fix some bugs

ppocr/data/rec/dataset_traversal.py

@@ -13,20 +13,16 @@
 #limitations under the License.
 
 import os
-import sys
-import math
 import random
-import numpy as np
-import cv2
+import sys
 
-import string
+import cv2
 import lmdb
 
-from ppocr.utils.utility import initial_logger
 from ppocr.utils.utility import get_image_file_list
-logger = initial_logger()
-
+from ppocr.utils.utility import initial_logger
 from .img_tools import process_image, process_image_srn, get_img_data
+logger = initial_logger()
 
 
 class LMDBReader(object):
@@ -268,7 +264,7 @@ class SimpleReader(object):
                             infer_mode=True)
                     yield norm_img
             else:
-                with open(self.label_file_path, "rb") as fin:
+                with open(self.label_file_path, "r", encoding="utf-8") as fin:
                     label_infor_list = fin.readlines()
                 img_num = len(label_infor_list)
                 img_id_list = list(range(img_num))
@@ -285,8 +281,8 @@ class SimpleReader(object):
                                self.num_workers))
                 for img_id in range(process_id, img_num, self.num_workers):
                     label_infor = label_infor_list[img_id_list[img_id]]
-                    substr = label_infor.decode('utf-8').strip("\n").split("\t")
-                    img_path = self.img_set_dir + "/" + substr[0]
+                    substr = label_infor.strip("\n").strip().split()
+                    img_path = os.path.join(self.img_set_dir, substr[0])
                     img = cv2.imread(img_path)
                     if img is None:
                         logger.info("{} does not exist!".format(img_path))