simpify codes and fix dtype bug in win (#1469)

Author: Steffy-zxf

examples/sentiment_analysis/skep/deploy/python/predict.py

@@ -41,54 +41,11 @@ def convert_example(example,
                     label_list,
                     max_seq_length=512,
                     is_test=False):
-    """
-    Builds model inputs from a sequence or a pair of sequence for sequence classification tasks
-    by concatenating and adding special tokens. And creates a mask from the two sequences passed 
-    to be used in a sequence-pair classification task.
-        
-    A BERT sequence has the following format:
-
-    - single sequence: ``[CLS] X [SEP]``
-    - pair of sequences: ``[CLS] A [SEP] B [SEP]``
-
-    A BERT sequence pair mask has the following format:
-    ::
-        0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
-        | first sequence    | second sequence |
-
-    If only one sequence, only returns the first portion of the mask (0's).
-
-
-    Args:
-        example(obj:`list[str]`): List of input data, containing text and label if it have label.
-        tokenizer(obj:`PretrainedTokenizer`): This tokenizer inherits from :class:`~paddlenlp.transformers.PretrainedTokenizer` 
-            which contains most of the methods. Users should refer to the superclass for more information regarding methods.
-        label_list(obj:`list[str]`): All the labels that the data has.
-        max_seq_len(obj:`int`): The maximum total input sequence length after tokenization. 
-            Sequences longer than this will be truncated, sequences shorter will be padded.
-        is_test(obj:`False`, defaults to `False`): Whether the example contains label or not.
-
-    Returns:
-        input_ids(obj:`list[int]`): The list of token ids.
-        segment_ids(obj: `list[int]`): List of sequence pair mask.
-        label(obj:`numpy.array`, data type of int64, optional): The input label if not is_test.
-    """
     text = example
     encoded_inputs = tokenizer(text=text, max_seq_len=max_seq_length)
-    input_ids = encoded_inputs["input_ids"]
-    segment_ids = encoded_inputs["token_type_ids"]
-
-    if not is_test:
-        # create label maps
-        label_map = {}
-        for (i, l) in enumerate(label_list):
-            label_map[l] = i
-
-        label = label_map[label]
-        label = np.array([label], dtype="int64")
-        return input_ids, segment_ids, label
-    else:
-        return input_ids, segment_ids
+    input_ids = np.array(tokenized_input['input_ids'], dtype="int64")
+    token_type_ids = np.array(tokenized_input['token_type_ids'], dtype="int64")
+    return input_ids, token_type_ids
 
 
 class Predictor(object):