Repository navigation
Expand file tree
/
Copy pathStyle Transfer.py
More file actions
210 lines (137 loc) · 4.94 KB
/
Copy pathStyle Transfer.py
File metadata and controls
210 lines (137 loc) · 4.94 KB
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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
#!/usr/bin/env python
# coding: utf-8
# In[1]:
import keras
keras.__version__
# In[4]:
from keras.preprocessing.image import load_img, img_to_array, save_img
target_image_path = './datasets/target.jpg'
style_reference_image_path = './datasets/style.jpg'
width, height = load_img(target_image_path).size
img_height = 400
img_width = int(width * img_height / height)
# In[5]:
import numpy as np
from keras.applications import vgg19
def preprocess_image(image_path):
img = load_img(image_path, target_size=(img_height, img_width))
img = img_to_array(img)
img = np.expand_dims(img, axis=0)
img = vgg19.preprocess_input(img)
return img
def deprocess_image(x):
x[:, :, 0] += 103.939
x[:, :, 1] += 116.779
x[:, :, 2] += 123.68
x = x[:, :, ::-1]
x = np.clip(x, 0, 255).astype('uint8')
return x
# In[6]:
from keras import backend as K
target_image = K.constant(preprocess_image(target_image_path))
style_reference_image = K.constant(preprocess_image(style_reference_image_path))
combination_image = K.placeholder((1, img_height, img_width, 3))
input_tensor = K.concatenate([target_image,
style_reference_image,
combination_image], axis=0)
model = vgg19.VGG19(input_tensor=input_tensor,
weights='imagenet',
include_top=False)
print('모델 로드 완료.')
# In[7]:
def content_loss(base, combination):
return K.sum(K.square(combination - base))
# In[8]:
def gram_matrix(x):
features = K.batch_flatten(K.permute_dimensions(x, (2, 0, 1)))
gram = K.dot(features, K.transpose(features))
return gram
def style_loss(style, combination):
S = gram_matrix(style)
C = gram_matrix(combination)
channels = 3
size = img_height * img_width
return K.sum(K.square(S - C)) / (4. * (channels ** 2) * (size ** 2))
# In[9]:
def total_variation_loss(x):
a = K.square(
x[:, :img_height - 1, :img_width - 1, :] - x[:, 1:, :img_width - 1, :])
b = K.square(
x[:, :img_height - 1, :img_width - 1, :] - x[:, :img_height - 1, 1:, :])
return K.sum(K.pow(a + b, 1.25))
# In[10]:
outputs_dict = dict([(layer.name, layer.output) for layer in model.layers])
content_layer = 'block5_conv2'
style_layers = ['block1_conv1',
'block2_conv1',
'block3_conv1',
'block4_conv1',
'block5_conv1']
total_variation_weight = 1e-4
style_weight = 1.
content_weight = 0.025
loss = K.variable(0.)
layer_features = outputs_dict[content_layer]
target_image_features = layer_features[0, :, :, :]
combination_features = layer_features[2, :, :, :]
loss += content_weight * content_loss(target_image_features,
combination_features)
for layer_name in style_layers:
layer_features = outputs_dict[layer_name]
style_reference_features = layer_features[1, :, :, :]
combination_features = layer_features[2, :, :, :]
sl = style_loss(style_reference_features, combination_features)
loss += (style_weight / len(style_layers)) * sl
loss += total_variation_weight * total_variation_loss(combination_image)
# In[11]:
grads = K.gradients(loss, combination_image)[0]
fetch_loss_and_grads = K.function([combination_image], [loss, grads])
class Evaluator(object):
def __init__(self):
self.loss_value = None
self.grads_values = None
def loss(self, x):
assert self.loss_value is None
x = x.reshape((1, img_height, img_width, 3))
outs = fetch_loss_and_grads([x])
loss_value = outs[0]
grad_values = outs[1].flatten().astype('float64')
self.loss_value = loss_value
self.grad_values = grad_values
return self.loss_value
def grads(self, x):
assert self.loss_value is not None
grad_values = np.copy(self.grad_values)
self.loss_value = None
self.grad_values = None
return grad_values
evaluator = Evaluator()
# In[ ]:
from scipy.optimize import fmin_l_bfgs_b
import time
result_prefix = 'style_transfer_result'
iterations = 20
x = preprocess_image(target_image_path)
x = x.flatten()
for i in range(iterations):
print('반복 횟수:', i)
start_time = time.time()
x, min_val, info = fmin_l_bfgs_b(evaluator.loss, x,
fprime=evaluator.grads, maxfun=20)
print('현재 손실 값:', min_val)
img = x.copy().reshape((img_height, img_width, 3))
img = deprocess_image(img)
fname = result_prefix + '_at_iteration_%d.png' % i
save_img(fname, img)
end_time = time.time()
print('저장 이미지: ', fname)
print('%d 번째 반복 완료: %ds' % (i, end_time - start_time))
# In[11]:
from matplotlib import pyplot as plt
# In[1]:
plt.imshow(load_img(target_image_path, target_size=(img_height, img_width)))
plt.figure()
plt.imshow(load_img(style_reference_image_path, target_size=(img_height, img_width)))
plt.figure()
plt.imshow(img)
plt.show()