fix python2 bug (#305)

* fix python2 bug

demo/sequence_labeling/predict.py

@@ -87,12 +87,13 @@ if __name__ == '__main__':
         add_crf=True)
 
     # Data to be predicted
+    # If using python 2, prefix "u" is necessary
     data = [
-        ["我们变而以书会友，以书结缘，把欧美、港台流行的食品类图谱、画册、工具书汇集一堂。"],
-        ["为了跟踪国际最新食品工艺、流行趋势，大量搜集海外专业书刊资料是提高技艺的捷径。"],
-        ["其中线装古籍逾千册；民国出版物几百种；珍本四册、稀见本四百余册，出版时间跨越三百余年。"],
-        ["有的古木交柯，春机荣欣，从诗人句中得之，而入画中，观之令人心驰。"],
-        ["不过重在晋趣，略增明人气息，妙在集古有道、不露痕迹罢了。"],
+        [u"我们变而以书会友，以书结缘，把欧美、港台流行的食品类图谱、画册、工具书汇集一堂。"],
+        [u"为了跟踪国际最新食品工艺、流行趋势，大量搜集海外专业书刊资料是提高技艺的捷径。"],
+        [u"其中线装古籍逾千册；民国出版物几百种；珍本四册、稀见本四百余册，出版时间跨越三百余年。"],
+        [u"有的古木交柯，春机荣欣，从诗人句中得之，而入画中，观之令人心驰。"],
+        [u"不过重在晋趣，略增明人气息，妙在集古有道、不露痕迹罢了。"],
     ]
 
     # Add 0x02 between characters to match the format of training data,

paddlehub/finetune/task/base_task.py

@@ -24,7 +24,11 @@ import copy
 import logging
 import inspect
 from functools import partial
-
+import six
+if six.PY2:
+    from inspect import getargspec as get_args
+else:
+    from inspect import getfullargspec as get_args
 import numpy as np
 import paddle.fluid as fluid
 from tb_paddle import SummaryWriter
@@ -129,7 +133,7 @@ class TaskHooks():
                 "name: %s has existed in hook_type:%s, use modify method to modify it"
                 % (name, hook_type))
         else:
-            args_num = len(inspect.getfullargspec(func).args)
+            args_num = len(get_args(func).args)
             if args_num != self._hook_params_num[hook_type]:
                 raise ValueError(
                     "The number of parameters to the hook hook_type:%s should be %i"

paddlehub/finetune/task/reading_comprehension_task.py

@@ -26,6 +26,7 @@ import json
 
 from collections import OrderedDict
 
+import io
 import numpy as np
 import paddle.fluid as fluid
 from .base_task import BaseTask
@@ -517,13 +518,13 @@ class ReadingComprehensionTask(BaseTask):
                 null_score_diff_threshold=self.null_score_diff_threshold,
                 is_english=self.is_english)
             if self.phase == 'val' or self.phase == 'dev':
-                with open(
+                with io.open(
                         self.data_reader.dataset.dev_path, 'r',
                         encoding="utf8") as dataset_file:
                     dataset_json = json.load(dataset_file)
                     dataset = dataset_json['data']
             elif self.phase == 'test':
-                with open(
+                with io.open(
                         self.data_reader.dataset.test_path, 'r',
                         encoding="utf8") as dataset_file:
                     dataset_json = json.load(dataset_file)

paddlehub/reader/tokenization.py

@@ -170,7 +170,7 @@ class WSSPTokenizer(object):
         self.inv_vocab = {v: k for k, v in self.vocab.items()}
         self.ws = ws
         self.lower = lower
-        self.dict = pickle.load(open(word_dict, 'rb'), encoding='utf8')
+        self.dict = pickle.load(open(word_dict, 'rb'))
         self.sp_model = spm.SentencePieceProcessor()
         self.window_size = 5
         self.sp_model.Load(sp_model_dir)