File size: 10,280 Bytes
5827423
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
from typing import Optional

import torch
from torch import nn
from torch.nn.utils import weight_norm

from inspiremusic.wavtokenizer.decoder.modules import ConvNeXtBlock, ResBlock1, AdaLayerNorm


def nonlinearity(x):
    # swish
    return x * torch.sigmoid(x)


def Normalize(in_channels, num_groups=32):
    return torch.nn.GroupNorm(num_groups=num_groups, num_channels=in_channels, eps=1e-6, affine=True)


class ResnetBlock(nn.Module):
    def __init__(self, *, in_channels, out_channels=None, conv_shortcut=False,
                 dropout, temb_channels=512):
        super().__init__()
        self.in_channels = in_channels
        out_channels = in_channels if out_channels is None else out_channels
        self.out_channels = out_channels
        self.use_conv_shortcut = conv_shortcut

        self.norm1 = Normalize(in_channels)
        self.conv1 = torch.nn.Conv1d(in_channels,
                                     out_channels,
                                     kernel_size=3,
                                     stride=1,
                                     padding=1)
        if temb_channels > 0:
            self.temb_proj = torch.nn.Linear(temb_channels,
                                             out_channels)
        self.norm2 = Normalize(out_channels)
        self.dropout = torch.nn.Dropout(dropout)
        self.conv2 = torch.nn.Conv1d(out_channels,
                                     out_channels,
                                     kernel_size=3,
                                     stride=1,
                                     padding=1)
        if self.in_channels != self.out_channels:
            if self.use_conv_shortcut:
                self.conv_shortcut = torch.nn.Conv1d(in_channels,
                                                     out_channels,
                                                     kernel_size=3,
                                                     stride=1,
                                                     padding=1)
            else:
                self.nin_shortcut = torch.nn.Conv1d(in_channels,
                                                    out_channels,
                                                    kernel_size=1,
                                                    stride=1,
                                                    padding=0)

    def forward(self, x, temb=None):            
        h = x
        h = self.norm1(h)
        h = nonlinearity(h)
        h = self.conv1(h)

        if temb is not None:
            h = h + self.temb_proj(nonlinearity(temb))[:, :, None, None]

        h = self.norm2(h)
        h = nonlinearity(h)
        h = self.dropout(h)
        h = self.conv2(h)

        if self.in_channels != self.out_channels:
            if self.use_conv_shortcut:
                x = self.conv_shortcut(x)
            else:
                x = self.nin_shortcut(x)

        return x + h

class AttnBlock(nn.Module):
    def __init__(self, in_channels):
        super().__init__()
        self.in_channels = in_channels

        self.norm = Normalize(in_channels)
        self.q = torch.nn.Conv1d(in_channels,
                                 in_channels,
                                 kernel_size=1,
                                 stride=1,
                                 padding=0)
        self.k = torch.nn.Conv1d(in_channels,
                                 in_channels,
                                 kernel_size=1,
                                 stride=1,
                                 padding=0)
        self.v = torch.nn.Conv1d(in_channels,
                                 in_channels,
                                 kernel_size=1,
                                 stride=1,
                                 padding=0)
        self.proj_out = torch.nn.Conv1d(in_channels,
                                        in_channels,
                                        kernel_size=1,
                                        stride=1,
                                        padding=0)

    def forward(self, x):
        h_ = x
        h_ = self.norm(h_)
        q = self.q(h_)
        k = self.k(h_)
        v = self.v(h_)

        # compute attention
        b, c, h = q.shape
        q = q.permute(0, 2, 1)  # b,hw,c
        w_ = torch.bmm(q, k)  # b,hw,hw    w[b,i,j]=sum_c q[b,i,c]k[b,c,j]
        w_ = w_ * (int(c) ** (-0.5))
        w_ = torch.nn.functional.softmax(w_, dim=2)

        # attend to values
        w_ = w_.permute(0, 2, 1)  # b,hw,hw (first hw of k, second of q)
        h_ = torch.bmm(v, w_)  # b, c,hw (hw of q) h_[b,c,j] = sum_i v[b,c,i] w_[b,i,j]

        h_ = self.proj_out(h_)

        return x + h_

def make_attn(in_channels, attn_type="vanilla"):
    assert attn_type in ["vanilla", "linear", "none"], f'attn_type {attn_type} unknown'
    print(f"making attention of type '{attn_type}' with {in_channels} in_channels")
    if attn_type == "vanilla":
        return AttnBlock(in_channels)


class Backbone(nn.Module):
    """Base class for the generator's backbone. It preserves the same temporal resolution across all layers."""

    def forward(self, x: torch.Tensor, **kwargs) -> torch.Tensor:
        """
        Args:
            x (Tensor): Input tensor of shape (B, C, L), where B is the batch size,
                        C denotes output features, and L is the sequence length.

