File size: 3,539 Bytes
98bb602 |
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 |
import math
import torch
from typing import List, Optional
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):
l = pad_shape[::-1]
pad_shape = [item for sublist in l for item in sublist]
return pad_shape
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 slice_segments(x: torch.Tensor, ids_str: torch.Tensor, segment_size: int = 4, dim: int = 2):
if dim == 2: ret = torch.zeros_like(x[:, :segment_size])
elif dim == 3: ret = torch.zeros_like(x[:, :, :segment_size])
for i in range(x.size(0)):
idx_str = ids_str[i].item()
idx_end = idx_str + segment_size
if dim == 2: ret[i] = x[i, idx_str:idx_end]
else: ret[i] = x[i, :, idx_str:idx_end]
return ret
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 = x_lengths - segment_size + 1
ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
ret = slice_segments(x, ids_str, segment_size, dim=3)
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 = torch.nn.functional.pad(signal, [0, 0, 0, channels % 2])
signal = signal.view(1, channels, length)
return signal
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 convert_pad_shape(pad_shape: List[List[int]]) -> List[int]:
return torch.tensor(pad_shape).flip(0).reshape(-1).int().tolist()
def sequence_mask(length: torch.Tensor, max_length: Optional[int] = 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 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 |