SYMBOL INDEX (364 symbols across 47 files)

FILE: docs/en/conf copy.py
  class MockedClassDocumenter (line 110) | class MockedClassDocumenter(autodoc.ClassDocumenter):
    method add_line (line 113) | def add_line(self, line: str, source: str, *lineno: int) -> None:

FILE: docs/en/conf.py
  function install (line 17) | def install(package):
  class MockedClassDocumenter (line 109) | class MockedClassDocumenter(autodoc.ClassDocumenter):
    method add_line (line 112) | def add_line(self, line: str, source: str, *lineno: int) -> None:

FILE: docs/zh_cn/conf.py
  function install (line 17) | def install(package):
  class MockedClassDocumenter (line 109) | class MockedClassDocumenter(autodoc.ClassDocumenter):
    method add_line (line 112) | def add_line(self, line: str, source: str, *lineno: int) -> None:

FILE: pdf_extract_kit/dataset/dataset.py
  class ResizeLongestSide (line 8) | class ResizeLongestSide:
    method __init__ (line 9) | def __init__(self, size):
    method __call__ (line 12) | def __call__(self, img):
  class ImageDataset (line 26) | class ImageDataset(Dataset):
    method __init__ (line 27) | def __init__(self, images, image_ids=None, img_size=1280):
    method __len__ (line 44) | def __len__(self):
    method __getitem__ (line 53) | def __getitem__(self, idx):
  class MathDataset (line 80) | class MathDataset(Dataset):
    method __init__ (line 81) | def __init__(self, image_paths, transform=None):
    method __len__ (line 85) | def __len__(self):
    method __getitem__ (line 88) | def __getitem__(self, idx):

FILE: pdf_extract_kit/registry/registry.py
  class Registry (line 1) | class Registry:
    method __init__ (line 2) | def __init__(self):
    method register (line 5) | def register(self, name):
    method get (line 13) | def get(self, name):
    method list_items (line 18) | def list_items(self):

FILE: pdf_extract_kit/tasks/__init__.py
  function load_task (line 19) | def load_task(name, cfg=None):

FILE: pdf_extract_kit/tasks/base_task.py
  class BaseTask (line 5) | class BaseTask:
    method __init__ (line 6) | def __init__(self, model):
    method load_images (line 9) | def load_images(self, input_data):
    method load_pdf_images (line 42) | def load_pdf_images(self, input_data):

FILE: pdf_extract_kit/tasks/formula_detection/models/yolo.py
  class FormulaDetectionYOLO (line 13) | class FormulaDetectionYOLO:
    method __init__ (line 14) | def __init__(self, config):
    method predict (line 39) | def predict(self, images, result_path, image_ids=None):

FILE: pdf_extract_kit/tasks/formula_detection/task.py
  class FormulaDetectionTask (line 5) | class FormulaDetectionTask(BaseTask):
    method __init__ (line 6) | def __init__(self, model):
    method predict_images (line 9) | def predict_images(self, input_data, result_path):
    method predict_pdfs (line 24) | def predict_pdfs(self, input_data, result_path):

FILE: pdf_extract_kit/tasks/formula_recognition/models/unimernet.py
  class FormulaRecognitionUniMERNet (line 17) | class FormulaRecognitionUniMERNet:
    method __init__ (line 18) | def __init__(self, config):
    method load_model_and_processor (line 33) | def load_model_and_processor(self):
    method predict (line 48) | def predict(self, images, result_path):

