Layout Detection Models¶

class layoutparser.models.Detectron2LayoutModel(config_path, model_path=None, label_map=None, extra_config=None, enforce_cpu=None, device=None)[source]¶

Bases: layoutparser.models.base_layoutmodel.BaseLayoutModel

Create a Detectron2-based Layout Detection Model

Parameters

config_path (str) – The path to the configuration file.
model_path (str, None) – The path to the saved weights of the model. If set, overwrite the weights in the configuration file. Defaults to None.
label_map (dict, optional) – The map from the model prediction (ids) to real word labels (strings). If the config is from one of the supported datasets, Layout Parser will automatically initialize the label_map. Defaults to None.
device (str, optional) – Whether to use cuda or cpu devices. If not set, LayoutParser will automatically determine the device to initialize the models on.
extra_config (list, optional) – Extra configuration passed to the Detectron2 model configuration. The argument will be used in the merge_from_list function. Defaults to [].

Examples::

>>> import layoutparser as lp
>>> model = lp.Detectron2LayoutModel('lp://HJDataset/faster_rcnn_R_50_FPN_3x/config')
>>> model.detect(image)

DEPENDENCIES = ['detectron2']¶

DETECTOR_NAME = 'detectron2'¶

MODEL_CATALOG = {'HJDataset': {'faster_rcnn_R_50_FPN_3x': 'https://www.dropbox.com/s/6icw6at8m28a2ho/model_final.pth?dl=1', 'mask_rcnn_R_50_FPN_3x': 'https://www.dropbox.com/s/893paxpy5suvlx9/model_final.pth?dl=1', 'retinanet_R_50_FPN_3x': 'https://www.dropbox.com/s/yxsloxu3djt456i/model_final.pth?dl=1'}, 'MFD': {'faster_rcnn_R_50_FPN_3x': 'https://www.dropbox.com/s/7xel0i3iqpm2p8y/model_final.pth?dl=1'}, 'NewspaperNavigator': {'faster_rcnn_R_50_FPN_3x': 'https://www.dropbox.com/s/6ewh6g8rqt2ev3a/model_final.pth?dl=1'}, 'PrimaLayout': {'mask_rcnn_R_50_FPN_3x': 'https://www.dropbox.com/s/h7th27jfv19rxiy/model_final.pth?dl=1'}, 'PubLayNet': {'faster_rcnn_R_50_FPN_3x': 'https://www.dropbox.com/s/dgy9c10wykk4lq4/model_final.pth?dl=1', 'mask_rcnn_R_50_FPN_3x': 'https://www.dropbox.com/s/d9fc9tahfzyl6df/model_final.pth?dl=1', 'mask_rcnn_X_101_32x8d_FPN_3x': 'https://www.dropbox.com/s/57zjbwv6gh3srry/model_final.pth?dl=1'}, 'TableBank': {'faster_rcnn_R_101_FPN_3x': 'https://www.dropbox.com/s/6vzfk8lk9xvyitg/model_final.pth?dl=1', 'faster_rcnn_R_50_FPN_3x': 'https://www.dropbox.com/s/8v4uqmz1at9v72a/model_final.pth?dl=1'}}¶

gather_output(outputs)[source]¶

detect(image)[source]¶

Detect the layout of a given image.

Parameters: image (np.ndarray or PIL.Image) – The input image to detect.
Returns: The detected layout of the input image
Return type: Layout

image_loader(image: Union[np.ndarray, Image.Image])[source]¶: It will process the input images appropriately to the target format.