-
Notifications
You must be signed in to change notification settings - Fork 2
/
module.py
187 lines (140 loc) · 8.78 KB
/
module.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
import tensorflow as tf
def gated_linear_layer(inputs, gates, name = None):
activation = tf.multiply(x = inputs, y = tf.sigmoid(gates), name = name)
return activation
def instance_norm_layer(
inputs,
epsilon = 1e-06,
activation_fn = None,
name = None):
instance_norm_layer = tf.contrib.layers.instance_norm(
inputs = inputs,
epsilon = epsilon,
activation_fn = activation_fn)
return instance_norm_layer
def conv1d_layer(
inputs,
filters,
kernel_size,
strides = 1,
padding = 'same',
activation = None,
kernel_initializer = None,
name = None):
conv_layer = tf.layers.conv1d(
inputs = inputs,
filters = filters,
kernel_size = kernel_size,
strides = strides,
padding = padding,
activation = activation,
kernel_initializer = kernel_initializer,
name = name)
return conv_layer
def residual1d_block(
inputs,
filters = 1024,
kernel_size = 3,
strides = 1,
name_prefix = 'residule_block_'):
h1 = conv1d_layer(inputs = inputs, filters = filters, kernel_size = kernel_size, strides = strides, activation = None, name = name_prefix + 'h1_conv')
h1_norm = instance_norm_layer(inputs = h1, activation_fn = None, name = name_prefix + 'h1_norm')
h1_gates = conv1d_layer(inputs = inputs, filters = filters, kernel_size = kernel_size, strides = strides, activation = None, name = name_prefix + 'h1_gates')
h1_norm_gates = instance_norm_layer(inputs = h1_gates, activation_fn = None, name = name_prefix + 'h1_norm_gates')
h1_glu = gated_linear_layer(inputs = h1_norm, gates = h1_norm_gates, name = name_prefix + 'h1_glu')
h2 = conv1d_layer(inputs = h1_glu, filters = filters // 2, kernel_size = kernel_size, strides = strides, activation = None, name = name_prefix + 'h2_conv')
h2_norm = instance_norm_layer(inputs = h2, activation_fn = None, name = name_prefix + 'h2_norm')
h3 = inputs + h2_norm
return h3
def downsample1d_block(
inputs,
filters,
kernel_size,
strides,
name_prefix = 'downsample1d_block_'):
h1 = conv1d_layer(inputs = inputs, filters = filters, kernel_size = kernel_size, strides = strides, activation = None, name = name_prefix + 'h1_conv')
h1_norm = instance_norm_layer(inputs = h1, activation_fn = None, name = name_prefix + 'h1_norm')
h1_gates = conv1d_layer(inputs = inputs, filters = filters, kernel_size = kernel_size, strides = strides, activation = None, name = name_prefix + 'h1_gates')
h1_norm_gates = instance_norm_layer(inputs = h1_gates, activation_fn = None, name = name_prefix + 'h1_norm_gates')
h1_glu = gated_linear_layer(inputs = h1_norm, gates = h1_norm_gates, name = name_prefix + 'h1_glu')
return h1_glu
def upsample1d_block(
inputs,
filters,
kernel_size,
strides,
shuffle_size = 2 ,
name_prefix = 'upsample1d_block_'):
h1 = conv1d_layer(inputs = inputs, filters = filters, kernel_size = kernel_size, strides = strides, activation = None, name = name_prefix + 'h1_conv')
h1_shuffle = pixel_shuffler(inputs = h1, shuffle_size = shuffle_size, name = name_prefix + 'h1_shuffle')
h1_norm = instance_norm_layer(inputs = h1_shuffle, activation_fn = None, name = name_prefix + 'h1_norm')
h1_gates = conv1d_layer(inputs = inputs, filters = filters, kernel_size = kernel_size, strides = strides, activation = None, name = name_prefix + 'h1_gates')
h1_shuffle_gates = pixel_shuffler(inputs = h1_gates, shuffle_size = shuffle_size, name = name_prefix + 'h1_shuffle_gates')
h1_norm_gates = instance_norm_layer(inputs = h1_shuffle_gates, activation_fn = None, name = name_prefix + 'h1_norm_gates')
h1_glu = gated_linear_layer(inputs = h1_norm, gates = h1_norm_gates, name = name_prefix + 'h1_glu')
return h1_glu
def pixel_shuffler(inputs, shuffle_size = 2, name = None):
if shuffle_size == 2:
n = tf.shape(inputs)[0]
w = tf.shape(inputs)[1]
c = inputs.get_shape().as_list()[2]
oc = c // shuffle_size
ow = w * shuffle_size
outputs = tf.reshape(tensor = inputs, shape = [n, ow, oc], name = name)
else:
outputs = inputs
return outputs
