add docstring demo

paddlehub/dataset/dataset.py

@@ -13,31 +13,6 @@
 # limitations under the License.
 
 
-class InputExample(object):
-    """
-    Input data structure of BERT/ERNIE, can satisfy single sequence task like
-    text classification, sequence lableing; Sequence pair task like dialog
-    task.
-    """
-
-    def __init__(self, guid, text_a, text_b=None, label=None):
-        """Constructs a InputExample.
-
-    Args:
-      guid: Unique id for the example.
-      text_a: string. The untokenized text of the first sequence. For single
-        sequence tasks, only this sequence must be specified.
-      text_b: (Optional) string. The untokenized text of the second sequence.
-        Only must be specified for sequence pair tasks.
-      label: (Optional) string. The label of the example. This should be
-        specified for train and dev examples, but not for test examples.
-    """
-        self.guid = guid
-        self.text_a = text_a
-        self.text_b = text_b
-        self.label = label
-
-
 class HubDataset(object):
     def get_train_examples(self):
         raise NotImplementedError()

paddlehub/finetune/task.py

@@ -109,8 +109,15 @@ def create_img_classification_task(feature,
                                    num_classes,
                                    hidden_units=None):
     """
-    Append a multi-layer perceptron classifier for binary classification base
-    on input feature
+    Create the transfer learning task for image classification.
+    Args:
+        feature:
+
+    Return:
+        Task
+
+    Raise:
+        None
     """
     cls_feats = feature
     # append fully connected layer according to hidden_units

paddlehub/reader/nlp_reader.py

@@ -52,12 +52,6 @@ class BaseReader(object):
         self.current_epoch = 0
         self.num_examples = 0
 
-        # if label_map_config:
-        #     with open(label_map_config) as f:
-        #         self.label_map = json.load(f)
-        # else:
-        #     self.label_map = None
-
         self.num_examples = {'train': -1, 'dev': -1, 'test': -1}
 
     def get_train_examples(self):
@@ -164,20 +158,6 @@ class BaseReader(object):
         else:
             label_id = example.label
 
-        # Record = namedtuple(
-        #     'Record',
-        #     ['token_ids', 'text_type_ids', 'position_ids', 'label_id', 'qid'])
-
-        # qid = None
-        # if "qid" in example._fields:
-        #     qid = example.qid
-
-        # record = Record(
-        #     token_ids=token_ids,
-        #     text_type_ids=text_type_ids,
-        #     position_ids=position_ids,
-        #     label_id=label_id,
-        #     qid=qid)
         Record = namedtuple(
             'Record',
             ['token_ids', 'text_type_ids', 'position_ids', 'label_id'])
@@ -211,10 +191,6 @@ class BaseReader(object):
         if batch_records:
             yield self._pad_batch_records(batch_records)
 
-    # def get_num_examples(self, input_file):
-    #     examples = self._read_tsv(input_file)
-    #     return len(examples)
-
     def get_num_examples(self, phase):
         """Get number of examples for train, dev or test."""
         if phase not in ['train', 'val', 'dev', 'test']: