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
| '''
with tf.variable_scope(scope, reuse=reuse):
lookup_table = tf.get_variable('lookup_table',
dtype=tf.float32,
shape=[vocab_size, num_units],
initializer=tf.contrib.layers.xavier_initializer())
if zero_pad:
lookup_table = tf.concat((tf.zeros(shape=[1, num_units]),lookup_table[1:, :]), 0)
outputs = tf.nn.embedding_lookup(lookup_table, inputs)
if scale:
outputs = outputs * (num_units ** 0.5)
return outputs
def positional_encoding(inputs,
num_units,
zero_pad=True,
scale=True,
scope="positional_encoding",
reuse=None):
'''Sinusoidal Positional_Encoding.
Args:
inputs: A 2d Tensor with shape of (N, T).
num_units: Output dimensionality
zero_pad: Boolean. If True, all the values of the first row (id = 0) should be constant zero
scale: Boolean. If True, the output will be multiplied by sqrt num_units(check details from paper)
scope: Optional scope for `variable_scope`.
reuse: Boolean, whether to reuse the weights of a previous layer
by the same name.
Returns:
A 'Tensor' with one more rank than inputs's, with the dimensionality should be 'num_units'
'''
N, T = inputs.get_shape().as_list()
with tf.variable_scope(scope, reuse=reuse):
position_ind = tf.tile(tf.expand_dims(tf.range(T), 0), [N, 1])
# First part of the PE function: sin and cos argument
position_enc = np.array([
[pos / np.power(10000, 2.*i/num_units) for i in range(num_units)]
for pos in range(T)])
# Second part, apply the cosine to even columns and sin to odds.
position_enc[:, 0::2] = np.sin(position_enc[:, 0::2]) # dim 2i
position_enc[:, 1::2] = np.cos(position_enc[:, 1::2]) # dim 2i+1
# Convert to a tensor
lookup_table = tf.convert_to_tensor(position_enc)
if zero_pad:
lookup_table = tf.concat((tf.zeros(shape=[1, num_units]),
lookup_table[1:, :]), 0)
outputs = tf.nn.embedding_lookup(lookup_table, position_ind)
if scale:
outputs = outputs * num_units**0.5
return outputs
def multihead_attention(queries,
keys,
num_units=None,
num_heads=8,
dropout_rate=0,
is_training=True,
causality=False,
scope="multihead_attention",
reuse=None):
'''Applies multihead attention.
Args:
queries: A 3d tensor with shape of [N, T_q, C_q].
keys: A 3d tensor with shape of [N, T_k, C_k].
num_units: A scalar. Attention size.
dropout_rate: A floating point number.
is_training: Boolean. Controller of mechanism for dropout.
causality: Boolean. If true, units that reference the future are masked.
num_heads: An int. Number of heads.
scope: Optional scope for `variable_scope`.
reuse: Boolean, whether to reuse the weights of a previous layer
by the same name.
Returns
A 3d tensor with shape of (N, T_q, C)
'''
with tf.variable_scope(scope, reuse=reuse):
# Set the fall back option for num_units
if num_units is None:
num_units = queries.get_shape().as_list()[-1]
# Linear projections
Q = tf.layers.dense(queries, num_units, activation=tf.nn.relu) # (N, T_q, C)
K = tf.layers.dense(keys, num_units, activation=tf.nn.relu) # (N, T_k, C)
V = tf.layers.dense(keys, num_units, activation=tf.nn.relu) # (N, T_k, C)
# Split and concat
Q_ = tf.concat(tf.split(Q, num_heads, axis=2), axis=0) # (h*N, T_q, C/h)
K_ = tf.concat(tf.split(K, num_heads, axis=2), axis=0) # (h*N, T_k, C/h)
V_ = tf.concat(tf.split(V, num_heads, axis=2), axis=0) # (h*N, T_k, C/h)
# Multiplication
outputs = tf.matmul(Q_, tf.transpose(K_, [0, 2, 1])) # (h*N, T_q, T_k)
# Scale
outputs = outputs / (K_.get_shape().as_list()[-1] ** 0.5)
# Key Masking
key_masks = tf.sign(tf.reduce_sum(tf.abs(keys), axis=-1)) # (N, T_k)
key_masks = tf.tile(key_masks, [num_heads, 1]) # (h*N, T_k)
key_masks = tf.tile(tf.expand_dims(key_masks, 1), [1, tf.shape(queries)[1], 1]) # (h*N, T_q, T_k)
paddings = tf.ones_like(outputs)*(-2**32+1)
outputs = tf.where(tf.equal(key_masks, 0), paddings, outputs) # (h*N, T_q, T_k)
# Causality = Future blinding
if causality:
diag_vals = tf.ones_like(outputs[0, :, :]) # (T_q, T_k)
tril = tf.linalg.LinearOperatorLowerTriangular(diag_vals).to_dense() # (T_q, T_k)
masks = tf.tile(tf.expand_dims(tril, 0), [tf.shape(outputs)[0], 1, 1]) # (h*N, T_q, T_k)
paddings = tf.ones_like(masks)*(-2**32+1)
outputs = tf.where(tf.equal(masks, 0), paddings, outputs) # (h*N, T_q, T_k)
# Activation
outputs = tf.nn.softmax(outputs) # (h*N, T_q, T_k)
# Query Masking
query_masks = tf.sign(tf.reduce_sum(tf.abs(queries), axis=-1)) # (N, T_q)
query_masks = tf.tile(query_masks, [num_heads, 1]) # (h*N, T_q)
query_masks = tf.tile(tf.expand_dims(query_masks, -1), [1, 1, tf.shape(keys)[1]]) # (h*N, T_q, T_k)
outputs *= query_masks # broadcasting. (N, T_q, C)
# Dropouts
outputs = tf.layers.dropout(outputs, rate=dropout_rate, training=tf.convert_to_tensor(is_training))
# Weighted sum
outputs = tf.matmul(outputs, V_) # ( h*N, T_q, C/h)
# Restore shape
outputs = tf.concat(tf.split(outputs, num_heads, axis=0), axis=2 ) # (N, T_q, C)
# Residual connection
outputs += queries
# Normalize
outputs = normalize(outputs) # (N, T_q, C)
return outputs
def feedforward(inputs,
num_units=[2048, 512],
scope="multihead_attention",
reuse=None):
'''Point-wise feed forward net.
Args:
inputs: A 3d tensor with shape of [N, T, C].
num_units: A list of two integers.
scope: Optional scope for `variable_scope`.
reuse: Boolean, whether to reuse the weights of a previous layer
by the same name.
Returns:
A 3d tensor with the same shape and dtype as inputs
'''
with tf.variable_scope(scope, reuse=reuse):
# Inner layer
params = {"inputs": inputs, "filters": num_units[0], "kernel_size": 1,"activation": tf.nn.relu, "use_bias": True}
outputs = tf.layers.conv1d(**params)
# Readout layer
params = {"inputs": outputs, "filters": num_units[1], "kernel_size": 1,"activation": None, "use_bias": True}
outputs = tf.layers.conv1d(**params)
# Residual connection
outputs += inputs
# Normalize
outputs = normalize(outputs)
return outputs
def label_smoothing(inputs, epsilon=0.1):
'''Applies label smoothing. See https://arxiv.org/abs/1512.00567.
Args:
inputs: A 3d tensor with shape of [N, T, V], where V is the number of vocabulary.
epsilon: Smoothing rate.
For example,
|
