feat(table): integrate RapidTable model for table recognition

- Add RapidTable model support for table recognition
- Update table model configuration and initialization
- Modify table recognition process to use RapidTable when specified
- Add RapidTable dependency to setup.py

magic-pdf.template.json

@@ -15,7 +15,7 @@
         "enable": true
     },
     "table-config": {
-        "model": "tablemaster",
+        "model": "rapid_table",
         "enable": false,
         "max_time": 400
     },

magic_pdf/libs/Constants.py

@@ -51,3 +51,5 @@ class MODEL_NAME:
     YOLO_V8_MFD = "yolo_v8_mfd"
 
     UniMerNet_v2_Small = "unimernet_small"
+
+    RAPID_TABLE = "rapid_table"
\ No newline at end of file

magic_pdf/model/pdf_extract_kit.py

 from loguru import logger
 import os
 import time
-from pathlib import Path
-import shutil
 from magic_pdf.libs.Constants import *
 from magic_pdf.libs.clean_memory import clean_memory
 from magic_pdf.model.model_list import AtomicModel
@@ -27,6 +25,7 @@ try:
     import unimernet.tasks as tasks
     from unimernet.processors import load_processor
     from doclayout_yolo import YOLOv10
+    from rapid_table import RapidTable
 
 except ImportError as e:
     logger.exception(e)
@@ -51,9 +50,12 @@ def table_model_init(table_model_type, model_path, max_time, _device_='cpu'):
             "device": _device_
         }
         table_model = ppTableModel(config)
+    elif table_model_type == MODEL_NAME.RAPID_TABLE:
+        table_model = RapidTable()
     else:
         logger.error("table model type not allow")
         exit(1)
+
     return table_model
 
 
@@ -226,7 +228,7 @@ class CustomPEKModel:
         self.table_config = kwargs.get("table_config")
         self.apply_table = self.table_config.get("enable", False)
         self.table_max_time = self.table_config.get("max_time", TABLE_MAX_TIME_VALUE)
-        self.table_model_name = self.table_config.get("model", MODEL_NAME.TABLE_MASTER)
+        self.table_model_name = self.table_config.get("model", MODEL_NAME.RAPID_TABLE)
 
         # ocr config
         self.apply_ocr = ocr
@@ -281,7 +283,7 @@ class CustomPEKModel:
                 doclayout_yolo_weights=str(os.path.join(models_dir, self.configs['weights'][self.layout_model_name]))
             )
         # 初始化ocr
-        if self.apply_ocr:
+        # if self.apply_ocr:
         self.ocr_model = atom_model_manager.get_atom_model(
             atom_model_name=AtomicModel.OCR,
             ocr_show_log=show_log,
@@ -451,8 +453,16 @@ class CustomPEKModel:
                         table_result = self.table_model.predict(new_image, "html")
                         if len(table_result) > 0:
                             html_code = table_result[0]
-                else:
+                elif self.table_model_name == MODEL_NAME.TABLE_MASTER:
                     html_code = self.table_model.img2html(new_image)
+                elif self.table_model_name == MODEL_NAME.RAPID_TABLE:
+                    new_image_bgr = cv2.cvtColor(np.asarray(new_image), cv2.COLOR_RGB2BGR)
+                    ocr_result = self.ocr_model.ocr(new_image_bgr)[0]
+                    new_ocr_result = []
+                    for box_ocr_res in ocr_result:
+                        text, score = box_ocr_res[1]
+                        new_ocr_result.append([box_ocr_res[0], text, score])
+                    html_code, table_cell_bboxes, elapse = self.table_model(np.asarray(new_image), new_ocr_result)
 
                 run_time = time.time() - single_table_start_time
                 # logger.info(f"------------table recognition processing ends within {run_time}s-----")

magic_pdf/resources/model_config/model_configs.yaml

@@ -5,3 +5,4 @@ weights:
   unimernet_small: MFR/unimernet_small
   struct_eqtable: TabRec/StructEqTable
   tablemaster: TabRec/TableMaster
+  rapid_table: TabRec/RapidTable
\ No newline at end of file

setup.py

@@ -47,6 +47,7 @@ if __name__ == '__main__':
                      "einops",  # struct-eqtable依赖
                      "accelerate",  # struct-eqtable依赖
                      "doclayout_yolo==0.0.2",  # doclayout_yolo
+                     "rapid_table",  # rapid_table
                      "detectron2"
                      ],
         },