-
Notifications
You must be signed in to change notification settings - Fork 5
/
model.py
178 lines (140 loc) · 5.41 KB
/
model.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
import tensorflow as tf
import numpy as np
import PIL.Image
def tensor_to_image(tensor):
tensor = tensor * 255
tensor = np.array(tensor, dtype=np.uint8)
if np.ndim(tensor) > 3:
assert tensor.shape[0] == 1
tensor = tensor[0]
return PIL.Image.fromarray(tensor)
def load_img(path_to_img, max_dim):
img = tf.io.read_file(path_to_img)
img = tf.image.decode_image(img, channels=3)
img = tf.image.convert_image_dtype(img, tf.float32)
shape = tf.cast(tf.shape(img)[:-1], tf.float32)
long_dim = max(shape)
scale = max_dim / long_dim
new_shape = tf.cast(shape * scale, tf.int32)
img = tf.image.resize(img, new_shape)
img = img[tf.newaxis, :]
return img
def vgg_layers(layer_names):
"""Creates a vgg model that returns a list of intermediate output values."""
# Load our model. Load pretrained VGG, trained on imagenet data
vgg = tf.keras.applications.VGG19(include_top=False, weights="imagenet")
vgg.trainable = False
outputs = [vgg.get_layer(name).output for name in layer_names]
model = tf.keras.Model([vgg.input], outputs)
return model
def gram_matrix(input_tensor):
result = tf.linalg.einsum("bijc,bijd->bcd", input_tensor, input_tensor)
input_shape = tf.shape(input_tensor)
num_locations = tf.cast(input_shape[1] * input_shape[2], tf.float32)
return result / (num_locations)
class StyleContentModel(tf.keras.models.Model):
def __init__(self, style_layers, content_layers):
super(StyleContentModel, self).__init__()
self.vgg = vgg_layers(style_layers + content_layers)
self.style_layers = style_layers
self.content_layers = content_layers
self.num_style_layers = len(style_layers)
self.vgg.trainable = False
def call(self, inputs):
"Expects float input in [0,1]"
inputs = inputs * 255.0
preprocessed_input = tf.keras.applications.vgg19.preprocess_input(inputs)
outputs = self.vgg(preprocessed_input)
style_outputs, content_outputs = (
outputs[: self.num_style_layers],
outputs[self.num_style_layers :],
)
style_outputs = [gram_matrix(style_output) for style_output in style_outputs]
content_dict = {
content_name: value
for content_name, value in zip(self.content_layers, content_outputs)
}
style_dict = {
style_name: value
for style_name, value in zip(self.style_layers, style_outputs)
}
return {"content": content_dict, "style": style_dict}
def style_transfer_image(
content,
style,
epochs=10,
steps_per_epoch=100,
style_weight=1e-2,
content_weight=1e4,
total_variation_weight=30,
max_dim=1000,
save_name="output.png",
):
content_img = load_img(content, max_dim=max_dim)
style_img = load_img(style, max_dim=max_dim)
content_layers = ["block5_conv2"]
style_layers = [
"block1_conv1",
"block2_conv1",
"block3_conv1",
"block4_conv1",
"block5_conv1",
]
num_content_layers = len(content_layers)
num_style_layers = len(style_layers)
extractor = StyleContentModel(style_layers, content_layers)
# Gradient Descent
style_targets = extractor(style_img)["style"]
content_targets = extractor(content_img)["content"]
image = tf.Variable(content_img)
def clip_0_1(image):
return tf.clip_by_value(image, clip_value_min=0.0, clip_value_max=1.0)
opt = tf.optimizers.Adam(learning_rate=0.02, beta_1=0.99, epsilon=1e-1)
def style_content_loss(outputs):
style_outputs = outputs["style"]
content_outputs = outputs["content"]
style_loss = tf.add_n(
[
tf.reduce_mean((style_outputs[name] - style_targets[name]) ** 2)
for name in style_outputs.keys()
]
)
style_loss *= style_weight / num_style_layers
content_loss = tf.add_n(
[
tf.reduce_mean((content_outputs[name] - content_targets[name]) ** 2)
for name in content_outputs.keys()
]
)
content_loss *= content_weight / num_content_layers
loss = style_loss + content_loss
return loss
@tf.function()
def train_step(image):
with tf.GradientTape() as tape:
outputs = extractor(image)
loss = style_content_loss(outputs)
loss += total_variation_weight * tf.image.total_variation(image)
grad = tape.gradient(loss, image)
opt.apply_gradients([(grad, image)])
image.assign(clip_0_1(image))
for n in range(epochs):
print(f"\nEpoch: {n+1}/{epochs}")
for m in range(steps_per_epoch):
print(m, " of ", steps_per_epoch, end="\r")
train_step(image)
img = tensor_to_image(image)
img.save(f"{save_name}-{n}.png")
if __name__ == "__main__":
style_transfer_image(
"blend.png", "images/style/greatwave.jpg", save_name="blend-wave",
style_weight=1e-2, content_weight=1e4, total_variation_weight=30,
)
style_transfer_image(
"blend.png", "images/style/greatwave.jpg", save_name="blend-weighted",
style_weight=1e-2, content_weight=3e4, total_variation_weight=30,
)
style_transfer_image(
"blend.png", "images/style/greatwave.jpg", save_name="blend-styled",
style_weight=3e-2, content_weight=1e4, total_variation_weight=30,
)