FILE: pdf_extract_kit/tasks/formula_recognition/task.py
  class FormulaRecognitionTask (line 6) | class FormulaRecognitionTask(BaseTask):
    method __init__ (line 7) | def __init__(self, model):
    method predict (line 10) | def predict(self, input_data, result_path, bboxes=None):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3.py
  class LayoutDetectionLayoutlmv3 (line 12) | class LayoutDetectionLayoutlmv3:
    method __init__ (line 13) | def __init__(self, config):
    method predict (line 36) | def predict(self, images, result_path, image_ids=None):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/backbone.py
  class VIT_Backbone (line 33) | class VIT_Backbone(Backbone):
    method __init__ (line 38) | def __init__(self, name, out_features, drop_path, img_size, pos_type, ...
    method forward (line 97) | def forward(self, x):
    method output_shape (line 116) | def output_shape(self):
  function build_VIT_backbone (line 125) | def build_VIT_backbone(cfg):
  function build_vit_fpn_backbone (line 158) | def build_vit_fpn_backbone(cfg, input_shape: ShapeSpec):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/beit.py
  function _cfg (line 33) | def _cfg(url='', **kwargs):
  class DropPath (line 43) | class DropPath(nn.Module):
    method __init__ (line 47) | def __init__(self, drop_prob=None):
    method forward (line 51) | def forward(self, x):
    method extra_repr (line 54) | def extra_repr(self) -> str:
  class Mlp (line 58) | class Mlp(nn.Module):
    method __init__ (line 59) | def __init__(self, in_features, hidden_features=None, out_features=Non...
    method forward (line 68) | def forward(self, x):
  class Attention (line 78) | class Attention(nn.Module):
    method __init__ (line 79) | def __init__(
    method forward (line 135) | def forward(self, x, rel_pos_bias=None, training_window_size=None):
  class Block (line 209) | class Block(nn.Module):
    method __init__ (line 211) | def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_sc...
    method forward (line 231) | def forward(self, x, rel_pos_bias=None, training_window_size=None):
  class PatchEmbed (line 243) | class PatchEmbed(nn.Module):
    method __init__ (line 247) | def __init__(self, img_size=[224, 224], patch_size=16, in_chans=3, emb...
    method forward (line 262) | def forward(self, x, position_embedding=None, **kwargs):
  class HybridEmbed (line 280) | class HybridEmbed(nn.Module):
    method __init__ (line 285) | def __init__(self, backbone, img_size=[224, 224], feature_size=None, i...
    method forward (line 309) | def forward(self, x):
  class RelativePositionBias (line 316) | class RelativePositionBias(nn.Module):
    method __init__ (line 318) | def __init__(self, window_size, num_heads):
    method forward (line 348) | def forward(self, training_window_size):
  class BEiT (line 398) | class BEiT(nn.Module):
    method __init__ (line 402) | def __init__(self,
    method fix_init_weight (line 506) | def fix_init_weight(self):
    method _init_weights (line 514) | def _init_weights(self, m):
    method get_num_layers (line 557) | def get_num_layers(self):
    method no_weight_decay (line 561) | def no_weight_decay(self):
    method forward_features (line 564) | def forward_features(self, x):
    method forward (line 601) | def forward(self, x):
  function beit_base_patch16 (line 606) | def beit_base_patch16(pretrained=False, **kwargs):
  function beit_large_patch16 (line 620) | def beit_large_patch16(pretrained=False, **kwargs):
  function dit_base_patch16 (line 634) | def dit_base_patch16(pretrained=False, **kwargs):
  function dit_large_patch16 (line 648) | def dit_large_patch16(pretrained=False, **kwargs):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/deit.py
  function _cfg (line 15) | def _cfg(url='', **kwargs):
  class DropPath (line 24) | class DropPath(nn.Module):
    method __init__ (line 28) | def __init__(self, drop_prob=None):
    method forward (line 32) | def forward(self, x):
    method extra_repr (line 35) | def extra_repr(self) -> str:
  class Mlp (line 39) | class Mlp(nn.Module):
    method __init__ (line 40) | def __init__(self, in_features, hidden_features=None, out_features=Non...
    method forward (line 49) | def forward(self, x):
  class Attention (line 58) | class Attention(nn.Module):
    method __init__ (line 59) | def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, at...
    method forward (line 71) | def forward(self, x):
  class Block (line 86) | class Block(nn.Module):
    method __init__ (line 88) | def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_sc...
    method forward (line 102) | def forward(self, x):
