郭霖的博客

腾讯音乐实习ing

Ai图像风格迁移

发表于 分类于
本文字数： 8.8k 阅读时长 ≈ 8 分钟

Ai图像风格迁移

参考论文：http://arxiv.org/abs/1508.06576

使用vgg16算法实现图片风格迁移

效果展示

梵高星夜

30次梯度迭代后的结果：

me_t_at_iteration_29

30次迭代过程：

diedai

原图：

landscape

梵高星夜：

starry_night

路边景色

风格迁移后：

beicaile_at_iteration_14

原图：

1

学习风格：

2

相关依赖库的安装

我使用的是anaconda环境下的python3.10

需要的包根据自己的环境自行下载即可

1
2
3
4
5
conda install keras
conda install h5py
conda install numpy
conda install scipy
conda install tensorflow

配置运行环境

下载VGG16模型 https://pan.baidu.com/s/1i5wYN1z 放入如下目录当中

(注意：每个人的主目录都不一样，如果没有.keras这个文件夹新建就行了)

image-20230801003307211

源码

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
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
from __future__ import print_function
from tensorflow.keras.preprocessing.image import load_img, img_to_array
import imageio
import numpy as np
from scipy.optimize import fmin_l_bfgs_b
import time
import argparse

from keras.applications import vgg16
from keras import backend as K

import os
os.environ['KMP_DUPLICATE_LIB_OK']='True'

import tensorflow as tf
# 禁用 Eager Execution
tf.compat.v1.disable_eager_execution()


parser = argparse.ArgumentParser(description='Neural style transfer with Keras.')
parser.add_argument('base_image_path', metavar='base', type=str,
                    help='Path to the image to transform.')
parser.add_argument('style_reference_image_path', metavar='ref', type=str,
                    help='Path to the style reference image.')
parser.add_argument('result_prefix', metavar='res_prefix', type=str,
                    help='Prefix for the saved results.')
parser.add_argument('--iter', type=int, default=10, required=False,
                    help='Number of iterations to run.')
parser.add_argument('--content_weight', type=float, default=0.025, required=False,
                    help='Content weight.')
parser.add_argument('--style_weight', type=float, default=1.0, required=False,
                    help='Style weight.')
parser.add_argument('--tv_weight', type=float, default=1.0, required=False,
                    help='Total Variation weight.')

args = parser.parse_args()
base_image_path = args.base_image_path
style_reference_image_path = args.style_reference_image_path
result_prefix = './training/' + args.result_prefix.split('/')[1]
iterations = args.iter

# these are the weights of the different loss components
total_variation_weight = args.tv_weight
style_weight = args.style_weight
content_weight = args.content_weight

# dimensions of the generated picture.
width, height = load_img(base_image_path).size
img_nrows = 400
img_ncols = int(width * img_nrows / height)

# util function to open, resize and format pictures into appropriate tensors


def preprocess_image(image_path):
    img = load_img(image_path, target_size=(img_nrows, img_ncols))
    img = img_to_array(img)
    img = np.expand_dims(img, axis=0)
    img = vgg16.preprocess_input(img)
    return img

# util function to convert a tensor into a valid image


def deprocess_image(x):
    if K.image_data_format() == 'channels_first':
        x = x.reshape((3, img_nrows, img_ncols))
        x = x.transpose((1, 2, 0))
    else:
        x = x.reshape((img_nrows, img_ncols, 3))
    # Remove zero-center by mean pixel
    x[:, :, 0] += 103.939
    x[:, :, 1] += 116.779
    x[:, :, 2] += 123.68
    # 'BGR'->'RGB'
    x = x[:, :, ::-1]
    x = np.clip(x, 0, 255).astype('uint8')
    return x

# get tensor representations of our images
base_image = K.variable(preprocess_image(base_image_path))
style_reference_image = K.variable(preprocess_image(style_reference_image_path))

# this will contain our generated image
if K.image_data_format() == 'channels_first':
    combination_image = K.placeholder((1, 3, img_nrows, img_ncols))
else:
    combination_image = K.placeholder((1, img_nrows, img_ncols, 3))

# combine the 3 images into a single Keras tensor
input_tensor = K.concatenate([base_image,
                              style_reference_image,
                              combination_image], axis=0)

# build the VGG16 network with our 3 images as input
# the model will be loaded with pre-trained ImageNet weights
model = vgg16.VGG16(input_tensor=input_tensor,
                    weights='imagenet', include_top=False)
print('Model loaded.')

