-
Notifications
You must be signed in to change notification settings - Fork 7
/
layer_util.py
215 lines (190 loc) · 8.62 KB
/
layer_util.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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
#!encoding=utf-8
import tensorflow.compat.v1 as tf
'''
The implementation of multi-head attention mechanism
refers to Kyubyong/transformer(https://github.com/Kyubyong/transformer)
February 2020
'''
def layer_norm(inputs, scope='ln'):
'''Applies layer normalization. See https://arxiv.org/abs/1607.06450.
inputs: A tensor with 2 or more dimensions, where the first dimension has `batch_size`.
epsilon: A floating number. A very small number for preventing ZeroDivision Error.
scope: Optional scope for `variable_scope`.
Returns:
A tensor with the same shape and data dtype as `inputs`.
'''
epsilon = 1e-8
with tf.variable_scope(scope):
inputs_shape = inputs.get_shape()
params_shape = inputs_shape[-1:]
# [-1] means last dimension
mean, variance = tf.nn.moments(inputs, [-1], keep_dims=True)
beta = tf.get_variable("beta", params_shape, initializer=tf.zeros_initializer())
gamma = tf.get_variable("gamma", params_shape, initializer=tf.ones_initializer())
normalized = (inputs - mean) / ((variance + epsilon) ** (.5))
outputs = gamma * normalized + beta
return outputs
def get_embeddings(dict_size, num_units, scope, zero_pad=True, partitioner=None):
'''Constructs token embedding matrix.
Note that the column of index 0's are set to zeros.
dict_size: scalar. V.
num_units: embedding dimensionalty. E.
zero_pad: Boolean. If True, all the values of the first row (id = 0) should be constant zero
To apply query/key masks easily, zero pad is turned on.
Returns
weight variable: (V, E)
'''
with tf.variable_scope(scope):
w_init = tf.truncated_normal_initializer(mean=0, stddev=0.1)
embeddings = tf.get_variable('w',
dtype=tf.float32,
shape=(dict_size, num_units),
initializer=w_init,
partitioner=partitioner)
# initializer=tf.contrib.layers.xavier_initializer())
if zero_pad:
embeddings = tf.concat((tf.zeros(shape=[1, num_units]),
embeddings[1:, :]), 0)
return embeddings
def mask(inputs, queries=None, keys=None, type=None):
"""Masks paddings on keys or queries to inputs
inputs: 3d tensor. (N, T_q, T_k)
queries: 3d tensor. (N, T_q, d)
keys: 3d tensor. (N, T_k, d)
e.g.,
>> queries = tf.constant([[[1.],
[2.],
[0.]]], tf.float32) # (1, 3, 1)
>> keys = tf.constant([[[4.],
[0.]]], tf.float32) # (1, 2, 1)
>> inputs = tf.constant([[[4., 0.],
[8., 0.],
[0., 0.]]], tf.float32)
>> mask(inputs, queries, keys, "key")
array([[[ 4.0000000e+00, -4.2949673e+09],
[ 8.0000000e+00, -4.2949673e+09],
[ 0.0000000e+00, -4.2949673e+09]]], dtype=float32)
>> inputs = tf.constant([[[1., 0.],
[1., 0.],
[1., 0.]]], tf.float32)
>> mask(inputs, queries, keys, "query")
array([[[1., 0.],
[1., 0.],
[0., 0.]]], dtype=float32)
"""
padding_num = -2 ** 32 + 1
#### 将keys对应的padding部分的权重设置成很大的一个负数（等价于不存在对应位置的attention）
if type in ("k", "key", "keys"):
# Generate masks
masks = tf.sign(tf.reduce_sum(tf.abs(keys), axis=-1)) # (N, T_k)
masks = tf.expand_dims(masks, 1) # (N, 1, T_k)
masks = tf.tile(masks, [1, tf.shape(queries)[1], 1]) # (N, T_q, T_k)
# Apply masks to inputs
paddings = tf.ones_like(inputs) * padding_num
outputs = tf.where(tf.equal(masks, 0), paddings, inputs) # (N, T_q, T_k)
elif type in ("q", "query", "queries"):
# Generate masks
masks = tf.sign(tf.reduce_sum(tf.abs(queries), axis=-1)) # (N, T_q)
masks = tf.expand_dims(masks, -1) # (N, T_q, 1)
masks = tf.tile(masks, [1, 1, tf.shape(keys)[1]]) # (N, T_q, T_k)
# Apply masks to inputs
outputs = inputs * masks
elif type in ("f", "future", "right"):
diag_vals = tf.ones_like(inputs[0, :, :]) # (T_q, T_k)
# tril = tf.linalg.LinearOperatorLowerTriangular(diag_vals).to_dense() # (T_q, T_k)
tril = tf.linalg.band_part(diag_vals, -1, 0) # (T_q, T_k)
masks = tf.tile(tf.expand_dims(tril, 0), [tf.shape(inputs)[0], 1, 1]) # (N, T_q, T_k)
paddings = tf.ones_like(masks) * padding_num
outputs = tf.where(tf.equal(masks, 0), paddings, inputs)
else:
print("Check if you entered type correctly!")