  class PatchEmbed (line 108) | class PatchEmbed(nn.Module):
    method __init__ (line 112) | def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=...
    method forward (line 128) | def forward(self, x):
  class HybridEmbed (line 133) | class HybridEmbed(nn.Module):
    method __init__ (line 138) | def __init__(self, backbone, img_size=224, feature_size=None, in_chans...
    method forward (line 163) | def forward(self, x):
  class ViT (line 170) | class ViT(nn.Module):
    method __init__ (line 174) | def __init__(self,
    method fix_init_weight (line 298) | def fix_init_weight(self):
    method _init_weights (line 306) | def _init_weights(self, m):
    method get_num_layers (line 336) | def get_num_layers(self):
    method no_weight_decay (line 340) | def no_weight_decay(self):
    method _conv_filter (line 343) | def _conv_filter(self, state_dict, patch_size=16):
    method to_2D (line 352) | def to_2D(self, x):
    method to_1D (line 358) | def to_1D(self, x):
    method interpolate_pos_encoding (line 363) | def interpolate_pos_encoding(self, x, w, h):
    method prepare_tokens (line 389) | def prepare_tokens(self, x, mask=None):
    method forward_features (line 414) | def forward_features(self, x):
    method forward (line 441) | def forward(self, x):
  function deit_base_patch16 (line 446) | def deit_base_patch16(pretrained=False, **kwargs):
  function mae_base_patch16 (line 462) | def mae_base_patch16(pretrained=False, **kwargs):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/layoutlmft/data/cord.py
  function quad_to_box (line 24) | def quad_to_box(quad):
  function _get_drive_url (line 46) | def _get_drive_url(url):
  class CordConfig (line 61) | class CordConfig(datasets.BuilderConfig):
    method __init__ (line 63) | def __init__(self, **kwargs):
  class Cord (line 70) | class Cord(datasets.GeneratorBasedBuilder):
    method _info (line 75) | def _info(self):
    method _split_generators (line 97) | def _split_generators(self, dl_manager):
    method get_line_bbox (line 122) | def get_line_bbox(self, bboxs):
    method _generate_examples (line 132) | def _generate_examples(self, filepath):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/layoutlmft/data/data_collator.py
  function pre_calc_rel_mat (line 15) | def pre_calc_rel_mat(segment_ids):
  class DataCollatorForKeyValueExtraction (line 25) | class DataCollatorForKeyValueExtraction(DataCollatorMixin):
    method __call__ (line 56) | def __call__(self, features):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/layoutlmft/data/funsd.py
  class FunsdConfig (line 32) | class FunsdConfig(datasets.BuilderConfig):
    method __init__ (line 35) | def __init__(self, **kwargs):
  class Funsd (line 44) | class Funsd(datasets.GeneratorBasedBuilder):
    method _info (line 51) | def _info(self):
    method _split_generators (line 73) | def _split_generators(self, dl_manager):
    method get_line_bbox (line 85) | def get_line_bbox(self, bboxs):
    method _generate_examples (line 95) | def _generate_examples(self, filepath):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/layoutlmft/data/image_utils.py
  function normalize_bbox (line 12) | def normalize_bbox(bbox, size):
  function load_image (line 21) | def load_image(image_path):
  function crop (line 30) | def crop(image, i, j, h, w, boxes=None):
  function resize (line 46) | def resize(image, size, interpolation, boxes=None):
  function clamp (line 63) | def clamp(num, min_value, max_value):
  function get_bb (line 67) | def get_bb(bb, page_size):
  class ToNumpy (line 91) | class ToNumpy:
    method __call__ (line 93) | def __call__(self, pil_img):
  class ToTensor (line 101) | class ToTensor:
    method __init__ (line 103) | def __init__(self, dtype=torch.float32):
    method __call__ (line 106) | def __call__(self, pil_img):
  function _pil_interp (line 124) | def _pil_interp(method):
  class Compose (line 136) | class Compose:
    method __init__ (line 164) | def __init__(self, transforms):
    method __call__ (line 167) | def __call__(self, img, augmentation=False, box=None):
  class RandomResizedCropAndInterpolationWithTwoPic (line 173) | class RandomResizedCropAndInterpolationWithTwoPic:
    method __init__ (line 186) | def __init__(self, size, second_size=None, scale=(0.08, 1.0), ratio=(3...
    method get_params (line 208) | def get_params(img, scale, ratio):
    method __call__ (line 248) | def __call__(self, img, augmentation=False, box=None):
    method __repr__ (line 264) | def __repr__(self):
  function pil_loader (line 280) | def pil_loader(path: str) -> Image.Image:

