-
Notifications
You must be signed in to change notification settings - Fork 0
/
style_transfer.py
192 lines (149 loc) · 6.15 KB
/
style_transfer.py
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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from PIL import Image
import torchvision.transforms as transforms
import torchvision.models as models
import torchvision
import argparse
import copy
def image_loader(image_name):
image = Image.open(image_name)
image = loader(image).unsqueeze(0)
return image.to(device, torch.float)
class ContentLoss(nn.Module):
def __init__(self, target,):
super(ContentLoss, self).__init__()
self.target = target.detach()
def forward(self, input):
self.loss = F.mse_loss(input, self.target)
return input
def gram_matrix(input):
batch, channel, height, width = input.size()
features = input.view(batch * channel, height * width)
G = torch.mm(features, features.t())
return G.div(batch * channel * height * width)
class StyleLoss(nn.Module):
def __init__(self, target_feature):
super(StyleLoss, self).__init__()
self.target = gram_matrix(target_feature).detach()
def forward(self, input):
G = gram_matrix(input)
self.loss = F.mse_loss(G, self.target)
return input
class Normalization(nn.Module):
def __init__(self):
super(Normalization, self).__init__()
mean = torch.tensor([0.485, 0.456, 0.406]).to(device)
std = torch.tensor([0.229, 0.224, 0.225]).to(device)
self.mean = torch.tensor(mean).view(-1, 1, 1)
self.std = torch.tensor(std).view(-1, 1, 1)
def forward(self, img):
return (img - self.mean) / self.std
def get_style_model_and_losses(cnn,style_img, content_img):
normalization = Normalization().to(device)
# Desired layers to calculate content and style loss
content_layers = ['conv_4']
style_layers = ['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']
content_losses = []
style_losses = []
model = nn.Sequential(normalization)
i = 0
for layer in cnn.children():
if isinstance(layer, nn.Conv2d):
i += 1
name = 'conv_{}'.format(i)
elif isinstance(layer, nn.ReLU):
name = 'relu_{}'.format(i)
layer = nn.ReLU(inplace=False)
elif isinstance(layer, nn.MaxPool2d):
name = 'pool_{}'.format(i)
elif isinstance(layer, nn.BatchNorm2d):
name = 'bn_{}'.format(i)
else:
raise RuntimeError('Unrecognized layer: {}'.format(layer.__class__.__name__))
model.add_module(name, layer)
# If the current layer is in desired content layers,
# add it to the the model
if name in content_layers:
target = model(content_img).detach()
content_loss = ContentLoss(target)
model.add_module("content_loss_{}".format(i), content_loss)
content_losses.append(content_loss)
# If the current layer is in desired style layers,
# add it to the the sequential model
if name in style_layers:
target_feature = model(style_img).detach()
style_loss = StyleLoss(target_feature)
model.add_module("style_loss_{}".format(i), style_loss)
style_losses.append(style_loss)
# Trim the layers after last content or style layer
for i in range(len(model) - 1, -1, -1):
if isinstance(model[i], ContentLoss) or isinstance(model[i], StyleLoss):
break
model = model[:(i + 1)]
return model, style_losses, content_losses
def get_input_optimizer(input_img):
optimizer = optim.LBFGS([input_img])
return optimizer
def main(cnn,content_img, style_img, input_img, num_steps,style_weight, content_weight):
model, style_losses, content_losses = get_style_model_and_losses(cnn,style_img, content_img)
# Optimize the input image not the network
input_img.requires_grad_(True)
model.requires_grad_(False)
optimizer = get_input_optimizer(input_img)
print('#####Optimizing Image#####')
run = [0]
while run[0] <= num_steps:
def closure():
# correct the values of updated input image
with torch.no_grad():
input_img.clamp_(0, 1)
optimizer.zero_grad()
model(input_img)
style_score = 0
content_score = 0
for sl in style_losses:
style_score += sl.loss
for cl in content_losses:
content_score += cl.loss
style_score *= style_weight
content_score *= content_weight
loss = style_score + content_score
loss.backward()
run[0] += 1
if run[0] % 50 == 0:
print("Epoch {}:".format(run))
print('Style Loss : {:4f} Content Loss: {:4f}'.format(
style_score.item(), content_score.item()))
print()
return style_score + content_score
optimizer.step(closure)
with torch.no_grad():
input_img.clamp_(0, 1)
return input_img
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('-c', help = "content image", required = True)
parser.add_argument('-s', help = "style image", required = True)
parser.add_argument('-style_weight', help = "style weight", type = int, default = 1000000)
parser.add_argument('-content_weight', help = "content weight",type = int, default = 1)
parser.add_argument('-steps', help = "number of steps",type = int, default = 300)
parser.add_argument('-save', help = "generated image name",type = str,required = True)
args = parser.parse_args()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# Desired image size
imsize = 512
loader = transforms.Compose([
transforms.Resize((imsize, imsize)),
transforms.ToTensor()])
style_img = image_loader(args.s)
content_img = image_loader(args.c)
# Pretrained CNN model
cnn = models.vgg19(pretrained=True).features.to(device).eval()
input_img = content_img.clone()
output = main(cnn, content_img, style_img, input_img,args.steps, args.style_weight, args.content_weight)
torchvision.utils.save_image(output, args.save + ".png")
print("Image Saved")