def generator_gatedcnn(inputs, reuse = False, scope_name = 'generator_gatedcnn'):
# inputs has shape [batch_size, num_features, time]
# we need to convert it to [batch_size, time, num_features] for 1D convolution
inputs = tf.transpose(inputs, perm = [0, 2, 1], name = 'input_transpose')
with tf.variable_scope(scope_name) as scope:
# Discriminator would be reused in CycleGAN
if reuse:
scope.reuse_variables()
else:
assert scope.reuse is False
#[batch_size, num_features, time] 1, 24, 128
h1 = conv1d_layer(inputs = inputs, filters = 128, kernel_size = 15, strides = 1, activation = None, name = 'h1_conv')
h1_gates = conv1d_layer(inputs = inputs, filters = 128, kernel_size = 15, strides = 1, activation = None, name = 'h1_conv_gates')
h1_glu = gated_linear_layer(inputs = h1, gates = h1_gates, name = 'h1_glu')
# Downsample
d1 = downsample1d_block(inputs = h1_glu, filters = 256, kernel_size = 5, strides = 2, name_prefix = 'downsample1d_block1_')
d2 = downsample1d_block(inputs = d1, filters = 512, kernel_size = 5, strides = 2, name_prefix = 'downsample1d_block2_')
# Residual blocks
r1 = residual1d_block(inputs = d2, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block1_')
r2 = residual1d_block(inputs = r1, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block2_')
r3 = residual1d_block(inputs = r2, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block3_')
r4 = residual1d_block(inputs = r3, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block4_')
r5 = residual1d_block(inputs = r4, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block5_')
r6 = residual1d_block(inputs = r5, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block6_')
# Upsample
u1 = upsample1d_block(inputs = r6, filters = 1024, kernel_size = 5, strides = 1, shuffle_size = 2, name_prefix = 'upsample1d_block1_')
u2 = upsample1d_block(inputs = u1, filters = 512, kernel_size = 5, strides = 1, shuffle_size = 2, name_prefix = 'upsample1d_block2_')
# Output
o1 = conv1d_layer(inputs = u2, filters = 24, kernel_size = 15, strides = 1, activation = None, name = 'o1_conv')
o2 = tf.transpose(o1, perm = [0, 2, 1], name = 'output_transpose')
return o2
def discriminator(inputs, reuse = False, scope_name = 'discriminator'):
inputs = tf.transpose(inputs, perm = [0, 2, 1], name = 'input_transpose_dic')
with tf.variable_scope(scope_name) as scope:
if reuse:
scope.reuse_variables()
else:
assert scope.reuse is False
h1 = conv1d_layer(inputs = inputs, filters = 128, kernel_size = 15, strides = 1, activation = None, name = 'h1_conv')
h1_gates = conv1d_layer(inputs = inputs, filters = 128, kernel_size = 15, strides = 1, activation = None, name = 'h1_conv_gates')
h1_glu = gated_linear_layer(inputs = h1, gates = h1_gates, name = 'h1_glu')
d1 = downsample1d_block(inputs = h1_glu, filters = 256, kernel_size = 5, strides = 2, name_prefix = 'downsample1d_block1_')
d2 = downsample1d_block(inputs = d1, filters = 512, kernel_size = 5, strides = 2, name_prefix = 'downsample1d_block2_')
r1 = residual1d_block(inputs = d2, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block1_')
r2 = residual1d_block(inputs = r1, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block2_')
r3 = residual1d_block(inputs = r2, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block3_')
r4 = residual1d_block(inputs = r3, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block4_')
r5 = residual1d_block(inputs = r4, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block5_')
r6 = residual1d_block(inputs = r5, filters = 1024, kernel_size = 3, strides = 1, name_prefix = 'residual1d_block6_')
u1 = upsample1d_block(inputs = r6, filters = 1024, kernel_size = 5, strides = 1, shuffle_size = 2, name_prefix = 'upsample1d_block1_')
u2 = upsample1d_block(inputs = u1, filters = 512, kernel_size = 5, strides = 1, shuffle_size = 2, name_prefix = 'upsample1d_block2_')
o1 = conv1d_layer(inputs = u2, filters = 24, kernel_size = 15, strides = 1, activation = None, name = 'o1_conv')
o2 = tf.transpose(o1, perm = [0, 2, 1], name = 'output_transpose')
return o2