mirrors
/
PaddleOCR
mirror of https://github.com/PaddlePaddle/PaddleOCR.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

修改完成:划分det与rec数据集脚本，以及对应的中英文文档指令及其数据集存放树状结构。已提交过release2.4分支

pull/5442/head
Alchemist_W 2022-02-10 22:40:19 +08:00
parent efc0908277
commit f58d8d0372
3 changed files with 53 additions and 29 deletions

26
PPOCRLabel/README.md
View File

@ -198,21 +198,31 @@ For some data that are difficult to recognize, the recognition results will not
- Enter the following command in the terminal to execute the dataset division script: - Enter the following command in the terminal to execute the dataset division script:
``` ```
cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
python gen_ocr_train_val_test.py --trainValTestRatio 6:2:2 --labelRootPath ../train_data/label --detRootPath ../train_data/det --recRootPath ../train_data/rec python gen_ocr_train_val_test.py --trainValTestRatio 6:2:2 --datasetRootPath ../train_data
``` ```
Parameter Description: Parameter Description:
- `trainValTestRatio` is the division ratio of the number of images in the training set, validation set, and test set, set according to your actual situation, the default is `6:2:2` - `trainValTestRatio` is the division ratio of the number of images in the training set, validation set, and test set, set according to your actual situation, the default is `6:2:2`
- `labelRootPath` is the storage path of the dataset labeled by PPOCRLabel, the default is `../train_data/label` - `datasetRootPath` is the storage path of the complete dataset labeled by PPOCRLabel. The default path is `PaddleOCR/train_data` .
```
- `detRootPath` is the path where the text detection dataset is divided according to the dataset marked by PPOCRLabel. The default is `../train_data/det` |-train_data
|-crop_img
- `recRootPath` is the path where the character recognition dataset is divided according to the dataset marked by PPOCRLabel. The default is `../train_data/rec` |- word_001_crop_0.png
|- word_002_crop_0.jpg
|- word_003_crop_0.jpg
| ...
| Label.txt
| rec_gt.txt
|- word_001.png
|- word_002.jpg
|- word_003.jpg
| ...
```
### 3.6 Error message ### 3.6 Error message
- If paddleocr is installed with whl, it has a higher priority than calling PaddleOCR class with paddleocr.py, which may cause an exception if whl package is not updated. - If paddleocr is installed with whl, it has a higher priority than calling PaddleOCR class with paddleocr.py, which may cause an exception if whl package is not updated.

24
PPOCRLabel/README_ch.md
View File

@ -185,19 +185,29 @@ PPOCRLabel支持三种导出方式：
``` ```
cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下 cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
python gen_ocr_train_val_test.py --trainValTestRatio 6:2:2 --labelRootPath ../train_data/label --detRootPath ../train_data/det --recRootPath ../train_data/rec python gen_ocr_train_val_test.py --trainValTestRatio 6:2:2 --datasetRootPath ../train_data
``` ```
参数说明： 参数说明：
- `trainValTestRatio` 是训练集、验证集、测试集的图像数量划分比例，根据实际情况设定，默认是`6:2:2` - `trainValTestRatio` 是训练集、验证集、测试集的图像数量划分比例，根据实际情况设定，默认是`6:2:2`
- `labelRootPath` 是PPOCRLabel标注的数据集存放路径，默认是`../train_data/label` - `datasetRootPath` 是PPOCRLabel标注的完整数据集存放路径。默认路径是 `PaddleOCR/train_data` 分割数据集前应有如下结构：
```
- `detRootPath` 是根据PPOCRLabel标注的数据集划分后的文本检测数据集存放的路径，默认是`../train_data/det ` |-train_data
|-crop_img
- `recRootPath` 是根据PPOCRLabel标注的数据集划分后的字符识别数据集存放的路径，默认是`../train_data/rec` |- word_001_crop_0.png
|- word_002_crop_0.jpg
|- word_003_crop_0.jpg
| ...
| Label.txt
| rec_gt.txt
|- word_001.png
|- word_002.jpg
|- word_003.jpg
| ...
```
### 3.6 错误提示 ### 3.6 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。 - 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。

