|
|
@@ -0,0 +1,226 @@
|
|
|
+
|
|
|
+pipeline_name: PP-StructureV3
|
|
|
+
|
|
|
+batch_size: 8
|
|
|
+
|
|
|
+use_doc_preprocessor: True
|
|
|
+use_seal_recognition: True
|
|
|
+use_table_recognition: True
|
|
|
+use_formula_recognition: True
|
|
|
+use_chart_recognition: False
|
|
|
+use_region_detection: True
|
|
|
+
|
|
|
+SubModules:
|
|
|
+ LayoutDetection:
|
|
|
+ module_name: layout_detection
|
|
|
+ model_name: PP-DocLayout_plus-L
|
|
|
+ model_dir: null
|
|
|
+ batch_size: 8
|
|
|
+ threshold:
|
|
|
+ 0: 0.3 # paragraph_title
|
|
|
+ 1: 0.5 # image
|
|
|
+ 2: 0.4 # text
|
|
|
+ 3: 0.5 # number
|
|
|
+ 4: 0.5 # abstract
|
|
|
+ 5: 0.5 # content
|
|
|
+ 6: 0.5 # figure_table_chart_title
|
|
|
+ 7: 0.3 # formula
|
|
|
+ 8: 0.5 # table
|
|
|
+ 9: 0.5 # reference
|
|
|
+ 10: 0.5 # doc_title
|
|
|
+ 11: 0.5 # footnote
|
|
|
+ 12: 0.5 # header
|
|
|
+ 13: 0.5 # algorithm
|
|
|
+ 14: 0.5 # footer
|
|
|
+ 15: 0.45 # seal
|
|
|
+ 16: 0.5 # chart
|
|
|
+ 17: 0.5 # formula_number
|
|
|
+ 18: 0.5 # aside_text
|
|
|
+ 19: 0.5 # reference_content
|
|
|
+ layout_nms: True
|
|
|
+ layout_unclip_ratio: [1.0, 1.0]
|
|
|
+ layout_merge_bboxes_mode:
|
|
|
+ 0: "large" # paragraph_title
|
|
|
+ 1: "large" # image
|
|
|
+ 2: "union" # text
|
|
|
+ 3: "union" # number
|
|
|
+ 4: "union" # abstract
|
|
|
+ 5: "union" # content
|
|
|
+ 6: "union" # figure_table_chart_title
|
|
|
+ 7: "large" # formula
|
|
|
+ 8: "union" # table
|
|
|
+ 9: "union" # reference
|
|
|
+ 10: "union" # doc_title
|
|
|
+ 11: "union" # footnote
|
|
|
+ 12: "union" # header
|
|
|
+ 13: "union" # algorithm
|
|
|
+ 14: "union" # footer
|
|
|
+ 15: "union" # seal
|
|
|
+ 16: "large" # chart
|
|
|
+ 17: "union" # formula_number
|
|
|
+ 18: "union" # aside_text
|
|
|
+ 19: "union" # reference_content
|
|
|
+ ChartRecognition:
|
|
|
+ module_name: chart_recognition
|
|
|
+ model_name: PP-Chart2Table
|
|
|
+ model_dir: null
|
|
|
+ batch_size: 1
|
|
|
+ RegionDetection:
|
|
|
+ module_name: layout_detection
|
|
|
+ model_name: PP-DocBlockLayout
|
|
|
+ model_dir: null
|
|
|
+ layout_nms: True
|
|
|
+ layout_merge_bboxes_mode: "small"
|
|
|
+
|
|
|
+SubPipelines:
|
|
|
+ DocPreprocessor:
|
|
|
+ pipeline_name: doc_preprocessor
|
|
|
+ batch_size: 8
|
|
|
+ use_doc_orientation_classify: True
|
|
|
+ use_doc_unwarping: False
|
|
|
+ SubModules:
|
|
|
+ DocOrientationClassify:
|
|
|
+ module_name: doc_text_orientation
|
|
|
+ model_name: PP-LCNet_x1_0_doc_ori
|
|
|
+ model_dir: null
|
|
|
+ batch_size: 8
|
|
|
+ DocUnwarping:
|
|
|
+ module_name: image_unwarping
|
|
|
+ model_name: UVDoc
|
|
|
+ model_dir: null
|
|
|
+
|
|
|
+ GeneralOCR:
|
|
|
+ pipeline_name: OCR
|
|
|
+ batch_size: 8
|
|
|
+ text_type: general
|
