Hugging Face's logo

Spaces:
Esmail-AGumaan
/
nanograd-engine
Runtime error

App Files Community
nanograd-engine
File size: 3,223 Bytes 
898fdaa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64e1ee8
 
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
 
import torch
from torch import nn
from torch.nn import functional as F
from attention import SelfAttention

class VAE_AttentionBlock(nn.Module):
    def __init__(self, channels):
        super().__init__()
        self.groupnorm = nn.GroupNorm(32, channels)
        self.attention = SelfAttention(1, channels)
    
    def forward(self, x):
        residue = x 
        x = self.groupnorm(x)
        n, c, h, w = x.shape
        x = x.view((n, c, h * w))
        x = x.transpose(-1, -2)
        x = self.attention(x)
        x = x.transpose(-1, -2)
        x = x.view((n, c, h, w))
        x += residue

        return x 

class VAE_ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.groupnorm_1 = nn.GroupNorm(32, in_channels)
        self.conv_1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1)

        self.groupnorm_2 = nn.GroupNorm(32, out_channels)
        self.conv_2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1)

        if in_channels == out_channels:
            self.residual_layer = nn.Identity()
        else:
            self.residual_layer = nn.Conv2d(in_channels, out_channels, kernel_size=1, padding=0)
    
    def forward(self, x):
        residue = x
        x = self.groupnorm_1(x)
        x = F.silu(x)
        x = self.conv_1(x)
        x = self.groupnorm_2(x)
        x = F.silu(x)
        x = self.conv_2(x)
        
        return x + self.residual_layer(residue)

class VAE_Decoder(nn.Sequential):
    def __init__(self):
        super().__init__(
            nn.Conv2d(4, 4, kernel_size=1, padding=0),
            nn.Conv2d(4, 512, kernel_size=3, padding=1),
            VAE_ResidualBlock(512, 512), 
            VAE_AttentionBlock(512), 
            VAE_ResidualBlock(512, 512), 
            VAE_ResidualBlock(512, 512), 
            VAE_ResidualBlock(512, 512), 
            VAE_ResidualBlock(512, 512), 
            
            # (Batch_Size, 512, Height / 8, Width / 8) -> (Batch_Size, 512, Height / 4, Width / 4)
            nn.Upsample(scale_factor=2),
            
            nn.Conv2d(512, 512, kernel_size=3, padding=1), 
            
            VAE_ResidualBlock(512, 512), 
            VAE_ResidualBlock(512, 512), 
            VAE_ResidualBlock(512, 512), 
            
            # (Batch_Size, 512, Height / 4, Width / 4) -> (Batch_Size, 512, Height / 2, Width / 2)
            nn.Upsample(scale_factor=2), 
            
            nn.Conv2d(512, 512, kernel_size=3, padding=1), 
            
            VAE_ResidualBlock(512, 256), 
            VAE_ResidualBlock(256, 256), 
            VAE_ResidualBlock(256, 256), 
            
            nn.Upsample(scale_factor=2), 
            
            nn.Conv2d(256, 256, kernel_size=3, padding=1), 
            
            VAE_ResidualBlock(256, 128), 
            VAE_ResidualBlock(128, 128), 
            VAE_ResidualBlock(128, 128), 
            
            nn.GroupNorm(32, 128), 
            
            nn.SiLU(), 
            
            nn.Conv2d(128, 3, kernel_size=3, padding=1), 
        )

    def forward(self, x):
        x /= 0.18215

        for module in self:
            x = module(x)
        return x