File size: 3,207 Bytes
6be1ab7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
from torch import nn
from torch.nn import functional as F

from .conv import Conv2d

class SyncNet_color(nn.Module):
    def __init__(self):
        super(SyncNet_color, self).__init__()

        self.face_encoder = nn.Sequential(
            Conv2d(15, 32, kernel_size=(7, 7), stride=1, padding=3),

            Conv2d(32, 64, kernel_size=5, stride=(1, 2), padding=1),
            Conv2d(64, 64, kernel_size=3, stride=1, padding=1, residual=True),
            Conv2d(64, 64, kernel_size=3, stride=1, padding=1, residual=True),

            Conv2d(64, 128, kernel_size=3, stride=2, padding=1),
            Conv2d(128, 128, kernel_size=3, stride=1, padding=1, residual=True),
            Conv2d(128, 128, kernel_size=3, stride=1, padding=1, residual=True),
            Conv2d(128, 128, kernel_size=3, stride=1, padding=1, residual=True),

            Conv2d(128, 256, kernel_size=3, stride=2, padding=1),
            Conv2d(256, 256, kernel_size=3, stride=1, padding=1, residual=True),
            Conv2d(256, 256, kernel_size=3, stride=1, padding=1, residual=True),

            Conv2d(256, 512, kernel_size=3, stride=2, padding=1),
            Conv2d(512, 512, kernel_size=3, stride=1, padding=1, residual=True),
            Conv2d(512, 512, kernel_size=3, stride=1, padding=1, residual=True),

            Conv2d(512, 512, kernel_size=3, stride=2, padding=1),
            Conv2d(512, 512, kernel_size=3, stride=1, padding=0),
            Conv2d(512, 512, kernel_size=1, stride=1, padding=0),)

        self.audio_encoder = nn.Sequential(
            Conv2d(1, 32, kernel_size=3, stride=1, padding=1),
            Conv2d(32, 32, kernel_size=3, stride=1, padding=1, residual=True),
            Conv2d(32, 32, kernel_size=3, stride=1, padding=1, residual=True),

            Conv2d(32, 64, kernel_size=3, stride=(3, 1), padding=1),
            Conv2d(64, 64, kernel_size=3, stride=1, padding=1, residual=True),
            Conv2d(64, 64, kernel_size=3, stride=1, padding=1, residual=True),

            Conv2d(64, 128, kernel_size=3, stride=3, padding=1),
            Conv2d(128, 128, kernel_size=3, stride=1, padding=1, residual=True),
            Conv2d(128, 128, kernel_size=3, stride=1, padding=1, residual=True),

            Conv2d(128, 256, kernel_size=3, stride=(3, 2), padding=1),
            Conv2d(256, 256, kernel_size=3, stride=1, padding=1, residual=True),
            Conv2d(256, 256, kernel_size=3, stride=1, padding=1, residual=True),

            Conv2d(256, 512, kernel_size=3, stride=1, padding=0),
            Conv2d(512, 512, kernel_size=1, stride=1, padding=0),)

    def forward(self, audio_sequences, face_sequences): # audio_sequences := (B, dim, T)
        face_embedding = self.face_encoder(face_sequences)
        audio_embedding = self.audio_encoder(audio_sequences)

        audio_embedding = audio_embedding.view(audio_embedding.size(0), -1)
        face_embedding = face_embedding.view(face_embedding.size(0), -1)

        audio_embedding = F.normalize(audio_embedding, p=2, dim=1)
        face_embedding = F.normalize(face_embedding, p=2, dim=1)


        return audio_embedding, face_embedding