m53297601
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #1344 from WenmuZhou/update_angle_class_doc

Browse Source 
paddleocr whl adaptation dygraph
release/2.0-rc1-0
zhoujun 4 years ago committed by GitHub
parent 0ecc335d9d 28b2d43e57
commit a948584ca5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 320 additions and 84 deletions
Show Stats Download Patch File Download Diff File

7
MANIFEST.in
Unescape View File

@ -1,8 +1,7 @@
include LICENSE.txt
include README.md
recursive-include ppocr/utils *.txt utility.py character.py check.py
recursive-include ppocr/data/det *.py
recursive-include ppocr/utils *.txt utility.py logging.py
recursive-include ppocr/data/ *.py
recursive-include ppocr/postprocess *.py
recursive-include ppocr/postprocess/lanms *.*
recursive-include tools/infer *.py
recursive-include tools/infer *.py

58
doc/doc_ch/whl.md
Unescape View File

@ -261,6 +261,61 @@ im_show.save('result.jpg')
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
```
### 使用网络图片或者numpy数组作为输入
1. 网络图片
代码使用
```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
img_path = 'http://n.sinaimg.cn/ent/transform/w630h933/20171222/o111-fypvuqf1838418.jpg'
result = ocr.ocr(img_path, cls=True)
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]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
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
```
2. numpy数组
仅通过代码使用时支持numpy数组作为输入
```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
img_path = 'PaddleOCR/doc/imgs/11.jpg'
img = cv2.imread(img_path)
# img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY), 如果你自己训练的模型支持灰度图，可以将这句话的注释取消
result = ocr.ocr(img_path, cls=True)
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]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
## 参数说明
| 字段 | 说明 | 默认值 |
@ -285,6 +340,7 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_
| max_text_length | 识别算法能识别的最大文字长度 | 25 |
| rec_char_dict_path | 识别模型字典路径，当rec_model_dir使用方式2传参时需要修改为自己的字典路径 | ./ppocr/utils/ppocr_keys_v1.txt |
| use_space_char | 是否识别空格 | TRUE |
| drop_score | 对输出按照分数(来自于识别模型)进行过滤，低于此分数的不返回 | 0.5 |
| use_angle_cls | 是否加载分类模型 | FALSE |
| cls_model_dir | 分类模型所在文件夹。传参方式有两种，1. None: 自动下载内置模型到 `~/.paddleocr/cls`；2.自己转换好的inference模型路径，模型路径下必须包含model和params文件 | None |
| cls_image_shape | 分类算法的输入图片尺寸 | "3, 48, 192" |
@ -295,4 +351,4 @@ 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 (命令行模式下使用use_angle_cls控制前向是否启动分类) | FALSE |

