Spaces:
Runtime error
Runtime error
File size: 4,324 Bytes
056ab49 |
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 |
import torch
import torch.nn as nn
from torch.nn import functional as F
from helperVAE import VAE_AttentionBlock, VAE_ResidualBlock
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 |