File size: 2,441 Bytes
dafe852
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
import torch.nn as nn
import torchvision

# VGG architecter, used for the perceptual loss using a pretrained VGG network
class VGG19(torch.nn.Module):
    def __init__(self, requires_grad=False):
        super().__init__()
        vgg_pretrained_features = torchvision.models.vgg19(pretrained=True).features
        self.slice1 = torch.nn.Sequential()
        self.slice2 = torch.nn.Sequential()
        self.slice3 = torch.nn.Sequential()
        self.slice4 = torch.nn.Sequential()
        self.slice5 = torch.nn.Sequential()
        self.slice6 = torch.nn.Sequential()
        for x in range(2):
            self.slice1.add_module(str(x), vgg_pretrained_features[x])
        for x in range(2, 7):
            self.slice2.add_module(str(x), vgg_pretrained_features[x])
        for x in range(7, 12):
            self.slice3.add_module(str(x), vgg_pretrained_features[x])
        for x in range(12, 21):
            self.slice4.add_module(str(x), vgg_pretrained_features[x])
        for x in range(21, 32):
            self.slice5.add_module(str(x), vgg_pretrained_features[x])
        for x in range(32, 36):
            self.slice6.add_module(str(x), vgg_pretrained_features[x])            
        if not requires_grad:
            for param in self.parameters():
                param.requires_grad = False
        
        self.pool = nn.AdaptiveAvgPool2d(output_size=1)
                
        self.mean = torch.tensor([0.485, 0.456, 0.406]).view(1,-1, 1, 1).cuda() * 2 - 1
        self.std = torch.tensor([0.229, 0.224, 0.225]).view(1,-1, 1, 1).cuda() * 2

    def forward(self, X): # relui_1
        X = (X-self.mean)/self.std
        h_relu1 = self.slice1(X)
        h_relu2 = self.slice2(h_relu1)
        h_relu3 = self.slice3(h_relu2)
        h_relu4 = self.slice4(h_relu3)
        h_relu5 = self.slice5[:-2](h_relu4)
        out = [h_relu1, h_relu2, h_relu3, h_relu4, h_relu5]
        return out
    
# Perceptual loss that uses a pretrained VGG network
class VGGLoss(nn.Module):
    def __init__(self):
        super(VGGLoss, self).__init__()
        self.vgg = VGG19().cuda()
        self.criterion = nn.L1Loss()
        self.weights = [1.0 / 32, 1.0 / 16, 1.0 / 8, 1.0 / 4, 1.0]

    def forward(self, x, y):
        x_vgg, y_vgg = self.vgg(x), self.vgg(y)
        loss = 0
        for i in range(len(x_vgg)):
            loss += self.weights[i] * self.criterion(x_vgg[i], y_vgg[i].detach())
        return loss