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/layoutlmft/data/xfund.py
  class xfund_dataset (line 21) | class xfund_dataset(Dataset):
    method box_norm (line 22) | def box_norm(self, box, width, height):
    method get_segment_ids (line 35) | def get_segment_ids(self, bboxs):
    method get_position_ids (line 47) | def get_position_ids(self, segment_ids):
    method load_data (line 59) | def load_data(
    method __init__ (line 147) | def __init__(
    method __len__ (line 179) | def __len__(self):
    method __getitem__ (line 182) | def __getitem__(self, index):
  function pil_loader (line 209) | def pil_loader(path: str) -> Image.Image:

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/layoutlmft/models/layoutlmv3/configuration_layoutlmv3.py
  class LayoutLMv3Config (line 15) | class LayoutLMv3Config(BertConfig):
    method __init__ (line 18) | def __init__(

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/layoutlmft/models/layoutlmv3/modeling_layoutlmv3.py
  class PatchEmbed (line 50) | class PatchEmbed(nn.Module):
    method __init__ (line 53) | def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=...
    method forward (line 64) | def forward(self, x, position_embedding=None):
  class LayoutLMv3Embeddings (line 77) | class LayoutLMv3Embeddings(nn.Module):
    method __init__ (line 83) | def __init__(self, config):
    method _calc_spatial_position_embeddings (line 105) | def _calc_spatial_position_embeddings(self, bbox):
    method create_position_ids_from_input_ids (line 132) | def create_position_ids_from_input_ids(self, input_ids, padding_idx, p...
    method forward (line 147) | def forward(
    method create_position_ids_from_inputs_embeds (line 188) | def create_position_ids_from_inputs_embeds(self, inputs_embeds):
  class LayoutLMv3PreTrainedModel (line 206) | class LayoutLMv3PreTrainedModel(PreTrainedModel):
    method _init_weights (line 216) | def _init_weights(self, module):
  class LayoutLMv3SelfAttention (line 233) | class LayoutLMv3SelfAttention(nn.Module):
    method __init__ (line 234) | def __init__(self, config):
    method transpose_for_scores (line 254) | def transpose_for_scores(self, x):
    method cogview_attn (line 259) | def cogview_attn(self, attention_scores, alpha=32):
    method forward (line 274) | def forward(
  class LayoutLMv3Attention (line 357) | class LayoutLMv3Attention(nn.Module):
    method __init__ (line 358) | def __init__(self, config):
    method prune_heads (line 364) | def prune_heads(self, heads):
    method forward (line 382) | def forward(
  class LayoutLMv3Layer (line 410) | class LayoutLMv3Layer(nn.Module):
    method __init__ (line 411) | def __init__(self, config):
    method forward (line 421) | def forward(
    method feed_forward_chunk (line 455) | def feed_forward_chunk(self, attention_output):
  class LayoutLMv3Encoder (line 461) | class LayoutLMv3Encoder(nn.Module):
    method __init__ (line 462) | def __init__(self, config, detection=False, out_features=None):
    method relative_position_bucket (line 507) | def relative_position_bucket(self, relative_position, bidirectional=Tr...
    method _cal_1d_pos_emb (line 530) | def _cal_1d_pos_emb(self, hidden_states, position_ids, valid_span):
    method _cal_2d_pos_emb (line 555) | def _cal_2d_pos_emb(self, hidden_states, bbox):
    method forward (line 579) | def forward(
  class LayoutLMv3Model (line 699) | class LayoutLMv3Model(LayoutLMv3PreTrainedModel):
    method __init__ (line 706) | def __init__(self, config, detection=False, out_features=None, image_o...
    method get_input_embeddings (line 746) | def get_input_embeddings(self):
    method set_input_embeddings (line 749) | def set_input_embeddings(self, value):
    method _prune_heads (line 752) | def _prune_heads(self, heads_to_prune):
    method _init_visual_bbox (line 760) | def _init_visual_bbox(self, img_size=(14, 14), max_len=1000):
    method _calc_visual_bbox (line 778) | def _calc_visual_bbox(self, device, dtype, bsz):  # , img_size=(14, 14...
    method forward_image (line 783) | def forward_image(self, x):
    method forward (line 803) | def forward(
  class LayoutLMv3ClassificationHead (line 986) | class LayoutLMv3ClassificationHead(nn.Module):
    method __init__ (line 992) | def __init__(self, config, pool_feature=False):
    method forward (line 1005) | def forward(self, x):
  class LayoutLMv3ForTokenClassification (line 1015) | class LayoutLMv3ForTokenClassification(LayoutLMv3PreTrainedModel):
    method __init__ (line 1019) | def __init__(self, config):
    method forward (line 1032) | def forward(
  class LayoutLMv3ForQuestionAnswering (line 1101) | class LayoutLMv3ForQuestionAnswering(LayoutLMv3PreTrainedModel):
    method __init__ (line 1105) | def __init__(self, config):
    method forward (line 1115) | def forward(
  class LayoutLMv3ForSequenceClassification (line 1196) | class LayoutLMv3ForSequenceClassification(LayoutLMv3PreTrainedModel):
    method __init__ (line 1199) | def __init__(self, config):
    method forward (line 1208) | def forward(

