[python] Update API name and return value

python/README.md

@@ -42,10 +42,10 @@
 - onnxruntime和openvino调用方式如下:
     ```python
     # 基于onnxruntime引擎推理
-    from rapidocr_onnxruntime import TextSystem
+    from rapidocr_onnxruntime import RapidOCR
 
     # 基于openvino引擎推理
-    from rapidocr_openvino import TextSystem
+    from rapidocr_openvino import RapidOCR
     ```
 - 关于openvino详细的使用方法，参见[openvino_readme](./rapidocr_openvino/README.md)。
 - 关于选择哪个推理引擎（onnxruntime 或者 openvino）?
@@ -100,15 +100,18 @@
 3. 推理使用
 ```python
 import cv2
-from rapidocr_onnxruntime import TextSystem
-# from rapidocr_openvino import TextSystem
+from rapidocr_onnxruntime import RapidOCR
+# from rapidocr_openvino import RapidOCR
 
-text_sys = TextSystem('config.yaml')
+text_sys = RapidOCR('config.yaml')
 
 img = cv2.imread('test_images/ch_en_num.jpg')
 
-dt_boxes, rec_res = text_sys(img)
-print(rec_res)
+result = text_sys(img)
+print(result)
+
+# result: [[文本框坐标], 文本内容, 置信度]
+# 示例：[[左上, 右上, 右下, 左下], '小明', '0.99']
 ```
 
 ### 源码使用步骤
@@ -182,18 +185,21 @@ print(rec_res)
         import cv2
 
         # 基于onnxruntime引擎推理
-        from rapidocr_onnxruntime import TextSystem
+        from rapidocr_onnxruntime import RapidOCR
 
         # 基于openvino引擎推理
-        # from rapidocr_openvino import TextSystem
+        # from rapidocr_openvino import RapidOCR
 
-        text_sys = TextSystem('config.yaml')
+        text_sys = RapidOCR('config.yaml')
 
         image_path = r'test_images/det_images/ch_en_num.jpg'
         img = cv2.imread(image_path)
 
-        dt_boxes, rec_res = text_sys(img)
-        print(rec_res)
+        result = text_sys(img)
+        print(result)
+
+        # result: [[文本框坐标], 文本内容, 置信度]
+        # 示例：[[左上, 右上, 右下, 左下], '小明', '0.99']
         ```
     - 直接运行`test_demo.py`，可直接可视化查看结果。
         ```bash

python/rapidocr_onnxruntime/__init__.py

@@ -1,4 +1,4 @@
 # -*- encoding: utf-8 -*-
 # @Author: SWHL
 # @Contact: liekkaskono@163.com
-from .rapid_ocr_api import TextSystem
+from .rapid_ocr_api import RapidOCR

python/rapidocr_onnxruntime/rapid_ocr_api.py

@@ -14,9 +14,9 @@ root_dir = Path(__file__).resolve().parent
 sys.path.append(str(root_dir))
 
 
-class TextSystem(object):
+class RapidOCR(object):
     def __init__(self, config_path):
-        super(TextSystem).__init__()
+        super(RapidOCR).__init__()
         if not Path(config_path).exists():
             raise FileExistsError(f'{config_path} does not exist!')
 
@@ -72,7 +72,9 @@ class TextSystem(object):
 
         filter_boxes, filter_rec_res = self.filter_boxes_rec_by_score(dt_boxes,
                                                                       rec_res)
-        return filter_boxes, filter_rec_res
+        fina_result = [[dt.tolist(), rec[0], str(rec[1])]
+                       for dt, rec in zip(filter_boxes, filter_rec_res)]
+        return fina_result
 
     @staticmethod
     def read_yaml(yaml_path):
@@ -155,7 +157,7 @@ class TextSystem(object):
 
 
 if __name__ == '__main__':
-    text_sys = TextSystem('config.yaml')
+    text_sys = RapidOCR('config.yaml')
 
     import cv2
     img = cv2.imread('resources/test_images/det_images/ch_en_num.jpg')

python/rapidocr_openvino/__init__.py

@@ -1,4 +1,4 @@
 # -*- encoding: utf-8 -*-
 # @Author: SWHL
 # @Contact: liekkaskono@163.com
-from .rapid_ocr_api import TextSystem
+from .rapid_ocr_api import RapidOCR

python/rapidocr_openvino/rapid_ocr_api.py

@@ -1,5 +1,6 @@
-# !/usr/bin/env python
 # -*- encoding: utf-8 -*-
+# @Author: SWHL
+# @Contact: liekkaskono@163.com
 import copy
 import importlib
 import sys
@@ -13,11 +14,12 @@ root_dir = Path(__file__).resolve().parent
 sys.path.append(str(root_dir))
 
 
-class TextSystem(object):
+class RapidOCR(object):
     def __init__(self, config_path):
-        super(TextSystem).__init__()
+        super(RapidOCR).__init__()
         if not Path(config_path).exists():
             raise FileExistsError(f'{config_path} does not exist!')
+
         config = self.read_yaml(config_path)
 
         global_config = config['Global']
@@ -60,7 +62,7 @@ class TextSystem(object):
             img_crop_list = self.get_crop_img_list(img, dt_boxes)
 
         if self.use_angle_cls:
-            img_crop_list, angle_list, elapse = self.text_cls(img_crop_list)
+            img_crop_list, _, elapse = self.text_cls(img_crop_list)
             if self.print_verbose:
                 print(f'cls num: {len(img_crop_list)}, elapse: {elapse}')
 
@@ -70,7 +72,9 @@ class TextSystem(object):
 
         filter_boxes, filter_rec_res = self.filter_boxes_rec_by_score(dt_boxes,
                                                                       rec_res)
-        return filter_boxes, filter_rec_res
+        fina_result = [[dt.tolist(), rec[0], str(rec[1])]
+                       for dt, rec in zip(filter_boxes, filter_rec_res)]
+        return fina_result
 