# get the symbolic outputs of each "key" layer (we gave them unique names).
outputs_dict = dict([(layer.name, layer.output) for layer in model.layers])

# compute the neural style loss
# first we need to define 4 util functions

# the gram matrix of an image tensor (feature-wise outer product)


def gram_matrix(x):
    assert K.ndim(x) == 3
    if K.image_data_format() == 'channels_first':
        features = K.batch_flatten(x)
    else:
        features = K.batch_flatten(K.permute_dimensions(x, (2, 0, 1)))
    gram = K.dot(features, K.transpose(features))
    return gram

# the "style loss" is designed to maintain
# the style of the reference image in the generated image.
# It is based on the gram matrices (which capture style) of
# feature maps from the style reference image
# and from the generated image


def style_loss(style, combination):
    assert K.ndim(style) == 3
    assert K.ndim(combination) == 3
    S = gram_matrix(style)
    C = gram_matrix(combination)
    channels = 3
    size = img_nrows * img_ncols
    return K.sum(K.square(S - C)) / (4. * (channels ** 2) * (size ** 2))

# an auxiliary loss function
# designed to maintain the "content" of the
# base image in the generated image


def content_loss(base, combination):
    return K.sum(K.square(combination - base))

# the 3rd loss function, total variation loss,
# designed to keep the generated image locally coherent


def total_variation_loss(x):
    assert K.ndim(x) == 4
    if K.image_data_format() == 'channels_first':
        a = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] - x[:, :, 1:, :img_ncols - 1])
        b = K.square(x[:, :, :img_nrows - 1, :img_ncols - 1] - x[:, :, :img_nrows - 1, 1:])
    else:
        a = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] - x[:, 1:, :img_ncols - 1, :])
        b = K.square(x[:, :img_nrows - 1, :img_ncols - 1, :] - x[:, :img_nrows - 1, 1:, :])
    return K.sum(K.pow(a + b, 1.25))

# combine these loss functions into a single scalar
loss = K.variable(0.)
layer_features = outputs_dict['block4_conv2']
base_image_features = layer_features[0, :, :, :]
combination_features = layer_features[2, :, :, :]
loss = loss + content_weight * content_loss(base_image_features,
                                      combination_features)

feature_layers = ['block1_conv1', 'block2_conv1',
                  'block3_conv1', 'block4_conv1',
                  'block5_conv1']
for layer_name in feature_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(feature_layers)) * sl
loss += total_variation_weight * total_variation_loss(combination_image)

# get the gradients of the generated image wrt the loss
grads = K.gradients(loss, combination_image)

outputs = [loss]
if isinstance(grads, (list, tuple)):
    outputs += grads
else:
    outputs.append(grads)

f_outputs = K.function([combination_image], outputs)


def eval_loss_and_grads(x):
    if K.image_data_format() == 'channels_first':
        x = x.reshape((1, 3, img_nrows, img_ncols))
    else:
        x = x.reshape((1, img_nrows, img_ncols, 3))
    outs = f_outputs([x])
    loss_value = outs[0]
    if len(outs[1:]) == 1:
        grad_values = outs[1].flatten().astype('float64')
    else:
        grad_values = np.array(outs[1:]).flatten().astype('float64')
    return loss_value, grad_values

# this Evaluator class makes it possible
# to compute loss and gradients in one pass
# while retrieving them via two separate functions,
# "loss" and "grads". This is done because scipy.optimize
# requires separate functions for loss and gradients,
# but computing them separately would be inefficient.


class Evaluator(object):

    def __init__(self):
        self.loss_value = None
        self.grads_values = None

    def loss(self, x):
        assert self.loss_value is None
        loss_value, grad_values = eval_loss_and_grads(x)
        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()

# run scipy-based optimization (L-BFGS) over the pixels of the generated image
# so as to minimize the neural style loss
if K.image_data_format() == 'channels_first':
    x = np.random.uniform(0, 255, (1, 3, img_nrows, img_ncols)) - 128.
else:
    x = np.random.uniform(0, 255, (1, img_nrows, img_ncols, 3)) - 128.

for i in range(iterations):
    print('Start of iteration', i)
    start_time = time.time()
    x, min_val, info = fmin_l_bfgs_b(evaluator.loss, x.flatten(),
                                     fprime=evaluator.grads, maxfun=20)
    print('Current loss value:', min_val)
    # save current generated image
    img = deprocess_image(x.copy())
    fname = result_prefix + '_at_iteration_%d.png' % i
    imageio.imwrite(fname, img)
    end_time = time.time()
    print('Image saved as', fname)
    print('Iteration %d completed in %ds' % (i, end_time - start_time))

运行

新建一个空文件夹，把上一步骤的文件neural_style_transfer.py放入这个空文件夹中。然后把相应的模板图片，待转化图片放入该文件当中。

1
2
3
4
python neural_style_transfer.py   你的待转化图片路径    模板图片路径   保存的生产图片路径加名称

# 例如
python neural_style_transfer.py ./me.jpg ./starry_night.jpg ./me_t

注意:图片路径需要去掉引号，自定义迭代次数请在末尾指定–iter n。

迭代结果截图：

image-20230801003621431

-------------本文结束感谢您的阅读-------------