Skip to content

GitLab

"backend/apps/vscode:/vscode.git/clone" did not exist on "40ea18d54d64ca51731e6371ed9f0f01e7003307"
Commit 22d81ceb authored by WenmuZhou's avatar WenmuZhou
Browse files

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

parents d173bba3 da5d7ee3
Show whitespace changes
Inline Side-by-side
Showing with 269 additions and 109 deletions
MANIFEST.in
View file @ 22d81ceb
......@@ -2,7 +2,8 @@ include LICENSE
include README.md
recursive-include ppocr/utils *.txt utility.py logging.py network.py
recursive-include ppocr/data/ *.py
recursive-include ppocr/data *.py
recursive-include ppocr/postprocess *.py
recursive-include tools/infer *.py
recursive-include ppocr/utils/e2e_utils/ *.py
\ No newline at end of file
recursive-include ppocr/utils/e2e_utils *.py
recursive-include ppstructure *.py
\ No newline at end of file
__init__.py
View file @ 22d81ceb
......@@ -11,7 +11,8 @@
# 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 paddleocr
from .paddleocr import *
__all__ = ['PaddleOCR', 'draw_ocr']
from .paddleocr import PaddleOCR
from .tools.infer.utility import draw_ocr
__version__ = paddleocr.VERSION
__all__ = ['PaddleOCR', 'PPStructure', 'draw_ocr', 'draw_structure_result', 'save_structure_res','download_with_progressbar']
deploy/cpp_infer/docs/windows_vs2019_build.md
View file @ 22d81ceb
......@@ -14,7 +14,7 @@ PaddleOCR在Windows 平台下基于`Visual Studio 2019 Community` 进行了测
### Step1: 下载PaddlePaddle C++ 预测库 fluid_inference
PaddlePaddle C++ 预测库针对不同的`CPU`和`CUDA`版本提供了不同的预编译版本，请根据实际情况下载: [C++预测库下载列表](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/guides/05_inference_deployment/inference/windows_cpp_inference.html)
PaddlePaddle C++ 预测库针对不同的`CPU`和`CUDA`版本提供了不同的预编译版本，请根据实际情况下载: [C++预测库下载列表](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#windows)
解压后`D:\projects\fluid_inference`目录包含内容为：
```
......
doc/doc_ch/whl.md
View file @ 22d81ceb
......@@ -5,23 +5,29 @@
### 1.1 安装whl包
pip安装
```bash
pip install "paddleocr>=2.0.1" # 推荐使用2.0.1+版本
```
本地构建并安装
```bash
python3 setup.py bdist_wheel
pip3 install dist/paddleocr-x.x.x-py3-none-any.whl # x.x.x是paddleocr的版本号
```
## 2 使用
### 2.1 代码使用
paddleocr whl包会自动下载ppocr轻量级模型作为默认模型，可以根据第3节**自定义模型**进行自定义更换。
* 检测+方向分类器+识别全流程
```python
from paddleocr import PaddleOCR, draw_ocr
# Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改lang参数进行切换
# 参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`。
ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
......@@ -32,6 +38,7 @@ for line in result:
# 显示结果
from PIL import Image
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
......@@ -40,31 +47,36 @@ im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
结果是一个list，每个item包含了文本框，文字和识别置信度
```bash
[[[24.0, 36.0], [304.0, 34.0], [304.0, 72.0], [24.0, 74.0]], ['纯臻营养护发素', 0.964739]]
[[[24.0, 80.0], [172.0, 80.0], [172.0, 104.0], [24.0, 104.0]], ['产品信息/参数', 0.98069626]]
[[[24.0, 109.0], [333.0, 109.0], [333.0, 136.0], [24.0, 136.0]], ['（45元/每公斤，100公斤起订）', 0.9676722]]
......
```
结果可视化
<div align="center">
<img src="../imgs_results/whl/11_det_rec.jpg" width="800">
</div>
* 检测+识别
```python
from paddleocr import PaddleOCR, draw_ocr
ocr = PaddleOCR() # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs/11.jpg'
result = ocr.ocr(img_path,cls=False)
result = ocr.ocr(img_path, cls=False)
for line in result:
print(line)
# 显示结果
from PIL import Image
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
......@@ -73,37 +85,45 @@ im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
结果是一个list，每个item包含了文本框，文字和识别置信度
```bash
[[[24.0, 36.0], [304.0, 34.0], [304.0, 72.0], [24.0, 74.0]], ['纯臻营养护发素', 0.964739]]
[[[24.0, 80.0], [172.0, 80.0], [172.0, 104.0], [24.0, 104.0]], ['产品信息/参数', 0.98069626]]
[[[24.0, 109.0], [333.0, 109.0], [333.0, 136.0], [24.0, 136.0]], ['（45元/每公斤，100公斤起订）', 0.9676722]]
......
```
结果可视化
<div align="center">
<img src="../imgs_results/whl/11_det_rec.jpg" width="800">
</div>
* 方向分类器+识别
```python
from paddleocr import PaddleOCR
ocr = PaddleOCR(use_angle_cls=True) # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs_words/ch/word_1.jpg'
result = ocr.ocr(img_path, det=False, cls=True)
for line in result:
print(line)
```
结果是一个list，每个item只包含识别结果和识别置信度
```bash
['韩国小馆', 0.9907421]
```
* 单独执行检测
```python
from paddleocr import PaddleOCR, draw_ocr
ocr = PaddleOCR() # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs/11.jpg'
result = ocr.ocr(img_path, rec=False)
......@@ -118,13 +138,16 @@ im_show = draw_ocr(image, result, txts=None, scores=None, font_path='/path/to/Pa
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
结果是一个list，每个item只包含文本框
```bash
[[26.0, 457.0], [137.0, 457.0], [137.0, 477.0], [26.0, 477.0]]
[[25.0, 425.0], [372.0, 425.0], [372.0, 448.0], [25.0, 448.0]]
[[128.0, 397.0], [273.0, 397.0], [273.0, 414.0], [128.0, 414.0]]
......
```
结果可视化
......@@ -133,29 +156,37 @@ im_show.save('result.jpg')
</div>
* 单独执行识别
```python
from paddleocr import PaddleOCR
ocr = PaddleOCR() # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs_words/ch/word_1.jpg'
result = ocr.ocr(img_path, det=False)
for line in result:
print(line)
```
结果是一个list，每个item只包含识别结果和识别置信度
```bash
['韩国小馆', 0.9907421]
```
* 单独执行方向分类器
```python
from paddleocr import PaddleOCR
ocr = PaddleOCR(use_angle_cls=True) # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs_words/ch/word_1.jpg'
result = ocr.ocr(img_path, det=False, rec=False, cls=True)
for line in result:
print(line)
```
结果是一个list，每个item只包含分类结果和分类置信度
```bash
['0', 0.9999924]
```
......@@ -163,15 +194,19 @@ for line in result:
### 2.2 通过命令行使用
查看帮助信息
```bash
paddleocr -h
```
* 检测+方向分类器+识别全流程
```bash
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
[[[24.0, 36.0], [304.0, 34.0], [304.0, 72.0], [24.0, 74.0]], ['纯臻营养护发素', 0.964739]]
[[[24.0, 80.0], [172.0, 80.0], [172.0, 104.0], [24.0, 104.0]], ['产品信息/参数', 0.98069626]]
......@@ -180,10 +215,13 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --use_angle_cls true
```
* 检测+识别
```bash
paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg
```
结果是一个list，每个item包含了文本框，文字和识别置信度
```bash
[[[24.0, 36.0], [304.0, 34.0], [304.0, 72.0], [24.0, 74.0]], ['纯臻营养护发素', 0.964739]]
[[[24.0, 80.0], [172.0, 80.0], [172.0, 104.0], [24.0, 104.0]], ['产品信息/参数', 0.98069626]]
......@@ -192,20 +230,25 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg
```
* 方向分类器+识别
```bash
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
```bash
['韩国小馆', 0.9907421]
```
* 单独执行检测
```bash
paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --rec false
```
结果是一个list，每个item只包含文本框
```bash
[[26.0, 457.0], [137.0, 457.0], [137.0, 477.0], [26.0, 477.0]]
[[25.0, 425.0], [372.0, 425.0], [372.0, 448.0], [25.0, 448.0]]
......@@ -214,34 +257,42 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --rec false
```
* 单独执行识别
```bash
paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --det false
```
结果是一个list，每个item只包含识别结果和识别置信度
```bash
['韩国小馆', 0.9907421]
```
* 单独执行方向分类器
```bash
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
```bash
