Example usage.

Merge images vertically with given alignment. Args: images (List[PIL.Image or np.ndarray]): List of images to merge. aligns

Extract OTSL tags and text parts from the input string. Args: s (str): OTSL string. Returns: Tuple[List[str], List[str]

Pad OTSL string to a square (rectangular) format, ensuring each row has equal number of cells. Args: otsl_str (str): OTSL string.

Parse OTSL text and tags into TableCell objects and tag structure. Args: texts (List[str]): List of tokens and text. tokens

Fill a rectangular area in the image with a white background and write the given token string. Args: image (np.ndarray): Image to pa

Transfer vertical point_pairs into poly point in clockwise.

Transfer vertical point_pairs into poly point in clockwise.

Calculate the IOU between two polygons. Args: poly_det (Polygon): A polygon predicted by detector. poly_gt (Polygon): A gt polygo

Calculate the union area between two polygon. Args: poly_det (Polygon): A polygon predicted by detector. poly_gt (Polygon): A gt

compute polygon area

_bitmap: single map with shape (1, H, W), whose values are binarized as {0, 1}

后处理，仿照 get_layout_parsing_results 的逻辑 Args: image: 原始图像 (BGR格式) outputs: 模型输出 scale: 缩放因子 (scale

Predicts the layout parsing result for the given input. Args: input (Union[str, list[str], np.ndarray, list[np.ndarray]]

Args: image: BGR格式的图像 target_input_size: 目标尺寸 (height, width) Returns: 输入字典, (scale_h, scale_w),

Recursively visualize a dict and indenting acrrording by the relationship of keys.

Recursively visualize a dict and indenting acrrording by the relationship of keys.

Process a list of images.

生成一个随机的 RGB 颜色元组 (0.0 到 1.0 之间).

reset

resize image to a size multiple of 32 which is required by the network args: img(array): array with shape [h, w, c]

from https://github.com/WenmuZhou/DBNet.pytorch/blob/master/data_loader/modules/augment.py Args: img: np.ndarray text_polys:

Run all tests

保存可视化结果

logits: N x d