32
PPOCRLabel/gen_ocr_train_val_test.py
View File

@ -17,15 +17,14 @@ def isCreateOrDeleteFolder(path, flag):
return flagAbsPath return flagAbsPath
def splitTrainVal(root, dir, absTrainRootPath, absValRootPath, absTestRootPath, trainTxt, valTxt, testTxt, flag): def splitTrainVal(root, absTrainRootPath, absValRootPath, absTestRootPath, trainTxt, valTxt, testTxt, flag):
# 按照指定的比例划分训练集、验证集、测试集 # 按照指定的比例划分训练集、验证集、测试集
labelPath = os.path.join(root, dir) dataAbsPath = os.path.abspath(root)
labelAbsPath = os.path.abspath(labelPath)
if flag == "det": if flag == "det":
labelFilePath = os.path.join(labelAbsPath, args.detLabelFileName) labelFilePath = os.path.join(dataAbsPath, args.detLabelFileName)
elif flag == "rec": elif flag == "rec":
labelFilePath = os.path.join(labelAbsPath, args.recLabelFileName) labelFilePath = os.path.join(dataAbsPath, args.recLabelFileName)
labelFileRead = open(labelFilePath, "r", encoding="UTF-8") labelFileRead = open(labelFilePath, "r", encoding="UTF-8")
labelFileContent = labelFileRead.readlines() labelFileContent = labelFileRead.readlines()
@ -38,9 +37,9 @@ def splitTrainVal(root, dir, absTrainRootPath, absValRootPath, absTestRootPath,
imageName = os.path.basename(imageRelativePath) imageName = os.path.basename(imageRelativePath)
if flag == "det": if flag == "det":
imagePath = os.path.join(labelAbsPath, imageName) imagePath = os.path.join(dataAbsPath, imageName)
elif flag == "rec": elif flag == "rec":
imagePath = os.path.join(labelAbsPath, "{}\\{}".format(args.recImageDirName, imageName)) imagePath = os.path.join(dataAbsPath, "{}\\{}".format(args.recImageDirName, imageName))
# 按预设的比例划分训练集、验证集、测试集 # 按预设的比例划分训练集、验证集、测试集
trainValTestRatio = args.trainValTestRatio.split(":") trainValTestRatio = args.trainValTestRatio.split(":")
@ -90,15 +89,20 @@ def genDetRecTrainVal(args):
recValTxt = open(os.path.join(args.recRootPath, "val.txt"), "a", encoding="UTF-8") recValTxt = open(os.path.join(args.recRootPath, "val.txt"), "a", encoding="UTF-8")
recTestTxt = open(os.path.join(args.recRootPath, "test.txt"), "a", encoding="UTF-8") recTestTxt = open(os.path.join(args.recRootPath, "test.txt"), "a", encoding="UTF-8")
for root, dirs, files in os.walk(args.labelRootPath): splitTrainVal(args.datasetRootPath, detAbsTrainRootPath, detAbsValRootPath, detAbsTestRootPath, detTrainTxt, detValTxt,
detTestTxt, "det")
for root, dirs, files in os.walk(args.datasetRootPath):
for dir in dirs: for dir in dirs:
splitTrainVal(root, dir, detAbsTrainRootPath, detAbsValRootPath, detAbsTestRootPath, detTrainTxt, detValTxt, if dir == 'crop_img':
detTestTxt, "det") splitTrainVal(root, recAbsTrainRootPath, recAbsValRootPath, recAbsTestRootPath, recTrainTxt, recValTxt,
splitTrainVal(root, dir, recAbsTrainRootPath, recAbsValRootPath, recAbsTestRootPath, recTrainTxt, recValTxt, recTestTxt, "rec")
recTestTxt, "rec") else:
continue
break break
if __name__ == "__main__": if __name__ == "__main__":
# 功能描述：分别划分检测和识别的训练集、验证集、测试集 # 功能描述：分别划分检测和识别的训练集、验证集、测试集
# 说明：可以根据自己的路径和需求调整参数，图像数据往往多人合作分批标注，每一批图像数据放在一个文件夹内用PPOCRLabel进行标注， # 说明：可以根据自己的路径和需求调整参数，图像数据往往多人合作分批标注，每一批图像数据放在一个文件夹内用PPOCRLabel进行标注，
@ -110,9 +114,9 @@ if __name__ == "__main__":
default="6:2:2", default="6:2:2",
help="ratio of trainset:valset:testset") help="ratio of trainset:valset:testset")
parser.add_argument( parser.add_argument(
"--labelRootPath", "--datasetRootPath",
type=str, type=str,
default="../train_data/label", default="../train_data/",
help="path to the dataset marked by ppocrlabel, E.g, dataset folder named 1,2,3..." help="path to the dataset marked by ppocrlabel, E.g, dataset folder named 1,2,3..."
) )
parser.add_argument( parser.add_argument(