['0', 0.9999924]
```
## 3 自定义模型
当内置模型无法满足需求时，需要使用到自己训练的模型。
首先，参照[inference.md](./inference.md) 第一节转换将检测、分类和识别模型转换为inference模型，然后按照如下方式使用
当内置模型无法满足需求时，需要使用到自己训练的模型。 首先，参照[inference.md](./inference.md) 第一节转换将检测、分类和识别模型转换为inference模型，然后按照如下方式使用
### 3.1 代码使用
```python
from paddleocr import PaddleOCR, draw_ocr
# 模型路径下必须含有model和params文件
ocr = PaddleOCR(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)
ocr = PaddleOCR(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)
img_path = 'PaddleOCR/doc/imgs/11.jpg'
result = ocr.ocr(img_path, cls=True)
for line in result:
......@@ -249,6 +300,7 @@ for line in result:
# 显示结果
from PIL import Image
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
......@@ -269,8 +321,10 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_
### 4.1 网络图片
- 代码使用
```python
from paddleocr import PaddleOCR, draw_ocr
from paddleocr import PaddleOCR, draw_ocr, download_with_progressbar
# Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改lang参数进行切换
# 参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`。
ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
......@@ -281,7 +335,9 @@ for line in result:
# 显示结果
from PIL import Image
image = Image.open(img_path).convert('RGB')
download_with_progressbar(img_path, 'tmp.jpg')
image = Image.open('tmp.jpg').convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
......@@ -289,15 +345,21 @@ im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
- 命令行模式
```bash
paddleocr --image_dir http://n.sinaimg.cn/ent/transform/w630h933/20171222/o111-fypvuqf1838418.jpg --use_angle_cls=true
```
### 4.2 numpy数组
仅通过代码使用时支持numpy数组作为输入
```python
import cv2
from paddleocr import PaddleOCR, draw_ocr
# Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改lang参数进行切换
# 参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`。
ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
......@@ -310,6 +372,7 @@ for line in result:
# 显示结果
from PIL import Image
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
......@@ -356,3 +419,4 @@ im_show.save('result.jpg')
| rec | 前向时是否启动识别 | TRUE |
| cls | 前向时是否启动分类 (命令行模式下使用use_angle_cls控制前向是否启动分类) | FALSE |
| show_log | 是否打印det和rec等信息 | FALSE |
| type | 执行ocr或者表格结构化, 值可选['ocr','structure'] | ocr |
doc/doc_en/whl_en.md
View file @ 22d81ceb
......@@ -305,7 +305,8 @@ paddleocr --image_dir http://n.sinaimg.cn/ent/transform/w630h933/20171222/o111-f
Support numpy array as input only when used by code
```python
from paddleocr import PaddleOCR, draw_ocr
import cv2
from paddleocr import PaddleOCR, draw_ocr, download_with_progressbar
ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs/11.jpg'
img = cv2.imread(img_path)
......@@ -316,7 +317,9 @@ for line in result:
# show result
from PIL import Image
image = Image.open(img_path).convert('RGB')
download_with_progressbar(img_path, 'tmp.jpg')
image = Image.open('tmp.jpg').convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
......@@ -362,5 +365,5 @@ im_show.save('result.jpg')
| 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((Use use_angle_cls in command line mode to control whether to start classification in the forward direction) | FALSE |
| show_log | Whether to print log in det and rec
| FALSE |
\ No newline at end of file
| show_log | Whether to print log in det and rec | FALSE |
| type | Perform ocr or table structuring, the value is selected in ['ocr','structure'] | ocr |
\ No newline at end of file
doc/joinus.PNG
View replaced file @ d173bba3 View file @ 22d81ceb
doc/joinus.PNG

