add missing docstring in paddleocr.py using copilot (#13344)
* add missing docstring in paddleocr.py using copilot Signed-off-by: Zhang Jun <jzhang533@gmail.com> * Update paddleocr.py Co-authored-by: Wang Xin <xinwang614@gmail.com> --------- Signed-off-by: Zhang Jun <jzhang533@gmail.com> Co-authored-by: Wang Xin <xinwang614@gmail.com>pull/13389/head
jzhang533
GitHub
parent
820c240593
commit
603b3728ac
72
paddleocr.py
72
paddleocr.py
|
|
@ -18,7 +18,6 @@ import importlib
|
|||
|
||||
__dir__ = os.path.dirname(__file__)
|
||||
|
||||
import paddle
|
||||
from paddle.utils import try_import
|
||||
|
||||
sys.path.append(os.path.join(__dir__, ""))
|
||||
|
|
@ -685,15 +684,30 @@ class PaddleOCR(predict_system.TextSystem):
|
|||
"""
|
||||
OCR with PaddleOCR
|
||||
|
||||
args:
|
||||
img: img for OCR, support ndarray, img_path and list or ndarray
|
||||
det: use text detection or not. If False, only rec will be exec. Default is True
|
||||
rec: use text recognition or not. If False, only det will be exec. Default is True
|
||||
cls: use angle classifier or not. Default is True. If True, the text with rotation of 180 degrees can be recognized. If no text is rotated by 180 degrees, use cls=False to get better performance. Text with rotation of 90 or 270 degrees can be recognized even if cls=False.
|
||||
bin: binarize image to black and white. Default is False.
|
||||
inv: invert image colors. Default is False.
|
||||
alpha_color: set RGB color Tuple for transparent parts replacement. Default is pure white.
|
||||
slice: use sliding window inference for large images, det and rec must be True. Requires int values for slice["horizontal_stride"], slice["vertical_stride"], slice["merge_x_thres"], slice["merge_y_thres] (See doc/doc_en/slice_en.md). Default is {}.
|
||||
Args:
|
||||
img: Image for OCR. It can be an ndarray, img_path, or a list of ndarrays.
|
||||
det: Use text detection or not. If False, only text recognition will be executed. Default is True.
|
||||
rec: Use text recognition or not. If False, only text detection will be executed. Default is True.
|
||||
cls: Use angle classifier or not. Default is True. If True, the text with a rotation of 180 degrees can be recognized. If no text is rotated by 180 degrees, use cls=False to get better performance.
|
||||
bin: Binarize image to black and white. Default is False.
|
||||
inv: Invert image colors. Default is False.
|
||||
alpha_color: Set RGB color Tuple for transparent parts replacement. Default is pure white.
|
||||
slice: Use sliding window inference for large images. Both det and rec must be True. Requires int values for slice["horizontal_stride"], slice["vertical_stride"], slice["merge_x_thres"], slice["merge_y_thres"] (See doc/doc_en/slice_en.md). Default is {}.
|
||||
|
||||
Returns:
|
||||
If both det and rec are True, returns a list of OCR results for each image. Each OCR result is a list of bounding boxes and recognized text for each detected text region.
|
||||
If det is True and rec is False, returns a list of detected bounding boxes for each image.
|
||||
If det is False and rec is True, returns a list of recognized text for each image.
|
||||
If both det and rec are False, returns a list of angle classification results for each image.
|
||||
|
||||
Raises:
|
||||
AssertionError: If the input image is not of type ndarray, list, str, or bytes.
|
||||
SystemExit: If det is True and the input is a list of images.
|
||||
|
||||
Note:
|
||||
- If the angle classifier is not initialized (use_angle_cls=False), it will not be used during the forward process.
|
||||
- For PDF files, if the input is a list of images and the page_num is specified, only the first page_num images will be processed.
|
||||
- The preprocess_image function is used to preprocess the input image by applying alpha color replacement, inversion, and binarization if specified.
|
||||
"""
|
||||
assert isinstance(img, (np.ndarray, list, str, bytes))
|
||||
if isinstance(img, list) and det == True:
|
||||
|
|
@ -763,7 +777,21 @@ class PaddleOCR(predict_system.TextSystem):
|
|||
|
||||
|
||||
class PPStructure(StructureSystem):
|
||||
"""
|
||||
PPStructure class represents the structure analysis system for PaddleOCR.
|
||||
"""
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
"""
|
||||
Initializes the PPStructure object with the given parameters.
|
||||
|
||||
Args:
|
||||
**kwargs: Additional keyword arguments to customize the behavior of the structure analysis system.
|
||||
|
||||
Raises:
|
||||
AssertionError: If the structure version is not supported.
|
||||
|
||||
"""
|
||||
params = parse_args(mMain=False)
|
||||
params.__dict__.update(**kwargs)
|
||||
assert (
|
||||
|
|
@ -842,6 +870,19 @@ class PPStructure(StructureSystem):
|
|||
img_idx=0,
|
||||
alpha_color=(255, 255, 255),
|
||||
):
|
||||
"""
|
||||
Performs structure analysis on the input image.
|
||||
|
||||
Args:
|
||||
img (str or numpy.ndarray): The input image to perform structure analysis on.
|
||||
return_ocr_result_in_table (bool, optional): Whether to return OCR results in table format. Defaults to False.
|
||||
img_idx (int, optional): The index of the image. Defaults to 0.
|
||||
alpha_color (tuple, optional): The alpha color for transparent images. Defaults to (255, 255, 255).
|
||||
|
||||
Returns:
|
||||
list or dict: The structure analysis results.
|
||||
|
||||
"""
|
||||
img, flag_gif, flag_pdf = check_img(img, alpha_color)
|
||||
if isinstance(img, list) and flag_pdf:
|
||||
res_list = []
|
||||
|
|
@ -857,6 +898,17 @@ class PPStructure(StructureSystem):
|
|||
|
||||
|
||||
def main():
|
||||
"""
|
||||
Main function for running PaddleOCR or PPStructure.
|
||||
|
||||
This function takes command line arguments, processes the images, and performs OCR or structure analysis based on the specified type.
|
||||
|
||||
Args:
|
||||
None
|
||||
|
||||
Returns:
|
||||
None
|
||||
"""
|
||||
# for cmd
|
||||
args = parse_args(mMain=True)
|
||||
image_dir = args.image_dir
|
||||
|
|
|
|||
Loading…
Reference in New Issue