From d1b2da280c3443bea32539812d997f87a4072cdf Mon Sep 17 00:00:00 2001
From: littletomatodonkey <dazhiningsibuqu@163.com>
Date: Thu, 22 Sep 2022 14:30:36 +0800
Subject: [PATCH] fix ocr det (#2035)

* fix ocr det

* fix default thres value

* fix readme
---
 .../ch_pp-ocrv3_det/README.md                 |  2 +-
 .../ch_pp-ocrv3_det/module.py                 | 26 +++++++++++++------
 .../ch_pp-ocrv3_det/processor.py              |  2 +-
 3 files changed, 20 insertions(+), 10 deletions(-)

diff --git a/modules/image/text_recognition/ch_pp-ocrv3_det/README.md b/modules/image/text_recognition/ch_pp-ocrv3_det/README.md
index d1bf63bf..495d5358 100755
--- a/modules/image/text_recognition/ch_pp-ocrv3_det/README.md
+++ b/modules/image/text_recognition/ch_pp-ocrv3_det/README.md
@@ -58,7 +58,7 @@
     ```
   - 通过命令行方式实现文字识别模型的调用，更多请见 [PaddleHub命令行指令](../../../../docs/docs_ch/tutorial/cmd_usage.rst)
 
-- ### 2、代码示例
+- ### 2、预测代码示例
 
   - ```python
     import paddlehub as hub
diff --git a/modules/image/text_recognition/ch_pp-ocrv3_det/module.py b/modules/image/text_recognition/ch_pp-ocrv3_det/module.py
index 52d50a60..331f2daf 100644
--- a/modules/image/text_recognition/ch_pp-ocrv3_det/module.py
+++ b/modules/image/text_recognition/ch_pp-ocrv3_det/module.py
@@ -168,8 +168,9 @@ class ChPPOCRv3Det(hub.Module):
                     use_gpu=False,
                     output_dir='detection_result',
                     visualization=False,
-                    box_thresh=0.5,
-                    det_db_unclip_ratio=1.5):
+                    box_thresh=0.6,
+                    det_db_unclip_ratio=1.5,
+                    det_db_score_mode="fast"):
         """
         Get the text box in the predicted images.
         Args:
@@ -180,6 +181,7 @@ class ChPPOCRv3Det(hub.Module):
             visualization (bool): Whether to save image or not.
             box_thresh(float): the threshold of the detected text box's confidence
             det_db_unclip_ratio(float): unclip ratio for post processing in DB detection.
+            det_db_score_mode(str): method to calc the final det score, one of fast(using box) and slow(using poly).
         Returns:
             res (list): The result of text detection box and save path of images.
         """
@@ -206,12 +208,14 @@ class ChPPOCRv3Det(hub.Module):
         assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
 
         preprocessor = DBProcessTest(params={'max_side_len': 960})
-        postprocessor = DBPostProcess(params={
-            'thresh': 0.3,
-            'box_thresh': 0.6,
-            'max_candidates': 1000,
-            'unclip_ratio': det_db_unclip_ratio
-        })
+        postprocessor = DBPostProcess(
+            params={
+                'thresh': 0.3,
+                'box_thresh': 0.6,
+                'max_candidates': 1000,
+                'unclip_ratio': det_db_unclip_ratio,
+                'det_db_score_mode': det_db_score_mode,
+            })
 
         all_imgs = []
         all_ratios = []
@@ -288,6 +292,7 @@ class ChPPOCRv3Det(hub.Module):
                                    use_gpu=args.use_gpu,
                                    output_dir=args.output_dir,
                                    det_db_unclip_ratio=args.det_db_unclip_ratio,
+                                   det_db_score_mode=args.det_db_score_mode,
                                    visualization=args.visualization)
         return results
 
@@ -311,6 +316,11 @@ class ChPPOCRv3Det(hub.Module):
                                            type=float,
                                            default=1.5,
                                            help="unclip ratio for post processing in DB detection.")
+        self.arg_config_group.add_argument(
+            '--det_db_score_mode',
+            type=str,
+            default="str",
+            help="method to calc the final det score, one of fast(using box) and slow(using poly).")
 
     def add_module_input_arg(self):
         """
diff --git a/modules/image/text_recognition/ch_pp-ocrv3_det/processor.py b/modules/image/text_recognition/ch_pp-ocrv3_det/processor.py
index 46a3b263..7854e7f0 100644
--- a/modules/image/text_recognition/ch_pp-ocrv3_det/processor.py
+++ b/modules/image/text_recognition/ch_pp-ocrv3_det/processor.py
@@ -124,9 +124,9 @@ class DBPostProcess(object):
         self.box_thresh = params['box_thresh']
         self.max_candidates = params['max_candidates']
         self.unclip_ratio = params['unclip_ratio']
+        self.score_mode = params['det_db_score_mode']
         self.min_size = 3
         self.dilation_kernel = None
-        self.score_mode = 'fast'
 
     def boxes_from_bitmap(self, pred, _bitmap, dest_width, dest_height):
         '''
-- 
GitLab