189 KB | W: | H:

doc/joinus.PNG

213 KB | W: | H:

doc/joinus.PNG
doc/joinus.PNG
doc/joinus.PNG
doc/joinus.PNG
  • 2-up
  • Swipe
  • Onion skin
doc/table/result_all.jpg
View replaced file @ d173bba3 View file @ 22d81ceb
doc/table/result_all.jpg

386 KB | W: | H:

doc/table/result_all.jpg

521 KB | W: | H:

doc/table/result_all.jpg
doc/table/result_all.jpg
doc/table/result_all.jpg
doc/table/result_all.jpg
  • 2-up
  • Swipe
  • Onion skin
doc/table/result_text.jpg
View replaced file @ d173bba3 View file @ 22d81ceb
doc/table/result_text.jpg

388 KB | W: | H:

doc/table/result_text.jpg

146 KB | W: | H:

doc/table/result_text.jpg
doc/table/result_text.jpg
doc/table/result_text.jpg
doc/table/result_text.jpg
  • 2-up
  • Swipe
  • Onion skin
paddleocr.py
View file @ 22d81ceb
......@@ -29,16 +29,19 @@ from ppocr.utils.logging import get_logger
logger = get_logger()
from ppocr.utils.utility import check_and_read_gif, get_image_file_list
from ppocr.utils.network import maybe_download, download_with_progressbar, is_link, confirm_model_dir_url
from tools.infer.utility import draw_ocr, init_args, str2bool
from tools.infer.utility import draw_ocr, str2bool
from ppstructure.utility import init_args, draw_structure_result
from ppstructure.predict_system import OCRSystem, save_structure_res
__all__ = ['PaddleOCR']
__all__ = ['PaddleOCR', 'PPStructure', 'draw_ocr', 'draw_structure_result', 'save_structure_res','download_with_progressbar']
model_urls = {
'det': {
'ch':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar',
'en':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar'
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar',
'structure': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar'
},
'rec': {
'ch': {
......@@ -110,14 +113,21 @@ model_urls = {
'url':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar',
'dict_path': './ppocr/utils/dict/devanagari_dict.txt'
},
'structure': {
'url': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar',
'dict_path': 'ppocr/utils/dict/table_dict.txt'
}
},
'cls':
'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar'
'cls': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar',
'table': {
'url': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar',
'dict_path': 'ppocr/utils/dict/table_structure_dict.txt'
}
}
SUPPORT_DET_MODEL = ['DB']
VERSION = '2.1'
VERSION = '2.2'
SUPPORT_REC_MODEL = ['CRNN']
BASE_DIR = os.path.expanduser("~/.paddleocr/")
......@@ -129,9 +139,10 @@ def parse_args(mMain=True):
parser.add_argument("--lang", type=str, default='ch')
parser.add_argument("--det", type=str2bool, default=True)
parser.add_argument("--rec", type=str2bool, default=True)
parser.add_argument("--type", type=str, default='ocr')
for action in parser._actions:
if action.dest == 'rec_char_dict_path':
if action.dest in ['rec_char_dict_path', 'table_char_dict_path']:
action.default = None
if mMain:
return parser.parse_args()
......@@ -142,19 +153,7 @@ def parse_args(mMain=True):
return argparse.Namespace(**inference_args_dict)
class PaddleOCR(predict_system.TextSystem):
def __init__(self, **kwargs):
"""
paddleocr package
args:
**kwargs: other params show in paddleocr --help
"""
params = parse_args(mMain=False)
params.__dict__.update(**kwargs)
if not params.show_log:
logger.setLevel(logging.INFO)
self.use_angle_cls = params.use_angle_cls
lang = params.lang
def parse_lang(lang):
latin_lang = [
'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga',
'hr', 'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms',
......@@ -183,23 +182,36 @@ class PaddleOCR(predict_system.TextSystem):
model_urls['rec'].keys(), lang)
if lang == "ch":
det_lang = "ch"
elif lang == 'structure':
det_lang = 'structure'
else:
det_lang = "en"
use_inner_dict = False
if params.rec_char_dict_path is None:
use_inner_dict = True
params.rec_char_dict_path = model_urls['rec'][lang][
'dict_path']
return lang, det_lang
class PaddleOCR(predict_system.TextSystem):
def __init__(self, **kwargs):
"""
paddleocr package
args:
**kwargs: other params show in paddleocr --help
"""
params = parse_args(mMain=False)
params.__dict__.update(**kwargs)
