File size: 4,796 Bytes
8dfbf56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import math
import torch
from torch.nn import functional as F


def init_weights(m, mean=0.0, std=0.01):
    classname = m.__class__.__name__
    if classname.find("Conv") != -1:
        m.weight.data.normal_(mean, std)


def get_padding(kernel_size, dilation=1):
    return int((kernel_size * dilation - dilation) / 2)


def convert_pad_shape(pad_shape):
    layer = pad_shape[::-1]
    pad_shape = [item for sublist in layer for item in sublist]
    return pad_shape


def intersperse(lst, item):
    result = [item] * (len(lst) * 2 + 1)
    result[1::2] = lst
    return result


def kl_divergence(m_p, logs_p, m_q, logs_q):
    """KL(P||Q)"""
    kl = (logs_q - logs_p) - 0.5
    kl += (
        0.5 * (torch.exp(2.0 * logs_p) + ((m_p - m_q) ** 2)) * torch.exp(-2.0 * logs_q)
    )
    return kl


def rand_gumbel(shape):
    """Sample from the Gumbel distribution, protect from overflows."""
    uniform_samples = torch.rand(shape) * 0.99998 + 0.00001
    return -torch.log(-torch.log(uniform_samples))


def rand_gumbel_like(x):
    g = rand_gumbel(x.size()).to(dtype=x.dtype, device=x.device)
    return g


def slice_segments(x, ids_str, segment_size=4):
    gather_indices = ids_str.view(x.size(0), 1, 1).repeat(
        1, x.size(1), 1
    ) + torch.arange(segment_size, device=x.device)
    return torch.gather(x, 2, gather_indices)


def rand_slice_segments(x, x_lengths=None, segment_size=4):
    b, d, t = x.size()
    if x_lengths is None:
        x_lengths = t
    ids_str_max = torch.clamp(x_lengths - segment_size + 1, min=0)
    ids_str = (torch.rand([b], device=x.device) * ids_str_max).to(dtype=torch.long)
    ret = slice_segments(x, ids_str, segment_size)
    return ret, ids_str


def get_timing_signal_1d(length, channels, min_timescale=1.0, max_timescale=1.0e4):
    position = torch.arange(length, dtype=torch.float)
    num_timescales = channels // 2
    log_timescale_increment = math.log(float(max_timescale) / float(min_timescale)) / (
        num_timescales - 1
    )
    inv_timescales = min_timescale * torch.exp(
        torch.arange(num_timescales, dtype=torch.float) * -log_timescale_increment
    )
    scaled_time = position.unsqueeze(0) * inv_timescales.unsqueeze(1)
    signal = torch.cat([torch.sin(scaled_time), torch.cos(scaled_time)], 0)
    signal = F.pad(signal, [0, 0, 0, channels % 2])
    signal = signal.view(1, channels, length)
    return signal


def add_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4):
    b, channels, length = x.size()
    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
    return x + signal.to(dtype=x.dtype, device=x.device)


def cat_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4, axis=1):
    b, channels, length = x.size()
    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
    return torch.cat([x, signal.to(dtype=x.dtype, device=x.device)], axis)


def subsequent_mask(length):
    mask = torch.tril(torch.ones(length, length)).unsqueeze(0).unsqueeze(0)
    return mask


@torch.jit.script
def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
    n_channels_int = n_channels[0]
    in_act = input_a + input_b
    t_act = torch.tanh(in_act[:, :n_channels_int, :])
    s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
    acts = t_act * s_act
    return acts


def shift_1d(x):
    x = F.pad(x, convert_pad_shape([[0, 0], [0, 0], [1, 0]]))[:, :, :-1]
    return x


def sequence_mask(length, max_length=None):
    if max_length is None:
        max_length = length.max()
    x = torch.arange(max_length, dtype=length.dtype, device=length.device)
    return x.unsqueeze(0) < length.unsqueeze(1)


def generate_path(duration, mask):
    """
    duration: [b, 1, t_x]
    mask: [b, 1, t_y, t_x]
    """

    b, _, t_y, t_x = mask.shape
    cum_duration = torch.cumsum(duration, -1)

    cum_duration_flat = cum_duration.view(b * t_x)
    path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype)
    path = path.view(b, t_x, t_y)
    path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1]
    path = path.unsqueeze(1).transpose(2, 3) * mask
    return path


def clip_grad_value_(parameters, clip_value, norm_type=2):
    if isinstance(parameters, torch.Tensor):
        parameters = [parameters]
    parameters = list(filter(lambda p: p.grad is not None, parameters))
    norm_type = float(norm_type)
    if clip_value is not None:
        clip_value = float(clip_value)

    total_norm = 0
    for p in parameters:
        param_norm = p.grad.data.norm(norm_type)
        total_norm += param_norm.item() ** norm_type
        if clip_value is not None:
            p.grad.data.clamp_(min=-clip_value, max=clip_value)
    total_norm = total_norm ** (1.0 / norm_type)
    return total_norm