Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleOCR into fixocr

ppocr/data/det/dataset_traversal.py

@@ -13,6 +13,7 @@
 #limitations under the License.
 
 import os
+import sys
 import math
 import random
 import functools
@@ -42,6 +43,10 @@ class TrainReader(object):
             img_num = len(label_infor_list)
             img_id_list = list(range(img_num))
             random.shuffle(img_id_list)
+            if sys.platform == "win32":
+                print("multiprocess is not fully compatible with Windows."
+                      "num_workers will be 1.")
+                self.num_workers = 1
             for img_id in range(process_id, img_num, self.num_workers):
                 label_infor = label_infor_list[img_id_list[img_id]]
                 outs = self.process(label_infor)

ppocr/data/reader_main.py

@@ -66,6 +66,8 @@ def reader_main(config=None, mode=None):
     reader_function = params['reader_function']
     function = create_module(reader_function)(params)
     if mode == "train":
+        if sys.platform == "win32":
+            return function(0)
         readers = []
         num_workers = params['num_workers']
         for process_id in range(num_workers):

ppocr/data/rec/dataset_traversal.py

@@ -13,6 +13,7 @@
 #limitations under the License.
 
 import os
+import sys
 import math
 import random
 import numpy as np
@@ -191,16 +192,21 @@ class SimpleReader(object):
                 img_num = len(label_infor_list)
                 img_id_list = list(range(img_num))
                 random.shuffle(img_id_list)
+                if sys.platform=="win32":
+                    print("multiprocess is not fully compatible with Windows."
+                          "num_workers will be 1.")
+                    self.num_workers = 1
                 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]
                     img = cv2.imread(img_path)
-                    if img.shape[-1]==1 or len(list(img.shape))==2:
-                        img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
                     if img is None:
                         logger.info("{} does not exist!".format(img_path))
                         continue
+                    if img.shape[-1]==1 or len(list(img.shape))==2:
+                        img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
+
                     label = substr[1]
                     outs = process_image(img, self.image_shape, label,
                                          self.char_ops, self.loss_type,

ppocr/utils/character.py

@@ -34,7 +34,7 @@ class CharacterOps(object):
             with open(character_dict_path, "rb") as fin:
                 lines = fin.readlines()
                 for line in lines:
-                    line = line.decode('utf-8').strip("\n")
+                    line = line.decode('utf-8').strip("\n").strip("\r\n")
                     self.character_str += line
             dict_character = list(self.character_str)
         elif self.character_type == "en_sensitive":

tools/eval_utils/eval_rec_utils.py

@@ -48,7 +48,7 @@ def eval_rec_run(exe, config, eval_info_dict, mode):
     total_sample_num = 0
     total_acc_num = 0
     total_batch_num = 0
-    if mode == "eval":
+    if mode == "test":
         is_remove_duplicate = False
     else:
         is_remove_duplicate = True
@@ -91,11 +91,11 @@ def test_rec_benchmark(exe, config, eval_info_dict):
     total_correct_number = 0
     eval_data_acc_info = {}
     for eval_data in eval_data_list:
-        config['TestReader']['lmdb_sets_dir'] = \
+        config['EvalReader']['lmdb_sets_dir'] = \
             eval_data_dir + "/" + eval_data
-        eval_reader = reader_main(config=config, mode="test")
+        eval_reader = reader_main(config=config, mode="eval")
         eval_info_dict['reader'] = eval_reader
-        metrics = eval_rec_run(exe, config, eval_info_dict, "test")
+        metrics = eval_rec_run(exe, config, eval_info_dict, "eval")
         total_evaluation_data_number += metrics['total_sample_num']
         total_correct_number += metrics['total_acc_num']
         eval_data_acc_info[eval_data] = metrics