if not params.show_log:
logger.setLevel(logging.INFO)
self.use_angle_cls = params.use_angle_cls
lang, det_lang = parse_lang(params.lang)
# init model dir
params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir,
os.path.join(BASE_DIR, VERSION, 'det', det_lang),
os.path.join(BASE_DIR, VERSION, 'ocr', 'det', det_lang),
model_urls['det'][det_lang])
params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir,
os.path.join(BASE_DIR, VERSION, 'rec', lang),
os.path.join(BASE_DIR, VERSION, 'ocr', 'rec', lang),
model_urls['rec'][lang]['url'])
params.cls_model_dir, cls_url = confirm_model_dir_url(params.cls_model_dir,
os.path.join(BASE_DIR, VERSION, 'cls'),
os.path.join(BASE_DIR, VERSION, 'ocr', 'cls'),
model_urls['cls'])
# download model
maybe_download(params.det_model_dir, det_url)
......@@ -212,9 +224,9 @@ class PaddleOCR(predict_system.TextSystem):
if params.rec_algorithm not in SUPPORT_REC_MODEL:
logger.error('rec_algorithm must in {}'.format(SUPPORT_REC_MODEL))
sys.exit(0)
if use_inner_dict:
params.rec_char_dict_path = str(
Path(__file__).parent / params.rec_char_dict_path)
if params.rec_char_dict_path is None:
params.rec_char_dict_path = str(Path(__file__).parent / model_urls['rec'][lang]['dict_path'])
print(params)
# init det_model and rec_model
......@@ -272,6 +284,59 @@ class PaddleOCR(predict_system.TextSystem):
return rec_res
class PPStructure(OCRSystem):
def __init__(self, **kwargs):
params = parse_args(mMain=False)
params.__dict__.update(**kwargs)
if not params.show_log:
logger.setLevel(logging.INFO)
lang, det_lang = parse_lang(params.lang)
# init model dir
params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir,
os.path.join(BASE_DIR, VERSION, 'ocr', 'det', det_lang),
model_urls['det'][det_lang])
params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir,
os.path.join(BASE_DIR, VERSION, 'ocr', 'rec', lang),
model_urls['rec'][lang]['url'])
params.table_model_dir, table_url = confirm_model_dir_url(params.table_model_dir,
os.path.join(BASE_DIR, VERSION, 'ocr', 'table'),
model_urls['table']['url'])
# download model
maybe_download(params.det_model_dir, det_url)
maybe_download(params.rec_model_dir, rec_url)
maybe_download(params.table_model_dir, table_url)
if params.rec_char_dict_path is None:
params.rec_char_dict_path = str(Path(__file__).parent / model_urls['rec'][lang]['dict_path'])
if params.table_char_dict_path is None:
params.table_char_dict_path = str(Path(__file__).parent / model_urls['table']['dict_path'])
print(params)
super().__init__(params)
def __call__(self, img):
if isinstance(img, str):
# download net image
if img.startswith('http'):
download_with_progressbar(img, 'tmp.jpg')
img = 'tmp.jpg'
image_file = img
img, flag = check_and_read_gif(image_file)
if not flag:
with open(image_file, 'rb') as f:
np_arr = np.frombuffer(f.read(), dtype=np.uint8)
img = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)
if img is None:
logger.error("error in loading image:{}".format(image_file))
return None
if isinstance(img, np.ndarray) and len(img.shape) == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
res = super().__call__(img)
return res
def main():
# for cmd
args = parse_args(mMain=True)
......@@ -284,14 +349,29 @@ def main():
if len(image_file_list) == 0:
logger.error('no images find in {}'.format(args.image_dir))
return
if args.type == 'ocr':
engine = PaddleOCR(**(args.__dict__))
elif args.type == 'structure':
engine = PPStructure(**(args.__dict__))
else:
raise NotImplementedError
ocr_engine = PaddleOCR(**(args.__dict__))
for img_path in image_file_list:
img_name = os.path.basename(img_path).split('.')[0]
logger.info('{}{}{}'.format('*' * 10, img_path, '*' * 10))
result = ocr_engine.ocr(img_path,
if args.type == 'ocr':
result = engine.ocr(img_path,
det=args.det,
rec=args.rec,
cls=args.use_angle_cls)
if result is not None:
for line in result:
logger.info(line)
elif args.type == 'structure':
result = engine(img_path)
save_structure_res(result, args.output, img_name)
for item in result:
item.pop('img')
logger.info(item)
ppocr/data/imaug/label_ops.py
View file @ 22d81ceb