return outputs
def scaled_dot_product_attention(Q, K, V,
causality=False, dropout_rate=0.,
training=True,
scope="sdpa"):
'''See 3.2.1.
Q: Packed queries. 3d tensor. [N, T_q, d_k].
K: Packed keys. 3d tensor. [N, T_k, d_k].
V: Packed values. 3d tensor. [N, T_k, d_v].
causality: If True, applies masking for future blinding
dropout_rate: A floating point number of [0, 1].
training: boolean for controlling droput
scope: Optional scope for `variable_scope`.
'''
with tf.variable_scope(scope, reuse=tf.AUTO_REUSE):
d_k = Q.get_shape().as_list()[-1]
# dot product
outputs = tf.matmul(Q, tf.transpose(K, [0, 2, 1])) # (N, T_q, T_k)
# scale
outputs /= d_k ** 0.5
# key masking
outputs = mask(outputs, Q, K, type="key")
# causality or future blinding masking
if causality:
outputs = mask(outputs, type="future")
# softmax
outputs = tf.nn.softmax(outputs)
attention = tf.transpose(outputs, [0, 2, 1])
tf.summary.image("attention", tf.expand_dims(attention[:1], -1))
# query masking
outputs = mask(outputs, Q, K, type="query")
# dropout
outputs = tf.layers.dropout(outputs, rate=dropout_rate, training=training)
# weighted sum (context vectors)
outputs = tf.matmul(outputs, V) # (N, T_q, d_v)
return outputs
def multihead_attention(queries, keys, values,
num_heads=4, dropout_rate=0.,
training=True,
causality=False,
scope="mha"):
'''Applies multihead attention. See 3.2.2
queries: A 3d tensor with shape of [N, T_q, d_model].
keys: A 3d tensor with shape of [N, T_k, d_model].
values: A 3d tensor with shape of [N, T_k, d_model].
num_heads: An int. Number of heads.
training: Boolean. Controller of mechanism for dropout.
causality: Boolean. If true, units that reference the future are masked.
scope: Optional scope for `variable_scope`.
Returns
A 3d tensor with shape of (N, T_q, C)
'''
d_model = queries.get_shape().as_list()[-1]
with tf.variable_scope(scope, reuse=tf.AUTO_REUSE):
# Linear projections
Q = tf.layers.dense(queries, d_model, use_bias=False) # (N, T_q, d_model)
K = tf.layers.dense(keys, d_model, use_bias=False) # (N, T_k, d_model)
V = tf.layers.dense(values, d_model, use_bias=False) # (N, T_k, d_model)
# Split and concat
Q_ = tf.concat(tf.split(Q, num_heads, axis=2), axis=0) # (h*N, T_q, d_model/h)
K_ = tf.concat(tf.split(K, num_heads, axis=2), axis=0) # (h*N, T_k, d_model/h)
V_ = tf.concat(tf.split(V, num_heads, axis=2), axis=0) # (h*N, T_k, d_model/h)
# Attention
outputs = scaled_dot_product_attention(Q_, K_, V_, causality, dropout_rate, training)
# Restore shape
outputs = tf.concat(tf.split(outputs, num_heads, axis=0), axis=2) # (N, T_q, d_model)
# Residual connection
outputs += queries
# Normalize
outputs = layer_norm(outputs)
return outputs
def feed_forward(inputs, num_units, activation, scope="positionwise_feedforward"):
'''position-wise feed forward net. See 3.3
inputs: A 3d tensor with shape of [N, T, C].
num_units: A list of two integers.
scope: Optional scope for `variable_scope`.
Returns:
A 3d tensor with the same shape and dtype as inputs
'''
with tf.variable_scope(scope, reuse=tf.AUTO_REUSE):
# Inner layer
outputs = tf.layers.dense(inputs, num_units[0], activation=activation)
# Outer layer
outputs = tf.layers.dense(outputs, num_units[1])
# Residual connection
outputs += inputs
# Normalize
outputs = layer_norm(outputs)
return outputs