add distort and space

configs/rec/rec_chinese_lite_train.yml

@@ -14,6 +14,7 @@ Global:
   character_type: ch
   character_dict_path: ./ppocr/utils/ppocr_keys_v1.txt
   loss_type: ctc
+  distort: true
   reader_yml: ./configs/rec/rec_chinese_reader.yml
   pretrain_weights:
   checkpoints:

configs/rec/rec_icdar15_train.yml

@@ -13,6 +13,7 @@ Global:
   max_text_length: 25
   character_type: en
   loss_type: ctc
+  distort: true
   reader_yml: ./configs/rec/rec_icdar15_reader.yml
   pretrain_weights: ./pretrain_models/rec_mv3_none_bilstm_ctc/best_accuracy
   checkpoints:

ppocr/data/rec/dataset_traversal.py

@@ -45,6 +45,8 @@ class LMDBReader(object):
         self.use_tps = False
         if "tps" in params:
             self.ues_tps = True
+        if "distort" in params:
+            self.use_distort = params['distort']
         if params['mode'] == 'train':
             self.batch_size = params['train_batch_size_per_card']
             self.drop_last = True
@@ -142,7 +144,8 @@ class LMDBReader(object):
                                 label=label,
                                 char_ops=self.char_ops,
                                 loss_type=self.loss_type,
-                                max_text_length=self.max_text_length)
+                                max_text_length=self.max_text_length,
+                                distort=self.use_distort)
                             if outs is None:
                                 continue
                             yield outs
@@ -185,6 +188,8 @@ class SimpleReader(object):
         self.use_tps = False
         if "tps" in params:
             self.use_tps = True
+        if "distort" in params:
+            self.use_distort = params['distort']
         if params['mode'] == 'train':
             self.batch_size = params['train_batch_size_per_card']
             self.drop_last = True
@@ -232,9 +237,14 @@ class SimpleReader(object):
                         img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
 
                     label = substr[1]
-                    outs = process_image(img, self.image_shape, label,
-                                         self.char_ops, self.loss_type,
-                                         self.max_text_length)
+                    outs = process_image(
+                        img=img,
+                        image_shape=self.image_shape,
+                        label=label,
+                        char_ops=self.char_ops,
+                        loss_type=self.loss_type,
+                        max_text_length=self.max_text_length,
+                        distort=self.use_distort)
                     if outs is None:
                         continue
                     yield outs

ppocr/utils/ppocr_keys_v1.txt

@@ -6620,4 +6620,5 @@ j
 緖
 續
 紹
-懮
+懮
+