......@@ -19,6 +19,7 @@ from __future__ import unicode_literals
import numpy as np
import string
import json
class ClsLabelEncode(object):
......@@ -39,7 +40,6 @@ class DetLabelEncode(object):
pass
def __call__(self, data):
import json
label = data['label']
label = json.loads(label)
nBox = len(label)
......@@ -53,6 +53,8 @@ class DetLabelEncode(object):
txt_tags.append(True)
else:
txt_tags.append(False)
if len(boxes) == 0:
return None
boxes = self.expand_points_num(boxes)
boxes = np.array(boxes, dtype=np.float32)
txt_tags = np.array(txt_tags, dtype=np.bool)
......@@ -352,19 +354,22 @@ class SRNLabelEncode(BaseRecLabelEncode):
% beg_or_end
return idx
class TableLabelEncode(object):
""" Convert between text-label and text-index """
def __init__(self,
max_text_length,
max_elem_length,
max_cell_num,
character_dict_path,
span_weight = 1.0,
span_weight=1.0,
**kwargs):
self.max_text_length = max_text_length
self.max_elem_length = max_elem_length
self.max_cell_num = max_cell_num
list_character, list_elem = self.load_char_elem_dict(character_dict_path)
list_character, list_elem = self.load_char_elem_dict(
character_dict_path)
list_character = self.add_special_char(list_character)
list_elem = self.add_special_char(list_elem)
self.dict_character = {}
......@@ -380,14 +385,15 @@ class TableLabelEncode(object):
list_elem = []
with open(character_dict_path, "rb") as fin:
lines = fin.readlines()
substr = lines[0].decode('utf-8').strip("\n").split("\t")
substr = lines[0].decode('utf-8').strip("\r\n").split("\t")
character_num = int(substr[0])
elem_num = int(substr[1])
for cno in range(1, 1+character_num):
character = lines[cno].decode('utf-8').strip("\n")
for cno in range(1, 1 + character_num):
character = lines[cno].decode('utf-8').strip("\r\n")
list_character.append(character)
for eno in range(1+character_num, 1+character_num+elem_num):
elem = lines[eno].decode('utf-8').strip("\n")
for eno in range(1 + character_num, 1 + character_num + elem_num):
elem = lines[eno].decode('utf-8').strip("\r\n")
list_elem.append(elem)
return list_character, list_elem
......@@ -412,18 +418,22 @@ class TableLabelEncode(object):
return None
elem_num = len(structure)
structure = [0] + structure + [len(self.dict_elem) - 1]
structure = structure + [0] * (self.max_elem_length + 2 - len(structure))
structure = structure + [0] * (self.max_elem_length + 2 - len(structure)
)
structure = np.array(structure)
data['structure'] = structure
elem_char_idx1 = self.dict_elem['<td>']
elem_char_idx2 = self.dict_elem['<td']
span_idx_list = self.get_span_idx_list()
td_idx_list = np.logical_or(structure == elem_char_idx1, structure == elem_char_idx2)
td_idx_list = np.logical_or(structure == elem_char_idx1,
structure == elem_char_idx2)
td_idx_list = np.where(td_idx_list)[0]
structure_mask = np.ones((self.max_elem_length + 2, 1), dtype=np.float32)
structure_mask = np.ones(
(self.max_elem_length + 2, 1), dtype=np.float32)
bbox_list = np.zeros((self.max_elem_length + 2, 4), dtype=np.float32)
bbox_list_mask = np.zeros((self.max_elem_length + 2, 1), dtype=np.float32)
bbox_list_mask = np.zeros(
(self.max_elem_length + 2, 1), dtype=np.float32)
img_height, img_width, img_ch = data['image'].shape
if len(span_idx_list) > 0:
span_weight = len(td_idx_list) * 1.0 / len(span_idx_list)
......@@ -450,9 +460,11 @@ class TableLabelEncode(object):
char_end_idx = self.get_beg_end_flag_idx('end', 'char')
elem_beg_idx = self.get_beg_end_flag_idx('beg', 'elem')
elem_end_idx = self.get_beg_end_flag_idx('end', 'elem')
data['sp_tokens'] = np.array([char_beg_idx, char_end_idx, elem_beg_idx,
elem_end_idx, elem_char_idx1, elem_char_idx2, self.max_text_length,
self.max_elem_length, self.max_cell_num, elem_num])
data['sp_tokens'] = np.array([
char_beg_idx, char_end_idx, elem_beg_idx, elem_end_idx,
elem_char_idx1, elem_char_idx2, self.max_text_length,
self.max_elem_length, self.max_cell_num, elem_num
])
return data
def encode(self, text, char_or_elem):
......@@ -509,4 +521,3 @@ class TableLabelEncode(object):
assert False, "Unsupport type %s in char_or_elem" \
% char_or_elem
return idx
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment