Spaces:
Runtime error
Runtime error
File size: 1,560 Bytes
d358e26 |
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 |
import torch
from torch import nn
class ConvNeXtBlock(nn.Module):
"""ConvNeXt Block adapted from https://github.com/facebookresearch/ConvNeXt to 1D audio signal.
Args:
dim (int): Number of input channels.
intermediate_dim (int): Dimensionality of the intermediate layer.
layer_scale_init_value (float, optional): Initial value for the layer scale. None means no scaling.
Defaults to None.
"""
def __init__(
self,
dim: int,
intermediate_dim: int,
layer_scale_init_value: float,
):
super().__init__()
self.dwconv = nn.Conv1d(dim, dim, kernel_size=7, padding=3, groups=dim) # depthwise conv
self.norm = nn.LayerNorm(dim, eps=1e-6)
self.pwconv1 = nn.Linear(dim, intermediate_dim) # pointwise/1x1 convs, implemented with linear layers
self.act = nn.GELU()
self.pwconv2 = nn.Linear(intermediate_dim, dim)
self.gamma = (
nn.Parameter(layer_scale_init_value * torch.ones(dim), requires_grad=True)
if layer_scale_init_value > 0
else None
)
def forward(self, x: torch.Tensor) -> torch.Tensor:
residual = x
x = self.dwconv(x)
x = x.transpose(1, 2) # (B, C, T) -> (B, T, C)
x = self.norm(x)
x = self.pwconv1(x)
x = self.act(x)
x = self.pwconv2(x)
if self.gamma is not None:
x = self.gamma * x
x = x.transpose(1, 2) # (B, T, C) -> (B, C, T)
x = residual + x
return x
|