     @staticmethod
     def read_yaml(yaml_path):
@@ -153,7 +157,7 @@ class TextSystem(object):
 
 
 if __name__ == '__main__':
-    text_sys = TextSystem('config.yaml')
+    text_sys = RapidOCR('config.yaml')
 
     import cv2
     img = cv2.imread('resources/test_images/det_images/ch_en_num.jpg')

python/setup_onnxruntime.py

@@ -45,7 +45,7 @@ version_num = version_add_one(latest_version)
 setuptools.setup(
     name=module_name,
     version=version_num,
-    platforms="Windows & Linux & Mac",
+    platforms="Any",
     description="RapidOCR",
     long_description=get_readme(),
     long_description_content_type='text/markdown',
@@ -54,7 +54,7 @@ setuptools.setup(
     url="https://github.com/RapidAI/RapidOCR",
     license='Apache-2.0',
     include_package_data=True,
-    install_requires=["pyclipper>=1.2.1", "onnxruntime",
+    install_requires=["pyclipper>=1.2.1", "onnxruntime>=1.7.0",
                       "opencv_python>=4.5.1.48", "numpy>=1.19.3",
                       "six>=1.15.0", "Shapely>=1.7.1"],
     package_dir={'': module_name},
@@ -62,4 +62,10 @@ setuptools.setup(
     keywords=[
         'ocr text_detection text_recognition db onnxruntime paddleocr openvino'
     ],
+    classifiers=[
+        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
+        'Programming Language :: Python :: 3.9',
+    ]
 )

python/setup_openvino.py

@@ -45,7 +45,7 @@ version_num = version_add_one(latest_version)
 setuptools.setup(
     name=module_name,
     version=version_num,
-    platforms="Windows & Linux & Mac",
+    platforms="Any",
     description="RapidOCR",
     long_description=get_readme(),
     long_description_content_type='text/markdown',
@@ -63,4 +63,10 @@ setuptools.setup(
     keywords=[
         'ocr text_detection text_recognition db onnxruntime paddleocr openvino'
     ],
+    classifiers=[
+        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
+        'Programming Language :: Python :: 3.9',
+    ]
 )

python/test_demo.py

@@ -9,8 +9,8 @@ import cv2
 import numpy as np
 from PIL import Image, ImageDraw, ImageFont
 
-from rapidocr_onnxruntime import TextSystem
-# from rapidocr_openvino import TextSystem
+from rapidocr_onnxruntime import RapidOCR
+# from rapidocr_openvino import RapidOCR
 
 
 def draw_ocr_box_txt(image, boxes, txts, font_path,
@@ -27,7 +27,7 @@ def draw_ocr_box_txt(image, boxes, txts, font_path,
     draw_left = ImageDraw.Draw(img_left)
     draw_right = ImageDraw.Draw(img_right)
     for idx, (box, txt) in enumerate(zip(boxes, txts)):
-        if scores is not None and scores[idx] < text_score:
+        if scores is not None and float(scores[idx]) < text_score:
             continue
 
         color = (random.randint(0, 255),
@@ -69,12 +69,11 @@ def draw_ocr_box_txt(image, boxes, txts, font_path,
     return np.array(img_show)
 
 
-def visualize(image_path, boxes, rec_res, font_path="resources/fonts/FZYTK.TTF"):
+def visualize(image_path, result, font_path="resources/fonts/FZYTK.TTF"):
     image = Image.open(image_path)
-    txts = [rec_res[i][0] for i in range(len(rec_res))]
-    scores = [rec_res[i][1] for i in range(len(rec_res))]
+    boxes, txts, scores = list(zip(*result))
 
-    draw_img = draw_ocr_box_txt(image, boxes,
+    draw_img = draw_ocr_box_txt(image, np.array(boxes),
                                 txts, font_path,
                                 scores,
                                 text_score=0.5)
@@ -89,12 +88,11 @@ def visualize(image_path, boxes, rec_res, font_path="resources/fonts/FZYTK.TTF")
 
 
 if __name__ == '__main__':
-    text_sys = TextSystem('config.yaml')
+    text_sys = RapidOCR('config.yaml')
 
     image_path = 'test_images/ch_en_num.jpg'
     img = cv2.imread(image_path)
-    dt_boxes, rec_res = text_sys(img)
-    print(rec_res)
+    result = text_sys(img)
+    print(result)
 
-    visualize(image_path, dt_boxes, rec_res,
-              font_path='resources/fonts/FZYTK.TTF')
+    visualize(image_path, result, font_path='resources/fonts/FZYTK.TTF')

python/tests/benchmark/benchmark.py

@@ -11,7 +11,7 @@ cur_dir = Path(__file__).resolve().parent
 sys.path.append(str(cur_dir.parent.parent))
 
 import cv2
-from rapidocr_onnxruntime import TextSystem
+from rapidocr_onnxruntime import RapidOCR
 
 
 if __name__ == '__main__':
@@ -20,7 +20,7 @@ if __name__ == '__main__':
     args = parser.parse_args()
 
     yaml_path = cur_dir / args.yaml_path
-    text_sys = TextSystem(yaml_path)
+    text_sys = RapidOCR(yaml_path)
 
     image_dir = cur_dir / 'test_images_benchmark'
     if not image_dir.exists():
@@ -33,7 +33,7 @@ if __name__ == '__main__':
         img = cv2.imread(str(image_path))
 
         start_time = time.time()
-        dt_boxes, rec_res = text_sys(img)
+        result = text_sys(img)
         elapse = time.time() - start_time
 
         cost_time_list.append(elapse)