File size: 5,274 Bytes
0c50ae6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch.nn as nn

from function import adaptive_instance_normalization as adain
from function import calc_mean_std

decoder = nn.Sequential(
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(512, 256, (3, 3)),
    nn.ReLU(),
    nn.Upsample(scale_factor=2, mode='nearest'),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(256, 256, (3, 3)),
    nn.ReLU(),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(256, 256, (3, 3)),
    nn.ReLU(),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(256, 256, (3, 3)),
    nn.ReLU(),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(256, 128, (3, 3)),
    nn.ReLU(),
    nn.Upsample(scale_factor=2, mode='nearest'),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(128, 128, (3, 3)),
    nn.ReLU(),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(128, 64, (3, 3)),
    nn.ReLU(),
    nn.Upsample(scale_factor=2, mode='nearest'),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(64, 64, (3, 3)),
    nn.ReLU(),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(64, 3, (3, 3)),
)

vgg = nn.Sequential(
    nn.Conv2d(3, 3, (1, 1)),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(3, 64, (3, 3)),
    nn.ReLU(),  # relu1-1
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(64, 64, (3, 3)),
    nn.ReLU(),  # relu1-2
    nn.MaxPool2d((2, 2), (2, 2), (0, 0), ceil_mode=True),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(64, 128, (3, 3)),
    nn.ReLU(),  # relu2-1
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(128, 128, (3, 3)),
    nn.ReLU(),  # relu2-2
    nn.MaxPool2d((2, 2), (2, 2), (0, 0), ceil_mode=True),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(128, 256, (3, 3)),
    nn.ReLU(),  # relu3-1
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(256, 256, (3, 3)),
    nn.ReLU(),  # relu3-2
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(256, 256, (3, 3)),
    nn.ReLU(),  # relu3-3
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(256, 256, (3, 3)),
    nn.ReLU(),  # relu3-4
    nn.MaxPool2d((2, 2), (2, 2), (0, 0), ceil_mode=True),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(256, 512, (3, 3)),
    nn.ReLU(),  # relu4-1, this is the last layer used
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(512, 512, (3, 3)),
    nn.ReLU(),  # relu4-2
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(512, 512, (3, 3)),
    nn.ReLU(),  # relu4-3
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(512, 512, (3, 3)),
    nn.ReLU(),  # relu4-4
    nn.MaxPool2d((2, 2), (2, 2), (0, 0), ceil_mode=True),
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(512, 512, (3, 3)),
    nn.ReLU(),  # relu5-1
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(512, 512, (3, 3)),
    nn.ReLU(),  # relu5-2
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(512, 512, (3, 3)),
    nn.ReLU(),  # relu5-3
    nn.ReflectionPad2d((1, 1, 1, 1)),
    nn.Conv2d(512, 512, (3, 3)),
    nn.ReLU()  # relu5-4
)


class Net(nn.Module):
    def __init__(self, encoder, decoder):
        super(Net, self).__init__()
        enc_layers = list(encoder.children())
        self.enc_1 = nn.Sequential(*enc_layers[:4])  # input -> relu1_1
        self.enc_2 = nn.Sequential(*enc_layers[4:11])  # relu1_1 -> relu2_1
        self.enc_3 = nn.Sequential(*enc_layers[11:18])  # relu2_1 -> relu3_1
        self.enc_4 = nn.Sequential(*enc_layers[18:31])  # relu3_1 -> relu4_1
        self.decoder = decoder
        self.mse_loss = nn.MSELoss()

        # fix the encoder
        for name in ['enc_1', 'enc_2', 'enc_3', 'enc_4']:
            for param in getattr(self, name).parameters():
                param.requires_grad = False

    # extract relu1_1, relu2_1, relu3_1, relu4_1 from input image
    def encode_with_intermediate(self, input):
        results = [input]
        for i in range(4):
            func = getattr(self, 'enc_{:d}'.format(i + 1))
            results.append(func(results[-1]))
        return results[1:]

    # extract relu4_1 from input image
    def encode(self, input):
        for i in range(4):
            input = getattr(self, 'enc_{:d}'.format(i + 1))(input)
        return input

    def calc_content_loss(self, input, target):
        assert (input.size() == target.size())
        assert (target.requires_grad is False)
        return self.mse_loss(input, target)

    def calc_style_loss(self, input, target):
        assert (input.size() == target.size())
        assert (target.requires_grad is False)
        input_mean, input_std = calc_mean_std(input)
        target_mean, target_std = calc_mean_std(target)
        return self.mse_loss(input_mean, target_mean) + \
               self.mse_loss(input_std, target_std)

    def forward(self, content, style, alpha=1.0):
        assert 0 <= alpha <= 1
        style_feats = self.encode_with_intermediate(style)
        content_feat = self.encode(content)
        t = adain(content_feat, style_feats[-1])
        t = alpha * t + (1 - alpha) * content_feat

        g_t = self.decoder(t)
        g_t_feats = self.encode_with_intermediate(g_t)

        loss_c = self.calc_content_loss(g_t_feats[-1], t)
        loss_s = self.calc_style_loss(g_t_feats[0], style_feats[0])
        for i in range(1, 4):
            loss_s += self.calc_style_loss(g_t_feats[i], style_feats[i])
        return loss_c, loss_s