Spaces:
Running
Running
File size: 2,003 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 48 49 50 51 52 53 54 55 56 57 |
from typing import Optional
import torch
from torch import nn
from .module import ConvNeXtBlock
class VocosBackbone(nn.Module):
"""
Vocos backbone module built with ConvNeXt blocks. Supports additional conditioning with Adaptive Layer Normalization
Args:
input_channels (int): Number of input features channels.
dim (int): Hidden dimension of the model.
intermediate_dim (int): Intermediate dimension used in ConvNeXtBlock.
num_layers (int): Number of ConvNeXtBlock layers.
layer_scale_init_value (float, optional): Initial value for layer scaling. Defaults to `1 / num_layers`.
"""
def __init__(
self,
input_channels: int,
dim: int,
intermediate_dim: int,
num_layers: int,
layer_scale_init_value: Optional[float] = None,
):
super().__init__()
self.input_channels = input_channels
self.embed = nn.Conv1d(input_channels, dim, kernel_size=7, padding=3)
self.norm = nn.LayerNorm(dim, eps=1e-6)
layer_scale_init_value = layer_scale_init_value or 1 / num_layers
self.convnext = nn.ModuleList(
[
ConvNeXtBlock(
dim=dim,
intermediate_dim=intermediate_dim,
layer_scale_init_value=layer_scale_init_value,
)
for _ in range(num_layers)
]
)
self.final_layer_norm = nn.LayerNorm(dim, eps=1e-6)
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, (nn.Conv1d, nn.Linear)):
nn.init.trunc_normal_(m.weight, std=0.02)
nn.init.constant_(m.bias, 0)
def forward(self, x: torch.Tensor) -> torch.Tensor:
x = self.embed(x)
x = self.norm(x.transpose(1, 2)).transpose(1, 2)
for conv_block in self.convnext:
x = conv_block(x)
x = self.final_layer_norm(x.transpose(1, 2))
return x |