File size: 7,643 Bytes
161e2ab |
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 |
import torch
import torch.nn as nn
import torch.nn.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):
# x: (Batch_Size, Features, Height, Width)
residue = x
# (Batch_Size, Features, Height, Width) -> (Batch_Size, Features, Height, Width)
x = self.groupnorm(x)
n, c, h, w = x.shape
# (Batch_Size, Features, Height, Width) -> (Batch_Size, Features, Height * Width)
x = x.view((n, c, h * w))
# (Batch_Size, Features, Height * Width) -> (Batch_Size, Height * Width, Features). Each pixel becomes a feature of size "Features", the sequence length is "Height * Width".
x = x.transpose(-1, -2)
# Perform self-attention WITHOUT mask
# (Batch_Size, Height * Width, Features) -> (Batch_Size, Height * Width, Features)
x = self.attention(x)
# (Batch_Size, Height * Width, Features) -> (Batch_Size, Features, Height * Width)
x = x.transpose(-1, -2)
# (Batch_Size, Features, Height * Width) -> (Batch_Size, Features, Height, Width)
x = x.view((n, c, h, w))
# (Batch_Size, Features, Height, Width) + (Batch_Size, Features, Height, Width) -> (Batch_Size, Features, Height, Width)
x += residue
# (Batch_Size, Features, Height, Width)
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):
# x: (Batch_Size, In_Channels, Height, Width)
residue = x
# (Batch_Size, In_Channels, Height, Width) -> (Batch_Size, In_Channels, Height, Width)
x = self.groupnorm_1(x)
# (Batch_Size, In_Channels, Height, Width) -> (Batch_Size, In_Channels, Height, Width)
x = F.silu(x)
# (Batch_Size, In_Channels, Height, Width) -> (Batch_Size, Out_Channels, Height, Width)
x = self.conv_1(x)
# (Batch_Size, Out_Channels, Height, Width) -> (Batch_Size, Out_Channels, Height, Width)
x = self.groupnorm_2(x)
# (Batch_Size, Out_Channels, Height, Width) -> (Batch_Size, Out_Channels, Height, Width)
x = F.silu(x)
# (Batch_Size, Out_Channels, Height, Width) -> (Batch_Size, Out_Channels, Height, Width)
x = self.conv_2(x)
# (Batch_Size, Out_Channels, Height, Width) -> (Batch_Size, Out_Channels, Height, Width)
return x + self.residual_layer(residue)
class VAE_Decoder(nn.Sequential):
def __init__(self):
super().__init__(
# (Batch_Size, 4, Height / 8, Width / 8) -> (Batch_Size, 4, Height / 8, Width / 8)
nn.Conv2d(4, 4, kernel_size=1, padding=0),
# (Batch_Size, 4, Height / 8, Width / 8) -> (Batch_Size, 512, Height / 8, Width / 8)
nn.Conv2d(4, 512, kernel_size=3, padding=1),
# (Batch_Size, 512, Height / 8, Width / 8) -> (Batch_Size, 512, Height / 8, Width / 8)
VAE_ResidualBlock(512, 512),
# (Batch_Size, 512, Height / 8, Width / 8) -> (Batch_Size, 512, Height / 8, Width / 8)
VAE_AttentionBlock(512),
# (Batch_Size, 512, Height / 8, Width / 8) -> (Batch_Size, 512, Height / 8, Width / 8)
VAE_ResidualBlock(512, 512),
# (Batch_Size, 512, Height / 8, Width / 8) -> (Batch_Size, 512, Height / 8, Width / 8)
VAE_ResidualBlock(512, 512),
# (Batch_Size, 512, Height / 8, Width / 8) -> (Batch_Size, 512, Height / 8, Width / 8)
VAE_ResidualBlock(512, 512),
# (Batch_Size, 512, Height / 8, Width / 8) -> (Batch_Size, 512, Height / 8, Width / 8)
VAE_ResidualBlock(512, 512),
# Repeats the rows and columns of the data by scale_factor (like when you resize an image by doubling its size).
# (Batch_Size, 512, Height / 8, Width / 8) -> (Batch_Size, 512, Height / 4, Width / 4)
nn.Upsample(scale_factor=2),
# (Batch_Size, 512, Height / 4, Width / 4) -> (Batch_Size, 512, Height / 4, Width / 4)
nn.Conv2d(512, 512, kernel_size=3, padding=1),
# (Batch_Size, 512, Height / 4, Width / 4) -> (Batch_Size, 512, Height / 4, Width / 4)
VAE_ResidualBlock(512, 512),
# (Batch_Size, 512, Height / 4, Width / 4) -> (Batch_Size, 512, Height / 4, Width / 4)
VAE_ResidualBlock(512, 512),
# (Batch_Size, 512, Height / 4, Width / 4) -> (Batch_Size, 512, Height / 4, Width / 4)
VAE_ResidualBlock(512, 512),
# (Batch_Size, 512, Height / 4, Width / 4) -> (Batch_Size, 512, Height / 2, Width / 2)
nn.Upsample(scale_factor=2),
# (Batch_Size, 512, Height / 2, Width / 2) -> (Batch_Size, 512, Height / 2, Width / 2)
nn.Conv2d(512, 512, kernel_size=3, padding=1),
# (Batch_Size, 512, Height / 2, Width / 2) -> (Batch_Size, 256, Height / 2, Width / 2)
VAE_ResidualBlock(512, 256),
# (Batch_Size, 256, Height / 2, Width / 2) -> (Batch_Size, 256, Height / 2, Width / 2)
VAE_ResidualBlock(256, 256),
# (Batch_Size, 256, Height / 2, Width / 2) -> (Batch_Size, 256, Height / 2, Width / 2)
VAE_ResidualBlock(256, 256),
# (Batch_Size, 256, Height / 2, Width / 2) -> (Batch_Size, 256, Height, Width)
nn.Upsample(scale_factor=2),
# (Batch_Size, 256, Height, Width) -> (Batch_Size, 256, Height, Width)
nn.Conv2d(256, 256, kernel_size=3, padding=1),
# (Batch_Size, 256, Height, Width) -> (Batch_Size, 128, Height, Width)
VAE_ResidualBlock(256, 128),
# (Batch_Size, 128, Height, Width) -> (Batch_Size, 128, Height, Width)
VAE_ResidualBlock(128, 128),
# (Batch_Size, 128, Height, Width) -> (Batch_Size, 128, Height, Width)
VAE_ResidualBlock(128, 128),
# (Batch_Size, 128, Height, Width) -> (Batch_Size, 128, Height, Width)
nn.GroupNorm(32, 128),
# (Batch_Size, 128, Height, Width) -> (Batch_Size, 128, Height, Width)
nn.SiLU(),
# (Batch_Size, 128, Height, Width) -> (Batch_Size, 3, Height, Width)
nn.Conv2d(128, 3, kernel_size=3, padding=1),
)
def forward(self, x):
# x: (Batch_Size, 4, Height / 8, Width / 8)
# Remove the scaling added by the Encoder.
x /= 0.18215
for module in self:
x = module(x)
# (Batch_Size, 3, Height, Width)
return x |