forked from bojone/attention
-
Notifications
You must be signed in to change notification settings - Fork 1
/
attention_keras.py
148 lines (128 loc) · 5.93 KB
/
attention_keras.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
#! -*- coding: utf-8 -*-
from keras import backend as K
from keras.engine.topology import Layer
class Position_Embedding(Layer):
def __init__(self, size=None, mode='sum', **kwargs):
self.size = size #必须为偶数
self.mode = mode
super(Position_Embedding, self).__init__(**kwargs)
def call(self, x):
if (self.size == None) or (self.mode == 'sum'):
self.size = int(x.shape[-1])
batch_size,seq_len = K.shape(x)[0],K.shape(x)[1]
position_j = 1. / K.pow(10000., \
2 * K.arange(self.size / 2, dtype='float32' \
) / self.size)
position_j = K.expand_dims(position_j, 0)
position_i = K.cumsum(K.ones_like(x[:,:,0]), 1)-1 #K.arange不支持变长，只好用这种方法生成
position_i = K.expand_dims(position_i, 2)
position_ij = K.dot(position_i, position_j)
position_ij = K.concatenate([K.cos(position_ij), K.sin(position_ij)], 2)
if self.mode == 'sum':
return position_ij + x
elif self.mode == 'concat':
return K.concatenate([position_ij, x], 2)
def compute_output_shape(self, input_shape):
if self.mode == 'sum':
return input_shape
elif self.mode == 'concat':
return (input_shape[0], input_shape[1], input_shape[2]+self.size)
class Attention(Layer):
def __init__(self, nb_head, size_per_head, **kwargs):
self.nb_head = nb_head
self.size_per_head = size_per_head
self.output_dim = nb_head*size_per_head
super(Attention, self).__init__(**kwargs)
def build(self, input_shape):
self.WQ = self.add_weight(name='WQ',
shape=(input_shape[0][-1], self.output_dim),
initializer='glorot_uniform',
trainable=True)
self.WK = self.add_weight(name='WK',
shape=(input_shape[1][-1], self.output_dim),
initializer='glorot_uniform',
trainable=True)
self.WV = self.add_weight(name='WV',
shape=(input_shape[2][-1], self.output_dim),
initializer='glorot_uniform',
trainable=True)
super(Attention, self).build(input_shape)
def Mask(self, inputs, seq_len, mode='mul'):
if seq_len == None:
return inputs
else:
mask = K.one_hot(seq_len[:,0], K.shape(inputs)[1])
mask = 1 - K.cumsum(mask, 1)
for _ in range(len(inputs.shape)-2):
mask = K.expand_dims(mask, 2)
if mode == 'mul':
return inputs * mask
if mode == 'add':
return inputs - (1 - mask) * 1e12
def call(self, x):
#如果只传入Q_seq,K_seq,V_seq，那么就不做Mask
#如果同时传入Q_seq,K_seq,V_seq,Q_len,V_len，那么对多余部分做Mask
if len(x) == 3:
Q_seq,K_seq,V_seq = x
Q_len,V_len = None,None
elif len(x) == 5:
Q_seq,K_seq,V_seq,Q_len,V_len = x
#对Q、K、V做线性变换
Q_seq = K.dot(Q_seq, self.WQ)
Q_seq = K.reshape(Q_seq, (-1, K.shape(Q_seq)[1], self.nb_head, self.size_per_head))
Q_seq = K.permute_dimensions(Q_seq, (0,2,1,3))
K_seq = K.dot(K_seq, self.WK)
K_seq = K.reshape(K_seq, (-1, K.shape(K_seq)[1], self.nb_head, self.size_per_head))
K_seq = K.permute_dimensions(K_seq, (0,2,1,3))
V_seq = K.dot(V_seq, self.WV)
V_seq = K.reshape(V_seq, (-1, K.shape(V_seq)[1], self.nb_head, self.size_per_head))
V_seq = K.permute_dimensions(V_seq, (0,2,1,3))
#计算内积，然后mask，然后softmax
A = K.batch_dot(Q_seq, K_seq, axes=[3,3])
A = K.permute_dimensions(A, (0,3,2,1))
A = self.Mask(A, V_len, 'add')
A = K.permute_dimensions(A, (0,3,2,1))
A = K.softmax(A)
#输出并mask
O_seq = K.batch_dot(A, V_seq, axes=[3,2])
O_seq = K.permute_dimensions(O_seq, (0,2,1,3))
O_seq = K.reshape(O_seq, (-1, K.shape(O_seq)[1], self.output_dim))
O_seq = self.Mask(O_seq, Q_len, 'mul')
return O_seq
def compute_output_shape(self, input_shape):
return (input_shape[0][0], input_shape[0][1], self.output_dim)
if __name__ == '__main__':
from __future__ import print_function
from keras.preprocessing import sequence
from keras.datasets import imdb
max_features = 20000
maxlen = 80
batch_size = 32
print('Loading data...')
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
print('Pad sequences (samples x time)')
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)
from keras.models import Model
from keras.layers import *
S_inputs = Input(shape=(None,), dtype='int32')
embeddings = Embedding(max_features, 128)(S_inputs)
#embeddings = Position_Embedding()(embeddings) #增加Position_Embedding能轻微提高准确率
O_seq = Attention(8,16)([embeddings,embeddings,embeddings])
O_seq = GlobalAveragePooling1D()(O_seq)
O_seq = Dropout(0.5)(O_seq)
outputs = Dense(1, activation='sigmoid')(O_seq)
model = Model(inputs=S_inputs, outputs=outputs)
# try using different optimizers and different optimizer configs
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
print('Train...')
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=5,
validation_data=(x_test, y_test))