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3.py
  class LayoutLMv3Tokenizer (line 28) | class LayoutLMv3Tokenizer(RobertaTokenizer):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3_fast.py
  class LayoutLMv3TokenizerFast (line 29) | class LayoutLMv3TokenizerFast(RobertaTokenizerFast):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/model_init.py
  function add_vit_config (line 11) | def add_vit_config(cfg):
  function setup (line 63) | def setup(args):
  class DotDict (line 86) | class DotDict(dict):
    method __init__ (line 87) | def __init__(self, *args, **kwargs):
    method __getattr__ (line 90) | def __getattr__(self, key):
    method __setattr__ (line 98) | def __setattr__(self, key, value):
  class Layoutlmv3_Predictor (line 101) | class Layoutlmv3_Predictor(object):
    method __init__ (line 102) | def __init__(self, weights):
    method __call__ (line 120) | def __call__(self, image, ignore_catids=[]):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/rcnn_vl.py
  class VLGeneralizedRCNN (line 23) | class VLGeneralizedRCNN(GeneralizedRCNN):
    method forward (line 31) | def forward(self, batched_inputs: List[Dict[str, torch.Tensor]]):
    method inference (line 85) | def inference(
    method get_batch (line 133) | def get_batch(self, examples, images):
    method _batch_inference (line 139) | def _batch_inference(self, batched_inputs, detected_instances=None):

FILE: pdf_extract_kit/tasks/layout_detection/models/layoutlmv3_util/visualizer.py
  class ColorMode (line 40) | class ColorMode(Enum):
  class GenericMask (line 62) | class GenericMask:
    method __init__ (line 70) | def __init__(self, mask_or_polygons, height, width):
    method mask (line 102) | def mask(self):
    method polygons (line 108) | def polygons(self):
    method has_holes (line 114) | def has_holes(self):
    method mask_to_polygons (line 122) | def mask_to_polygons(self, mask):
    method polygons_to_mask (line 141) | def polygons_to_mask(self, polygons):
    method area (line 146) | def area(self):
    method bbox (line 149) | def bbox(self):
  class _PanopticPrediction (line 158) | class _PanopticPrediction:
    method __init__ (line 163) | def __init__(self, panoptic_seg, segments_info, metadata=None):
    method non_empty_mask (line 199) | def non_empty_mask(self):
    method semantic_masks (line 215) | def semantic_masks(self):
    method instance_masks (line 223) | def instance_masks(self):
  function _create_text_labels (line 233) | def _create_text_labels(classes, scores, class_names, is_crowd=None):
  class VisImage (line 262) | class VisImage:
    method __init__ (line 263) | def __init__(self, img, scale=1.0):
    method _setup_figure (line 274) | def _setup_figure(self, img):
    method reset_image (line 299) | def reset_image(self, img):
    method save (line 307) | def save(self, filepath):
    method get_image (line 315) | def get_image(self):
  class Visualizer (line 336) | class Visualizer:
    method __init__ (line 362) | def __init__(self, img_rgb, metadata=None, scale=1.0, instance_mode=Co...
    method draw_instance_predictions (line 388) | def draw_instance_predictions(self, predictions):
    method draw_sem_seg (line 441) | def draw_sem_seg(self, sem_seg, area_threshold=None, alpha=0.8):
    method draw_panoptic_seg (line 477) | def draw_panoptic_seg(self, panoptic_seg, segments_info, area_threshol...
    method draw_dataset_dict (line 543) | def draw_dataset_dict(self, dic):
    method overlay_instances (line 612) | def overlay_instances(
    method overlay_rotated_instances (line 755) | def overlay_rotated_instances(self, boxes=None, labels=None, assigned_...
    method draw_and_connect_keypoints (line 793) | def draw_and_connect_keypoints(self, keypoints):
    method draw_text (line 855) | def draw_text(
    method draw_box (line 902) | def draw_box(self, box_coord, alpha=0.5, edge_color="g", line_style="-"):
    method draw_rotated_box_with_label (line 936) | def draw_rotated_box_with_label(
    method draw_circle (line 991) | def draw_circle(self, circle_coord, color, radius=3):
    method draw_line (line 1009) | def draw_line(self, x_data, y_data, color, linestyle="-", linewidth=No...
    method draw_binary_mask (line 1040) | def draw_binary_mask(
    method draw_polygon (line 1101) | def draw_polygon(self, segment, color, edge_color=None, alpha=0.5):
    method _jitter (line 1137) | def _jitter(self, color):
    method _create_grayscale_image (line 1156) | def _create_grayscale_image(self, mask=None):
    method _change_color_brightness (line 1167) | def _change_color_brightness(self, color, brightness_factor):
    method _convert_boxes (line 1192) | def _convert_boxes(self, boxes):
    method _convert_masks (line 1201) | def _convert_masks(self, masks_or_polygons):
    method _convert_keypoints (line 1224) | def _convert_keypoints(self, keypoints):
    method get_output (line 1230) | def get_output(self):

FILE: pdf_extract_kit/tasks/layout_detection/models/yolo.py
  class LayoutDetectionYOLO (line 9) | class LayoutDetectionYOLO:
    method __init__ (line 10) | def __init__(self, config):
    method predict (line 52) | def predict(self, images, result_path, image_ids=None):

FILE: pdf_extract_kit/tasks/layout_detection/task.py
  class LayoutDetectionTask (line 6) | class LayoutDetectionTask(BaseTask):
    method __init__ (line 7) | def __init__(self, model):
    method predict_images (line 10) | def predict_images(self, input_data, result_path):
    method predict_pdfs (line 25) | def predict_pdfs(self, input_data, result_path):

FILE: pdf_extract_kit/tasks/ocr/models/paddle_ocr.py
  function img_decode (line 17) | def img_decode(content: bytes):
  function check_img (line 21) | def check_img(img):
  function sorted_boxes (line 57) | def sorted_boxes(dt_boxes):
  function __is_overlaps_y_exceeds_threshold (line 81) | def __is_overlaps_y_exceeds_threshold(bbox1, bbox2, overlap_ratio_thresh...
  function bbox_to_points (line 94) | def bbox_to_points(bbox):
  function points_to_bbox (line 100) | def points_to_bbox(points):
  function merge_intervals (line 108) | def merge_intervals(intervals):
  function remove_intervals (line 125) | def remove_intervals(original, masks):
  function update_det_boxes (line 156) | def update_det_boxes(dt_boxes, mfd_res):
  function merge_spans_to_line (line 175) | def merge_spans_to_line(spans):
  function merge_overlapping_spans (line 213) | def merge_overlapping_spans(spans):
  function merge_det_boxes (line 250) | def merge_det_boxes(dt_boxes):
  class ModifiedPaddleOCR (line 292) | class ModifiedPaddleOCR(PaddleOCR):
    method __init__ (line 293) | def __init__(self, config):
    method predict (line 296) | def predict(self, img, **kwargs):
    method ocr (line 310) | def ocr(self, img, det=True, rec=True, cls=True, bin=False, inv=False,...
    method __call__ (line 388) | def __call__(self, img, cls=True, mfd_res=None):

FILE: pdf_extract_kit/tasks/ocr/task.py
  class OCRTask (line 11) | class OCRTask(BaseTask):
    method __init__ (line 12) | def __init__(self, model):
    method predict_image (line 20) | def predict_image(self, image):
    method prepare_input_files (line 51) | def prepare_input_files(self, input_path):
    method process (line 58) | def process(self, input_path, save_dir=None, visualize=False):
    method visualize_image (line 88) | def visualize_image(self, image, ocr_res, save_path="", cate2color={}):
    method save_json_result (line 106) | def save_json_result(self, ocr_res, save_path):

FILE: pdf_extract_kit/tasks/table_parsing/models/struct_eqtable.py
  class TableParsingStructEqTable (line 9) | class TableParsingStructEqTable:
    method __init__ (line 10) | def __init__(self, config):
    method predict (line 38) | def predict(self, images, result_path, output_format=None, **kwargs):

