| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135 |
- pipeline_name: PP-StructureV3
- use_doc_preprocessor: True
- use_general_ocr: True
- use_seal_recognition: True
- use_table_recognition: True
- use_formula_recognition: True
- SubModules:
- LayoutDetection:
- module_name: layout_detection
- model_name: PP-DocLayout-L
- model_dir: null
- threshold:
- 0: 0.3 # paragraph_title
- 7: 0.3 # formula
- 16: 0.3 # seal
- layout_nms: True
- layout_unclip_ratio: 1.0
- layout_merge_bboxes_mode:
- 1: "large" # image
- 18: "large" # chart
- SubPipelines:
- DocPreprocessor:
- pipeline_name: doc_preprocessor
- use_doc_orientation_classify: True
- use_doc_unwarping: True
- SubModules:
- DocOrientationClassify:
- module_name: doc_text_orientation
- model_name: PP-LCNet_x1_0_doc_ori
- model_dir: null
- DocUnwarping:
- module_name: image_unwarping
- model_name: UVDoc
- model_dir: null
- GeneralOCR:
- pipeline_name: OCR
- text_type: general
- use_doc_preprocessor: False
- use_textline_orientation: True
- SubModules:
- TextDetection:
- module_name: text_detection
- model_name: PP-OCRv4_mobile_det
- model_dir: null
- limit_side_len: 960
- limit_type: max
- thresh: 0.3
- box_thresh: 0.6
- unclip_ratio: 2.0
- TextLineOrientation:
- module_name: textline_orientation
- model_name: PP-LCNet_x0_25_textline_ori
- model_dir: null
- batch_size: 1
- TextRecognition:
- module_name: text_recognition
- model_name: PP-OCRv4_server_rec_doc
- model_dir: null
- batch_size: 6
- score_thresh: 0.0
-
- TableRecognition:
- pipeline_name: table_recognition_v2
- use_layout_detection: False
- use_doc_preprocessor: False
- use_ocr_model: False
- SubModules:
- TableClassification:
- module_name: table_classification
- model_name: PP-LCNet_x1_0_table_cls
- model_dir: null
- WiredTableStructureRecognition:
- module_name: table_structure_recognition
- model_name: SLANeXt_wired
- model_dir: null
-
- WirelessTableStructureRecognition:
- module_name: table_structure_recognition
- model_name: SLANeXt_wireless
- model_dir: null
-
- WiredTableCellsDetection:
- module_name: table_cells_detection
- model_name: RT-DETR-L_wired_table_cell_det
- model_dir: null
-
- WirelessTableCellsDetection:
- module_name: table_cells_detection
- model_name: RT-DETR-L_wireless_table_cell_det
- model_dir: null
- SealRecognition:
- pipeline_name: seal_recognition
- use_layout_detection: False
- use_doc_preprocessor: False
- SubPipelines:
- SealOCR:
- pipeline_name: OCR
- text_type: seal
- use_doc_preprocessor: False
- use_textline_orientation: False
- SubModules:
- TextDetection:
- module_name: seal_text_detection
- model_name: PP-OCRv4_server_seal_det
- model_dir: null
- limit_side_len: 736
- limit_type: min
- thresh: 0.2
- box_thresh: 0.6
- unclip_ratio: 0.5
- TextRecognition:
- module_name: text_recognition
- model_name: PP-OCRv4_server_rec
- model_dir: null
- batch_size: 1
- score_thresh: 0
-
- FormulaRecognition:
- pipeline_name: formula_recognition
- use_layout_detection: False
- use_doc_preprocessor: False
- SubModules:
- FormulaRecognition:
- module_name: formula_recognition
- model_name: PP-FormulaNet-L
- model_dir: null
- batch_size: 5
|