File size: 2,298 Bytes
8a06b33 | 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 | import torch
from typing import 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 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], device=x.device) * ids_str_max).to(dtype=torch.long)
ret = slice_segments(x, ids_str, segment_size, dim=3)
return ret, ids_str
@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 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 grad_norm(parameters, norm_type: float = 2.0):
if isinstance(parameters, torch.Tensor):
parameters = [parameters]
parameters = [p for p in parameters if p.grad is not None]
if not parameters:
return 0.0
return torch.linalg.vector_norm(
torch.stack([p.grad.norm(norm_type) for p in parameters]), ord=norm_type
).item()
|