FILE: pdf_extract_kit/tasks/table_parsing/task.py
  class TableParsingTask (line 6) | class TableParsingTask(BaseTask):
    method __init__ (line 7) | def __init__(self, model):
    method predict (line 10) | def predict(self, input_data, result_path, **kwargs):

FILE: pdf_extract_kit/utils/config_loader.py
  function load_config (line 6) | def load_config(config_path):
  function initialize_tasks_and_models (line 31) | def initialize_tasks_and_models(config):

FILE: pdf_extract_kit/utils/data_preprocess.py
  function load_pdf_page (line 5) | def load_pdf_page(page, dpi):
  function load_pdf (line 13) | def load_pdf(pdf_path, dpi=144):

FILE: pdf_extract_kit/utils/merge_blocks_and_spans.py
  function __is_overlaps_y_exceeds_threshold (line 7) | def __is_overlaps_y_exceeds_threshold(bbox1, bbox2, overlap_ratio_thresh...
  function merge_spans_to_line (line 19) | def merge_spans_to_line(spans):
  function line_sort_spans_by_left_to_right (line 54) | def line_sort_spans_by_left_to_right(lines):
  function fix_text_block (line 71) | def fix_text_block(block):
  function fix_interline_block (line 83) | def fix_interline_block(block):
  function calculate_overlap_area_in_bbox1_area_ratio (line 90) | def calculate_overlap_area_in_bbox1_area_ratio(bbox1, bbox2):
  function fill_spans_in_blocks (line 111) | def fill_spans_in_blocks(blocks, spans, radio):
  function fix_block_spans (line 157) | def fix_block_spans(block_with_spans):
  function detect_lang (line 195) | def detect_lang(string):
  function ocr_escape_special_markdown_char (line 207) | def ocr_escape_special_markdown_char(content):
  function merge_para_with_text (line 228) | def merge_para_with_text(para_block):

FILE: pdf_extract_kit/utils/pdf_utils.py
  function load_pdf (line 3) | def load_pdf(pdf_path):

FILE: pdf_extract_kit/utils/visualization.py
  function colormap (line 5) | def colormap(N=256, normalized=False):
  function visualize_bbox (line 45) | def visualize_bbox(image_path, bboxes, classes, scores, id_to_names, alp...

FILE: pdf_extract_kit/version.py
  function parse_version_info (line 8) | def parse_version_info(version_str: str) -> Tuple:

FILE: project/pdf2markdown/scripts/pdf2markdown.py
  function latex_rm_whitespace (line 23) | def latex_rm_whitespace(s: str):
  function crop_img (line 41) | def crop_img(input_res, input_pil_img, padding_x=0, padding_y=0):
  class PDF2MARKDOWN (line 57) | class PDF2MARKDOWN(OCRTask):
    method __init__ (line 58) | def __init__(self, layout_model, mfd_model, mfr_model, ocr_model):
    method convert_format (line 83) | def convert_format(self, yolo_res, id_to_names, ):
    method process_single_pdf (line 99) | def process_single_pdf(self, image_list):
    method order_blocks (line 262) | def order_blocks(self, blocks):
    method convert2md (line 268) | def convert2md(self, extract_res):
    method process (line 326) | def process(self, input_path, save_dir=None, visualize=False, merge2ma...

FILE: project/pdf2markdown/scripts/run_project.py
  function parse_args (line 14) | def parse_args():
  function main (line 19) | def main(config_path):

FILE: scripts/formula_detection.py
  function parse_args (line 13) | def parse_args():
  function main (line 18) | def main(config_path):

FILE: scripts/formula_recognition.py
  function parse_args (line 13) | def parse_args():
  function main (line 18) | def main(config_path):

FILE: scripts/layout_detection.py
  function parse_args (line 13) | def parse_args():
  function main (line 18) | def main(config_path):

FILE: scripts/ocr.py
  function parse_args (line 13) | def parse_args():
  function main (line 18) | def main(config_path):

FILE: scripts/run_task.py
  function parse_args (line 11) | def parse_args():
  function main (line 16) | def main(config_path):

FILE: scripts/table_parsing.py
  function parse_args (line 13) | def parse_args():
  function main (line 18) | def main(config_path):