update text.py

hapi/text/text.py

@@ -19,7 +19,6 @@ from __future__ import print_function
 import os
 import six
 import sys
-
 if six.PY2:
     reload(sys)
     sys.setdefaultencoding('utf8')
@@ -50,8 +49,8 @@ __all__ = [
     'BeamSearchDecoder', 'MultiHeadAttention', 'FFN',
     'TransformerEncoderLayer', 'TransformerEncoder', 'TransformerDecoderLayer',
     'TransformerDecoder', 'TransformerBeamSearchDecoder', 'Linear_chain_crf',
-    'Crf_decoding', 'SequenceTagging', 'GRUEncoderLayer', 'CNNEncoder',
-    'BOWEncoder', 'SimpleConvPoolLayer', 'GRUEncoder', 'DynamicGRU', 'LSTMEncoder'
+    'Crf_decoding', 'SequenceTagging', 'GRUEncoderLayer', 'SimCNNEncoder',
+    'SimBOWEncoder', 'SimpleConvPoolLayer', 'SimGRUEncoder', 'DynamicGRU', 'SimLSTMEncoder'
 ]
 
 
@@ -89,12 +88,12 @@ class RNNCell(Layer):
         batch_ref = flatten(batch_ref)[0]
 
         def _is_shape_sequence(seq):
-            if sys.version_info < (3,):
+            if sys.version_info < (3, ):
                 integer_types = (
                     int,
-                    long,)
+                    long, )
             else:
-                integer_types = (int,)
+                integer_types = (int, )
             """For shape, list/tuple of integer is the finest-grained objection"""
             if (isinstance(seq, list) or isinstance(seq, tuple)):
                 if reduce(
@@ -1219,7 +1218,7 @@ class MultiHeadAttention(Layer):
 
         # scale dot product attention
         product = layers.matmul(
-            x=q, y=k, transpose_y=True, alpha=self.d_model ** -0.5)
+            x=q, y=k, transpose_y=True, alpha=self.d_model**-0.5)
         if attn_bias:
             product += attn_bias
         weights = layers.softmax(product)
@@ -1309,6 +1308,7 @@ class TransformerEncoderLayer(Layer):
                  reused_ffn_weights={"reused_fc1": None,
                                      "reused_fc2": None},
                  reused_post_ffn_layernorm=None):
+
         super(TransformerEncoderLayer, self).__init__()
 
         self.preprocesser1 = PrePostProcessLayer(preprocess_cmd, d_model,
@@ -1556,7 +1556,7 @@ class TransformerDecoder(Layer):
         ]
 
 
-# TODO: we should merge GRUCell with BasicGRUCell
+#TODO: we should merge GRUCell with BasicGRUCell
 class GRUCell(RNNCell):
     def __init__(self,
                  input_size,
@@ -1590,7 +1590,7 @@ class GRUCell(RNNCell):
         return [self.hidden_size]
 
 
-# TODO: we should merge GRUCell with BasicGRUCell
+#TODO: we should merge GRUCell with BasicGRUCell
 class GRUEncoderCell(RNNCell):
     def __init__(self,
                  num_layers,
@@ -1606,7 +1606,7 @@ class GRUEncoderCell(RNNCell):
             self.gru_cells.append(
                 self.add_sublayer(
                     "gru_%d" % i,
-                    # BasicGRUCell(
+                    #BasicGRUCell(
                     GRUCell(
                         input_size=input_size if i == 0 else hidden_size,
                         hidden_size=hidden_size,
@@ -1673,6 +1673,7 @@ class Linear_chain_crf(fluid.dygraph.Layer):
         self._transition = value
 
     def forward(self, input, label, length=None):
+
         alpha = self._helper.create_variable_for_type_inference(
             dtype=self._dtype)
         emission_exps = self._helper.create_variable_for_type_inference(
@@ -1723,6 +1724,7 @@ class Crf_decoding(fluid.dygraph.Layer):
         self._transition = value
 
     def forward(self, input, label=None, length=None):
+
         viterbi_path = self._helper.create_variable_for_type_inference(
             dtype=self._dtype)
         this_inputs = {
@@ -1919,7 +1921,7 @@ class SimpleConvPoolLayer(Layer):
         return x
 
 
-class CNNEncoder(Layer):
+class SimCNNEncoder(Layer):
     """
     simple CNNEncoder for simnet
     """
@@ -1933,7 +1935,7 @@ class CNNEncoder(Layer):
                  padding_idx,
                  act
                  ):
-        super(CNNEncoder, self).__init__()
+        super(SimCNNEncoder, self).__init__()
         self.dict_size = dict_size
         self.emb_dim = emb_dim
         self.filter_size = filter_size
@@ -1962,7 +1964,7 @@ class CNNEncoder(Layer):
         emb_out=self.cnn_layer(emb_reshape)
         return emb_out
 
-class BOWEncoder(Layer):
+class SimBOWEncoder(Layer):
     """
     simple BOWEncoder for simnet
     """
@@ -1973,7 +1975,7 @@ class BOWEncoder(Layer):
                  seq_len,
                  padding_idx
                  ):
-        super(BOWEncoder, self).__init__()
+        super(SimBOWEncoder, self).__init__()
         self.dict_size = dict_size
         self.bow_dim = bow_dim
         self.seq_len = seq_len
@@ -2034,7 +2036,7 @@ class DynamicGRU(fluid.dygraph.Layer):
         res = fluid.layers.concat(res, axis=1)
         return res
 
-class GRUEncoder(Layer):
+class SimGRUEncoder(Layer):
     """
     simple GRUEncoder for simnet
     """
@@ -2046,7 +2048,7 @@ class GRUEncoder(Layer):
                  padding_idx,
                  seq_len
                  ):
-        super(GRUEncoder, self).__init__()
+        super(SimGRUEncoder, self).__init__()
         self.dict_size = dict_size
         self.emb_dim = emb_dim
         self.gru_dim = gru_dim
@@ -2071,7 +2073,7 @@ class GRUEncoder(Layer):
         gru = fluid.layers.tanh(gru)
         return gru
 
-class LSTMEncoder(Layer):
+class SimLSTMEncoder(Layer):
     """
     simple LSTMEncoder for simnet
     """
@@ -2087,7 +2089,7 @@ class LSTMEncoder(Layer):
         """
         initialize
         """
-        super(LSTMEncoder, self).__init__()
+        super(SimLSTMEncoder, self).__init__()
         self.dict_size = dict_size
         self.emb_dim = emb_dim
         self.lstm_dim = lstm_dim