|
|
+ use_doc_preprocessor: False
|
|
|
+ use_textline_orientation: True
|
|
|
+ SubModules:
|
|
|
+ TextDetection:
|
|
|
+ module_name: text_detection
|
|
|
+ model_name: PP-OCRv5_server_det
|
|
|
+ model_dir: null
|
|
|
+ limit_side_len: 1200
|
|
|
+ limit_type: max
|
|
|
+ max_side_limit: 4000
|
|
|
+ thresh: 0.3
|
|
|
+ box_thresh: 0.6
|
|
|
+ unclip_ratio: 1.5
|
|
|
+ TextLineOrientation:
|
|
|
+ module_name: textline_orientation
|
|
|
+ model_name: PP-LCNet_x1_0_textline_ori
|
|
|
+ model_dir: null
|
|
|
+ batch_size: 8
|
|
|
+ TextRecognition:
|
|
|
+ module_name: text_recognition
|
|
|
+ model_name: PP-OCRv5_server_rec
|
|
|
+ model_dir: null
|
|
|
+ batch_size: 8
|
|
|
+ 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: SLANet_plus
|
|
|
+ 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
|
|
|
+
|
|
|
+ TableOrientationClassify:
|
|
|
+ module_name: doc_text_orientation
|
|
|
+ model_name: PP-LCNet_x1_0_doc_ori
|
|
|
+ model_dir: null
|
|
|
+ SubPipelines:
|
|
|
+ GeneralOCR:
|
|
|
+ pipeline_name: OCR
|
|
|
+ text_type: general
|
|
|
+ use_doc_preprocessor: False
|
|
|
+ use_textline_orientation: True
|
|
|
+ SubModules:
|
|
|
+ TextDetection:
|
|
|
+ module_name: text_detection
|
|
|
+ model_name: PP-OCRv5_server_det
|
|
|
+ model_dir: null
|
|
|
+ limit_side_len: 1600
|
|
|
+ limit_type: max
|
|
|
+ max_side_limit: 4000
|
|
|
+ thresh: 0.3
|
|
|
+ box_thresh: 0.4
|
|
|
+ unclip_ratio: 1.5
|
|
|
+ TextLineOrientation:
|
|
|
+ module_name: textline_orientation
|
|
|
+ model_name: PP-LCNet_x1_0_textline_ori
|
|
|
+ model_dir: null
|
|
|
+ batch_size: 8
|
|
|
+ TextRecognition:
|
|
|
+ module_name: text_recognition
|
|
|
+ model_name: PP-OCRv5_server_rec
|
|
|
+ model_dir: null
|
|
|
+ batch_size: 8
|
|
|
+ score_thresh: 0.0
|
|
|
+
|
|
|
+ SealRecognition:
|
|
|
+ pipeline_name: seal_recognition
|
|
|
+ batch_size: 8
|
|
|
+ use_layout_detection: False
|
|
|
+ use_doc_preprocessor: False
|
|
|
+ SubPipelines:
|
|
|
+ SealOCR:
|
|
|
+ pipeline_name: OCR
|
|
|
+ batch_size: 8
|
|
|
+ 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
|
|
|
+ max_side_limit: 4000
|
|
|
+ thresh: 0.2
|
|
|
+ box_thresh: 0.6
|
|
|
+ unclip_ratio: 0.5
|
|
|
+ TextRecognition:
|
|
|
+ module_name: text_recognition
|
|
|
+ model_name: PP-OCRv5_server_rec
|
|
|
+ model_dir: null
|
|
|
+ batch_size: 8
|
|
|
+ score_thresh: 0
|
|
|
+
|
|
|
+ FormulaRecognition:
|
|
|
+ pipeline_name: formula_recognition
|
|
|
+ batch_size: 8
|
|
|
+ use_layout_detection: False
|
|
|
+ use_doc_preprocessor: False
|
|
|
+ SubModules:
|
|
|
+ FormulaRecognition:
|
|
|
+ module_name: formula_recognition
|
|
|
+ model_name: PP-FormulaNet_plus-L
|
|
|
+ model_dir: null
|
|
|
+ batch_size: 8
|
