Merge pull request #112 from littletomatodonkey/fix_deli

add delimiter reader

ppcls/data/reader.py

-#copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
+# copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
 #
-#Licensed under the Apache License, Version 2.0 (the "License");
-#you may not use this file except in compliance with the License.
-#You may obtain a copy of the License at
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
 #
 #    http://www.apache.org/licenses/LICENSE-2.0
 #
-#Unless required by applicable law or agreed to in writing, software
-#distributed under the License is distributed on an "AS IS" BASIS,
-#WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-#See the License for the specific language governing permissions and
-#limitations under the License.
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
-import cv2
 import numpy as np
 import os
 import signal
-
+import imghdr
 import paddle
 
 from . import imaug
 from .imaug import transform
-from .imaug import MixupOperator
 from ppcls.utils import logger
 
 trainers_num = int(os.environ.get('PADDLE_TRAINERS_NUM', 1))
@@ -176,7 +174,7 @@ def partial_reader(params, full_lines, part_id=0, part_num=1):
         part_id(int): part index of the current partial data
         part_num(int): part num of the dataset
     """
-    assert part_id < part_num, ("part_num: {} should be larger " \
+    assert part_id < part_num, ("part_num: {} should be larger "
                                 "than part_id: {}".format(part_num, part_id))
 
     full_lines = full_lines[part_id::part_num]
@@ -187,8 +185,9 @@ def partial_reader(params, full_lines, part_id=0, part_num=1):
 
     def reader():
         ops = create_operators(params['transforms'])
+        delimiter = params.get('delimiter', ' ')
         for line in full_lines:
-            img_path, label = line.split()
+            img_path, label = line.split(delimiter)
             img_path = os.path.join(params['data_dir'], img_path)
             with open(img_path, 'rb') as f:
                 img = f.read()