        Returns:
            Tensor: Output of shape (B, L, H), where B is the batch size, L is the sequence length,
                    and H denotes the model dimension.
        """
        raise NotImplementedError("Subclasses must implement the forward method.")


class VocosBackbone(Backbone):
    """
    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`.
        adanorm_num_embeddings (int, optional): Number of embeddings for AdaLayerNorm.
                                                None means non-conditional model. Defaults to None.
    """

    def __init__(
        self,
        input_channels: int,
        dim: int,
        intermediate_dim: int,
        num_layers: int,
        layer_scale_init_value: Optional[float] = None,
        adanorm_num_embeddings: Optional[int] = None,
    ):
        super().__init__()
        self.input_channels = input_channels
        self.embed = nn.Conv1d(input_channels, dim, kernel_size=7, padding=3)
        self.adanorm = adanorm_num_embeddings is not None
        if adanorm_num_embeddings:
            self.norm = AdaLayerNorm(adanorm_num_embeddings, dim, eps=1e-6)
        else:
            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,
                    adanorm_num_embeddings=adanorm_num_embeddings,
                )
                for _ in range(num_layers)
            ]
        )
        self.final_layer_norm = nn.LayerNorm(dim, eps=1e-6)
        self.apply(self._init_weights)

        self.temb_ch = 0
        block_in = dim
        dropout = 0.1
        attn_type="vanilla"

        pos_net : tp.List[nn.Module] = [
            ResnetBlock(in_channels=block_in,out_channels=block_in,
                        temb_channels=self.temb_ch,dropout=dropout),
            ResnetBlock(in_channels=block_in,out_channels=block_in,
                        temb_channels=self.temb_ch,dropout=dropout),
            make_attn(block_in, attn_type=attn_type),
            ResnetBlock(in_channels=block_in,out_channels=block_in,
                    temb_channels=self.temb_ch,dropout=dropout),
            ResnetBlock(in_channels=block_in,out_channels=block_in,
                        temb_channels=self.temb_ch,dropout=dropout),
            Normalize(block_in)
        ]

        self.pos_net = nn.Sequential(*pos_net)

    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, bandwidth_id: Optional[torch.Tensor] = None) -> torch.Tensor:
        x = self.embed(x)
        x = self.pos_net(x)
        if self.adanorm:
            # assert bandwidth_id is not None
            if bandwidth_id is None:
                bandwidth_id = torch.tensor(0, device='cuda')
            x = self.norm(x.transpose(1, 2), cond_embedding_id=bandwidth_id)
        else:
            x = self.norm(x.transpose(1, 2))
        x = x.transpose(1, 2)
        for conv_block in self.convnext:
            x = conv_block(x, cond_embedding_id=bandwidth_id)
        x = self.final_layer_norm(x.transpose(1, 2))
        return x


class VocosResNetBackbone(Backbone):
    """
    Vocos backbone module built with ResBlocks.

    Args:
        input_channels (int): Number of input features channels.
        dim (int): Hidden dimension of the model.
        num_blocks (int): Number of ResBlock1 blocks.
        layer_scale_init_value (float, optional): Initial value for layer scaling. Defaults to None.
    """

    def __init__(
        self, input_channels, dim, num_blocks, layer_scale_init_value=None,
    ):
        super().__init__()
        self.input_channels = input_channels
        self.embed = weight_norm(nn.Conv1d(input_channels, dim, kernel_size=3, padding=1))
        layer_scale_init_value = layer_scale_init_value or 1 / num_blocks / 3
        self.resnet = nn.Sequential(
            *[ResBlock1(dim=dim, layer_scale_init_value=layer_scale_init_value) for _ in range(num_blocks)]
        )

    def forward(self, x: torch.Tensor, **kwargs) -> torch.Tensor:
        x = self.embed(x)
        x = self.resnet(x)
        x = x.transpose(1, 2)
        return x