56
doc/doc_en/whl_en.md
Unescape View File

@ -271,6 +271,59 @@ im_show.save('result.jpg')
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
```
### Use web images or numpy array as input
1. Web image
Use by code
```python
from paddleocr import PaddleOCR, draw_ocr
ocr = PaddleOCR(use_angle_cls=True, lang="ch") # need to run only once to download and load model into memory
img_path = 'http://n.sinaimg.cn/ent/transform/w630h933/20171222/o111-fypvuqf1838418.jpg'
result = ocr.ocr(img_path, cls=True)
for line in result:
print(line)
# show result
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]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
Use by command line
```bash
paddleocr --image_dir http://n.sinaimg.cn/ent/transform/w630h933/20171222/o111-fypvuqf1838418.jpg --use_angle_cls=true
```
2. Numpy array
Support numpy array as input only when used by code
```python
from paddleocr import PaddleOCR, draw_ocr
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)
# img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY), If your own training model supports grayscale images, you can uncomment this line
result = ocr.ocr(img_path, cls=True)
for line in result:
print(line)
# show result
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]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
## Parameter Description
| Parameter | Description | Default value |
@ -295,6 +348,7 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_
| max_text_length | The maximum text length that the recognition algorithm can recognize | 25 |
| rec_char_dict_path | the alphabet path which needs to be modified to your own path when `rec_model_Name` use mode 2 | ./ppocr/utils/ppocr_keys_v1.txt |
| use_space_char | Whether to recognize spaces | TRUE |
| drop_score | Filter the output by score (from the recognition model), and those below this score will not be returned | 0.5 |
| use_angle_cls | Whether to load classification model | FALSE |
| cls_model_dir | the classification inference model folder. There are two ways to transfer parameters, 1. None: Automatically download the built-in model to `~/.paddleocr/cls`; 2. The path of the inference model converted by yourself, the model and params files must be included in the model path | None |
| cls_image_shape | image shape of classification algorithm | "3,48,192" |
@ -305,4 +359,4 @@ 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((Use use_angle_cls in command line mode to control whether to start classification in the forward direction) | FALSE |

248
paddleocr.py
View File

File diff suppressed because it is too large Load Diff

2
setup.py
Unescape View File

@ -32,7 +32,7 @@ setup(
package_dir={'paddleocr': ''},
include_package_data=True,
entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
version='0.0.3',
version='2.0',
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',

33
tools/infer/predict_system.py
Unescape View File

@ -13,6 +13,7 @@
# limitations under the License.
import os
import sys
__dir__ = os.path.dirname(os.path.abspath(__file__))
sys.path.append(__dir__)
sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
@ -30,12 +31,15 @@ from ppocr.utils.utility import get_image_file_list, check_and_read_gif
from ppocr.utils.logging import get_logger
from tools.infer.utility import draw_ocr_box_txt
logger = get_logger()
class TextSystem(object):
def __init__(self, args):
self.text_detector = predict_det.TextDetector(args)
self.text_recognizer = predict_rec.TextRecognizer(args)
self.use_angle_cls = args.use_angle_cls
self.drop_score = args.drop_score
if self.use_angle_cls:
self.text_classifier = predict_cls.TextClassifier(args)
@ -81,7 +85,8 @@ class TextSystem(object):
def __call__(self, img):
ori_im = img.copy()
dt_boxes, elapse = self.text_detector(img)
logger.info("dt_boxes num : {}, elapse : {}".format(len(dt_boxes), elapse))
logger.info("dt_boxes num : {}, elapse : {}".format(
len(dt_boxes), elapse))
if dt_boxes is None:
return None, None
img_crop_list = []
@ -99,9 +104,16 @@ class TextSystem(object):
len(img_crop_list), elapse))
rec_res, elapse = self.text_recognizer(img_crop_list)
logger.info("rec_res num : {}, elapse : {}".format(len(rec_res), elapse))
logger.info("rec_res num : {}, elapse : {}".format(
len(rec_res), elapse))
# self.print_draw_crop_rec_res(img_crop_list, rec_res)
return dt_boxes, rec_res
filter_boxes, filter_rec_res = [], []
for box, rec_reuslt in zip(dt_boxes, rec_res):
text, score = rec_reuslt
if score >= self.drop_score:
filter_boxes.append(box)
filter_rec_res.append(rec_reuslt)
return filter_boxes, filter_rec_res
def sorted_boxes(dt_boxes):
@ -117,8 +129,8 @@ def sorted_boxes(dt_boxes):
_boxes = list(sorted_boxes)
for i in range(num_boxes - 1):
if abs(_boxes[i+1][0][1] - _boxes[i][0][1]) < 10 and \
(_boxes[i + 1][0][0] < _boxes[i][0][0]):
if abs(_boxes[i + 1][0][1] - _boxes[i][0][1]) < 10 and \
(_boxes[i + 1][0][0] < _boxes[i][0][0]):
tmp = _boxes[i]
_boxes[i] = _boxes[i + 1]
_boxes[i + 1] = tmp
@ -143,12 +155,8 @@ def main(args):
elapse = time.time() - starttime
logger.info("Predict time of %s: %.3fs" % (image_file, elapse))
dt_num = len(dt_boxes)
for dno in range(dt_num):
text, score = rec_res[dno]
if score >= drop_score:
text_str = "%s, %.3f" % (text, score)
logger.info(text_str)
for text, score in rec_res:
logger.info("{}, {:.3f}".format(text, score))
if is_visualize:
image = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
@ -174,5 +182,4 @@ def main(args):
if __name__ == "__main__":
logger = get_logger()
main(utility.parse_args())
main(utility.parse_args())
Write Preview
Loading…
Cancel
Save