File size: 2,775 Bytes
a92fb7a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
import torch.nn as nn

class DoubleConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        """
        This module applies two consecutive convolutional layers to the input.
        
        Args:
            in_channels (int): Number of input channels.
            out_channels (int): Number of output channels.
        """
        super(DoubleConv, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.LeakyReLU(0.2, inplace=True),
        )

    def forward(self, x):
        """Forward pass of the DoubleConv module."""
        x = self.conv(x)
        return x

class UNet(nn.Module):
    def __init__(self, in_channels=3, out_channels=3, features=[64, 128, 256, 512, 1024]):
        """
        Basic U-Net model for image to image
        
        Args:
            in_channels (int, optional): Number of input channels.
            out_channels (int, optional): Number of output channels.
            features (list, optional): List of features for encoding and decoding.
        """
        super(UNet, self).__init__()

        self.ups = nn.ModuleList()
        self.downs = nn.ModuleList()
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)

        # Encoder
        for feature in features:
            self.downs.append(DoubleConv(in_channels, feature))
            in_channels = feature

        # Decoder
        for feature in reversed(features):
            self.ups.append(nn.ConvTranspose2d(feature*2, feature, kernel_size=2, stride=2))
            self.ups.append(DoubleConv(feature*2, feature))
        
        self.bottleneck = DoubleConv(features[-1], features[-1]*2)

        self.final_conv = nn.Conv2d(features[0], out_channels, kernel_size=1)

    def forward(self, x):
        """Forward pass of the U-Net model"""
        skip_connections = []
        for down in self.downs:
            x = down(x)
            skip_connections.append(x)
            x = self.pool(x)

        x = self.bottleneck(x)

        skip_connections = skip_connections[::-1]

        for i in range(0, len(self.ups), 2):
            x = self.ups[i](x)
            skip_connection = skip_connections[i//2]

            if x.shape != skip_connection.shape:
                x = nn.functional.interpolate(x, size=skip_connection.shape[2:], mode='bilinear', align_corners=True)

            concat_skip = torch.cat((skip_connection, x), dim=1)
            x = self.ups[i+1](concat_skip)

        x = self.final_conv(x)

        return x