未验证 提交 235b3aff 编写于 作者: M MissPenguin 提交者: GitHub

Merge pull request #749 from tink2123/make_label

make label for paddleocr
...@@ -14,6 +14,15 @@ wget -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/train_icdar2015_l ...@@ -14,6 +14,15 @@ wget -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/train_icdar2015_l
wget -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/test_icdar2015_label.txt wget -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/test_icdar2015_label.txt
``` ```
PaddleOCR 也提供了数据格式转换脚本,可以将官网 label 转换支持的数据格式。 数据转换工具在 `train_data/gen_label.py`, 这里以训练集为例:
```
# 将官网下载的标签文件转换为 train_icdar2015_label.txt
python gen_label.py --mode="det" --root_path="icdar_c4_train_imgs/" \
--input_path="ch4_training_localization_transcription_gt" \
--output_label="train_icdar2015_label.txt"
```
解压数据集和下载标注文件后,PaddleOCR/train_data/ 有两个文件夹和两个文件,分别是: 解压数据集和下载标注文件后,PaddleOCR/train_data/ 有两个文件夹和两个文件,分别是:
``` ```
/PaddleOCR/train_data/icdar2015/text_localization/ /PaddleOCR/train_data/icdar2015/text_localization/
......
...@@ -44,6 +44,13 @@ wget -P ./train_data/ic15_data https://paddleocr.bj.bcebos.com/dataset/rec_gt_t ...@@ -44,6 +44,13 @@ wget -P ./train_data/ic15_data https://paddleocr.bj.bcebos.com/dataset/rec_gt_t
wget -P ./train_data/ic15_data https://paddleocr.bj.bcebos.com/dataset/rec_gt_test.txt wget -P ./train_data/ic15_data https://paddleocr.bj.bcebos.com/dataset/rec_gt_test.txt
``` ```
PaddleOCR 也提供了数据格式转换脚本,可以将官网 label 转换支持的数据格式。 数据转换工具在 `train_data/gen_label.py`, 这里以训练集为例:
```
# 将官网下载的标签文件转换为 rec_gt_label.txt
python gen_label.py --mode="rec" --input_path="{path/of/origin/label}" --output_label="rec_gt_label.txt"
```
最终训练集应有如下文件结构: 最终训练集应有如下文件结构:
``` ```
|-train_data |-train_data
......
#copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
#Licensed under the Apache License, Version 2.0 (the "License");
#you may not use this file except in compliance with the License.
#You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
#Unless required by applicable law or agreed to in writing, software
#distributed under the License is distributed on an "AS IS" BASIS,
#WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#See the License for the specific language governing permissions and
#limitations under the License.
import os
import argparse
def gen_rec_label(input_path, out_label):
with open(out_label, 'w') as out_file:
with open(input_path, 'r') as f:
for line in f.readlines():
tmp = line.strip('\n').replace(" ", "").split(',')
img_path, label = tmp[0], tmp[1]
label = label.replace("\"", "")
out_file.write(img_path + '\t' + label + '\n')
def gen_det_label(root_path, input_dir, out_label):
with open(out_label, 'w') as out_file:
for label_file in os.listdir(input_dir):
img_path = root_path + label_file[3:-4] + ".jpg"
label = []
with open(os.path.join(input_dir, label_file), 'r') as f:
for line in f.readlines():
tmp = line.strip("\n\r").replace("\xef\xbb\xbf", "").split(',')
points = tmp[:-2]
s = []
for i in range(0, len(points), 2):
b = points[i:i + 2]
s.append(b)
result = {"transcription": tmp[-1], "points": s}
label.append(result)
out_file.write(img_path + '\t' + str(label) + '\n')
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
'--mode',
type=str,
default="rec",
help='Generate rec_label or det_label, can be set rec or det')
parser.add_argument(
'--root_path',
type=str,
default=".",
help='The root directory of images.Only takes effect when mode=det ')
parser.add_argument(
'--input_path',
type=str,
default=".",
help='Input_label or input path to be converted')
parser.add_argument(
'--output_label',
type=str,
default="out_label.txt",
help='Output file name')
args = parser.parse_args()
if args.mode == "rec":
print("Generate rec label")
gen_rec_label(args.input_path, args.output_label)
elif args.mode == "det":
gen_det_label(args.root_path, args.input_path, args.output_label)
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册