                                                                                                                                                                   | TRUE                    |
-| cls                     | 前向时是否启动分类                                                                                                                                                                                                 | FALSE                    |
+| cls                     | 前向时是否启动分类,  此参数仅存在于`代码使用`模式                                                                                                                                                                                      | FALSE                    |

doc/doc_en/whl_en.md

@@ -2,6 +2,9 @@
 
 ## Get started quickly
 ### install package
+
+First, you need to refer to [installation document](installation_en.md) to install paddlepaddle, and then start to install paddleocr package
+
 install by pypi
 ```bash
 pip install paddleocr
@@ -172,7 +175,7 @@ paddleocr -h
 
 * detection classification and recognition
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --use_angle_cls true -cls true --lang en
+paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --use_angle_cls true --lang en
 ```
 
 Output will be a list, each item contains bounding box, text and recognition confidence
@@ -198,7 +201,7 @@ Output will be a list, each item contains bounding box, text and recognition con
 
 * classification and recognition
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true -cls true --det false --lang en
+paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true --det false --lang en
 ```
 
 Output will be a list, each item contains text and recognition confidence
@@ -221,7 +224,7 @@ Output will be a list, each item only contains bounding box
 
 * only recognition
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --det false --cls false --lang en
+paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --det false --lang en
 ```
 
 Output will be a list, each item contains text and recognition confidence
@@ -231,7 +234,7 @@ Output will be a list, each item contains text and recognition confidence
 
 * only classification
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true -cls true --det false --rec false
+paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true --det false --rec false
 ```
 
 Output will be a list, each item contains classification result and confidence
@@ -268,7 +271,7 @@ im_show.save('result.jpg')
 ### Use by command line
 
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_dir} --rec_model_dir {your_rec_model_dir} --rec_char_dict_path {your_rec_char_dict_path} --cls_model_dir {your_cls_model_dir} --use_angle_cls true --cls true
+paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_dir} --rec_model_dir {your_rec_model_dir} --rec_char_dict_path {your_rec_char_dict_path} --cls_model_dir {your_cls_model_dir} --use_angle_cls true
 ```
 
 ## Parameter Description
@@ -305,4 +308,4 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_
 | lang                     | The support language, now only Chinese(ch)、English(en)、French(french)、German(german)、Korean(korean)、Japanese(japan) are supported                                                                                                                                                                                                  | ch                    |
 | det                     | Enable detction when `ppocr.ocr` func exec                                                                                                                                                                                                   | TRUE                    |
 | rec                     | Enable recognition when `ppocr.ocr` func exec                                                                                                                                                                                                   | TRUE                    |
-| cls                     | Enable classification when `ppocr.ocr` func exec                                                                                                                                                                                                   | FALSE                    |
+| cls                     | Enable classification when `ppocr.ocr` func exec，this parameter only exists in `code usage` mode                                                                                                                                                                                                   | FALSE                    |

paddleocr.py

@@ -117,14 +117,16 @@ def maybe_download(model_storage_directory, url):
         os.remove(tmp_path)
 
 
-def parse_args(mMain=True):
+
+def parse_args(mMain=True,add_help=True):
+
     import argparse
 
     def str2bool(v):
         return v.lower() in ("true", "t", "1")
 
     if mMain:
-        parser = argparse.ArgumentParser()
+        parser = argparse.ArgumentParser(add_help=add_help)
         # params for prediction engine
         parser.add_argument("--use_gpu", type=str2bool, default=True)
         parser.add_argument("--ir_optim", type=str2bool, default=True)
@@ -211,6 +213,7 @@ def parse_args(mMain=True):
                                     )
 
 
+
 class PaddleOCR(predict_system.TextSystem):
     def __init__(self, **kwargs):
         """
@@ -218,7 +221,7 @@ class PaddleOCR(predict_system.TextSystem):
         args:
             **kwargs: other params show in paddleocr --help
         """
-        postprocess_params = parse_args(mMain=False)
+        postprocess_params = parse_args(mMain=False, add_help=False)
         postprocess_params.__dict__.update(**kwargs)
         self.use_angle_cls = postprocess_params.use_angle_cls
         lang = postprocess_params.lang

ppocr/modeling/architectures/rec_model.py

@@ -160,6 +160,7 @@ class RecModel(object):
                         "We set img_shape to be the same , it may affect the inference effect"
                     )
                     image_shape = deepcopy(self.image_shape)
+                    image_shape.insert(0, -1)
             image = fluid.data(name='image', shape=image_shape, dtype='float32')
             image.stop_gradient = False
             if self.loss_type == "srn":

requirements.txt

@@ -4,4 +4,4 @@ pyclipper
 lmdb
 tqdm
 numpy
-opencv-python
+opencv-python==4.2.0.32

setup.py

@@ -32,7 +32,7 @@ setup(
     package_dir={'paddleocr': ''},
     include_package_data=True,
     entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
-    version='1.1.1',
+    version='1.1.2',
     install_requires=requirements,
     license='Apache License 2.0',
     description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',

tools/export_model.py

@@ -15,6 +15,7 @@
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
+from ppocr.utils.utility import enable_static_mode
 
 import os
 import sys
@@ -43,7 +44,6 @@ logger = initial_logger()
 from ppocr.utils.save_load import init_model
 
 
-
 def main():
     startup_prog, eval_program, place, config, _ = program.preprocess()
 
@@ -72,4 +72,5 @@ def main():
 
 
 if __name__ == '__main__':
+    enable_static_mode()
     main()

tools/infer/predict_det.py

@@ -191,10 +191,13 @@ if __name__ == "__main__":
         if count > 0:
             total_time += elapse
         count += 1
-        print("Predict time of %s:" % image_file, elapse)
+        logger.info("The predicted time of img: {} is  {}:".format(image_file,
+                                                                   elapse))
         src_im = utility.draw_text_det_res(dt_boxes, image_file)
-        img_name_pure = os.path.split(image_file)[-1]  # image_file.split("/")[-1]
-        img_path = os.path.join(draw_img_save, "det_res_%s" % img_name_pure)
-        cv2.imwrite(img_path, src_im)
+        img_name_pure = image_file.split("/")[-1]
+        cv2.imwrite(
+            os.path.join(draw_img_save, "det_res_%s" % img_name_pure), src_im)
+        logger.info("The visualized img saved in {}".format(
+            os.path.join(draw_img_save, "det_res_%s" % img_name_pure)))
     if count > 1:
-        print("Avg Time:", total_time / (count - 1))
+        logger.info("Avg Time:", total_time / (count - 1))