Remove obsolete package file tiny_tts/nn/commons.py
This commit is contained in:
Owen Song
system
@@ -1,151 +0,0 @@
|
|||||||
import math
|
|
||||||
import torch
|
|
||||||
from torch.nn import functional as F
|
|
||||||
|
|
||||||
|
|
||||||
def initialize_weights(m, mean=0.0, std=0.01):
|
|
||||||
classname = m.__class__.__name__
|
|
||||||
if classname.find("Conv") != -1:
|
|
||||||
m.weight.data.normal_(mean, std)
|
|
||||||
|
|
||||||
|
|
||||||
def compute_padding(kernel_size, dilation=1):
|
|
||||||
return int((kernel_size * dilation - dilation) / 2)
|
|
||||||
|
|
||||||
|
|
||||||
def flatten_pad_shape(pad_shape):
|
|
||||||
layer = pad_shape[::-1]
|
|
||||||
pad_shape = [item for sublist in layer for item in sublist]
|
|
||||||
return pad_shape
|
|
||||||
|
|
||||||
|
|
||||||
def insert_blanks(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 = (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):
|
|
||||||
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 extract_segments(x, ids_str, segment_size=4):
|
|
||||||
ret = torch.zeros_like(x[:, :, :segment_size])
|
|
||||||
for i in range(x.size(0)):
|
|
||||||
idx_str = max(0, ids_str[i].item())
|
|
||||||
idx_end = idx_str + segment_size
|
|
||||||
available = x.size(2) - idx_str
|
|
||||||
if available >= segment_size:
|
|
||||||
ret[i] = x[i, :, idx_str:idx_end]
|
|
||||||
elif available > 0:
|
|
||||||
ret[i, :, :available] = x[i, :, idx_str:idx_str + available]
|
|
||||||
return ret
|
|
||||||
|
|
||||||
|
|
||||||
def random_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]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
|
|
||||||
ret = extract_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 gated_activation(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, flatten_pad_shape([[0, 0], [0, 0], [1, 0]]))[:, :, :-1]
|
|
||||||
return x
|
|
||||||
|
|
||||||
|
|
||||||
def create_length_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 compute_alignment_path(duration, mask):
|
|
||||||
b, _, t_y, t_x = mask.shape
|
|
||||||
cum_duration = torch.cumsum(duration, -1)
|
|
||||||
|
|
||||||
cum_duration_flat = cum_duration.view(b * t_x)
|
|
||||||
path = create_length_mask(cum_duration_flat, t_y).to(mask.dtype)
|
|
||||||
path = path.view(b, t_x, t_y)
|
|
||||||
path = path - F.pad(path, flatten_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
|
|
||||||
Reference in New Issue
Block a user