mirror of
https://github.com/AIGC-Audio/AudioGPT.git
synced 2026-07-10 04:20:09 +02:00
113 lines
3.9 KiB
Python
113 lines
3.9 KiB
Python
import math
|
|
import torch
|
|
|
|
|
|
class PositionalEncoding(torch.nn.Module):
|
|
"""Positional encoding.
|
|
Args:
|
|
d_model (int): Embedding dimension.
|
|
dropout_rate (float): Dropout rate.
|
|
max_len (int): Maximum input length.
|
|
reverse (bool): Whether to reverse the input position.
|
|
"""
|
|
|
|
def __init__(self, d_model, dropout_rate, max_len=5000, reverse=False):
|
|
"""Construct an PositionalEncoding object."""
|
|
super(PositionalEncoding, self).__init__()
|
|
self.d_model = d_model
|
|
self.reverse = reverse
|
|
self.xscale = math.sqrt(self.d_model)
|
|
self.dropout = torch.nn.Dropout(p=dropout_rate)
|
|
self.pe = None
|
|
self.extend_pe(torch.tensor(0.0).expand(1, max_len))
|
|
|
|
def extend_pe(self, x):
|
|
"""Reset the positional encodings."""
|
|
if self.pe is not None:
|
|
if self.pe.size(1) >= x.size(1):
|
|
if self.pe.dtype != x.dtype or self.pe.device != x.device:
|
|
self.pe = self.pe.to(dtype=x.dtype, device=x.device)
|
|
return
|
|
pe = torch.zeros(x.size(1), self.d_model)
|
|
if self.reverse:
|
|
position = torch.arange(
|
|
x.size(1) - 1, -1, -1.0, dtype=torch.float32
|
|
).unsqueeze(1)
|
|
else:
|
|
position = torch.arange(0, x.size(1), dtype=torch.float32).unsqueeze(1)
|
|
div_term = torch.exp(
|
|
torch.arange(0, self.d_model, 2, dtype=torch.float32)
|
|
* -(math.log(10000.0) / self.d_model)
|
|
)
|
|
pe[:, 0::2] = torch.sin(position * div_term)
|
|
pe[:, 1::2] = torch.cos(position * div_term)
|
|
pe = pe.unsqueeze(0)
|
|
self.pe = pe.to(device=x.device, dtype=x.dtype)
|
|
|
|
def forward(self, x: torch.Tensor):
|
|
"""Add positional encoding.
|
|
Args:
|
|
x (torch.Tensor): Input tensor (batch, time, `*`).
|
|
Returns:
|
|
torch.Tensor: Encoded tensor (batch, time, `*`).
|
|
"""
|
|
self.extend_pe(x)
|
|
x = x * self.xscale + self.pe[:, : x.size(1)]
|
|
return self.dropout(x)
|
|
|
|
|
|
class ScaledPositionalEncoding(PositionalEncoding):
|
|
"""Scaled positional encoding module.
|
|
See Sec. 3.2 https://arxiv.org/abs/1809.08895
|
|
Args:
|
|
d_model (int): Embedding dimension.
|
|
dropout_rate (float): Dropout rate.
|
|
max_len (int): Maximum input length.
|
|
"""
|
|
|
|
def __init__(self, d_model, dropout_rate, max_len=5000):
|
|
"""Initialize class."""
|
|
super().__init__(d_model=d_model, dropout_rate=dropout_rate, max_len=max_len)
|
|
self.alpha = torch.nn.Parameter(torch.tensor(1.0))
|
|
|
|
def reset_parameters(self):
|
|
"""Reset parameters."""
|
|
self.alpha.data = torch.tensor(1.0)
|
|
|
|
def forward(self, x):
|
|
"""Add positional encoding.
|
|
Args:
|
|
x (torch.Tensor): Input tensor (batch, time, `*`).
|
|
Returns:
|
|
torch.Tensor: Encoded tensor (batch, time, `*`).
|
|
"""
|
|
self.extend_pe(x)
|
|
x = x + self.alpha * self.pe[:, : x.size(1)]
|
|
return self.dropout(x)
|
|
|
|
|
|
class RelPositionalEncoding(PositionalEncoding):
|
|
"""Relative positional encoding module.
|
|
See : Appendix B in https://arxiv.org/abs/1901.02860
|
|
Args:
|
|
d_model (int): Embedding dimension.
|
|
dropout_rate (float): Dropout rate.
|
|
max_len (int): Maximum input length.
|
|
"""
|
|
|
|
def __init__(self, d_model, dropout_rate, max_len=5000):
|
|
"""Initialize class."""
|
|
super().__init__(d_model, dropout_rate, max_len, reverse=True)
|
|
|
|
def forward(self, x):
|
|
"""Compute positional encoding.
|
|
Args:
|
|
x (torch.Tensor): Input tensor (batch, time, `*`).
|
|
Returns:
|
|
torch.Tensor: Encoded tensor (batch, time, `*`).
|
|
torch.Tensor: Positional embedding tensor (1, time, `*`).
|
|
"""
|
|
self.extend_pe(x)
|
|
x = x * self.xscale
|
|
pos_emb = self.pe[:, : x.size(1)]
|
|
return self.dropout(x) + self.dropout(pos_emb) |