-
Notifications
You must be signed in to change notification settings - Fork 0
/
nst_utils.py
186 lines (160 loc) · 6.42 KB
/
nst_utils.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
import os
import sys
import scipy.io
import scipy.misc
import matplotlib.pyplot as plt
from matplotlib.pyplot import imshow
from PIL import Image
from nst_utils import *
import numpy as np
import tensorflow as tf
class CONFIG:
IMAGE_WIDTH = 400
IMAGE_HEIGHT = 300
COLOR_CHANNELS = 3
NOISE_RATIO = 0.6
MEANS = np.array([123.68, 116.779, 103.939]).reshape((1,1,1,3))
VGG_MODEL = 'pretrained-model/imagenet-vgg-verydeep-19.mat' # Pick the VGG 19-layer model by from the paper "Very Deep Convolutional Networks for Large-Scale Image Recognition".
STYLE_IMAGE = 'images/stone_style.jpg' # Style image to use.
CONTENT_IMAGE = 'images/content300.jpg' # Content image to use.
OUTPUT_DIR = 'output/'
def load_vgg_model(path):
"""
Returns a model for the purpose of 'painting' the picture.
Takes only the convolution layer weights and wrap using the TensorFlow
Conv2d, Relu and AveragePooling layer. VGG actually uses maxpool but
the paper indicates that using AveragePooling yields bette1r results.
The last few fully connected layers are not used.
Here is the detailed configuration of the VGG model:
0 is conv1_1 (3, 3, 3, 64)
1 is relu
2 is conv1_2 (3, 3, 64, 64)
3 is relu
4 is maxpool
5 is conv2_1 (3, 3, 64, 128)
6 is relu
7 is conv2_2 (3, 3, 128, 128)
8 is relu
9 is maxpool
10 is conv3_1 (3, 3, 128, 256)
11 is relu
12 is conv3_2 (3, 3, 256, 256)
13 is relu
14 is conv3_3 (3, 3, 256, 256)
15 is relu
16 is conv3_4 (3, 3, 256, 256)
17 is relu
18 is maxpool
19 is conv4_1 (3, 3, 256, 512)
20 is relu
21 is conv4_2 (3, 3, 512, 512)
22 is relu
23 is conv4_3 (3, 3, 512, 512)
24 is relu
25 is conv4_4 (3, 3, 512, 512)
26 is relu
27 is maxpool
28 is conv5_1 (3, 3, 512, 512)
29 is relu
30 is conv5_2 (3, 3, 512, 512)
31 is relu
32 is conv5_3 (3, 3, 512, 512)
33 is relu
34 is conv5_4 (3, 3, 512, 512)
35 is relu
36 is maxpool
37 is fullyconnected (7, 7, 512, 4096)
38 is relu
39 is fullyconnected (1, 1, 4096, 4096)
40 is relu
41 is fullyconnected (1, 1, 4096, 1000)
42 is softmax
"""
vgg = scipy.io.loadmat(path)
vgg_layers = vgg['layers']
def _weights(layer, expected_layer_name):
"""
Return the weights and bias from the VGG model for a given layer.
"""
wb = vgg_layers[0][layer][0][0][2]
W = wb[0][0]
b = wb[0][1]
layer_name = vgg_layers[0][layer][0][0][0][0]
assert layer_name == expected_layer_name
return W, b
return W, b
def _relu(conv2d_layer):
"""
Return the RELU function wrapped over a TensorFlow layer. Expects a
Conv2d layer input.
"""
return tf.nn.relu(conv2d_layer)
def _conv2d(prev_layer, layer, layer_name):
"""
Return the Conv2D layer using the weights, biases from the VGG
model at 'layer'.
"""
W, b = _weights(layer, layer_name)
W = tf.constant(W)
b = tf.constant(np.reshape(b, (b.size)))
return tf.nn.conv2d(prev_layer, filter=W, strides=[1, 1, 1, 1], padding='SAME') + b
def _conv2d_relu(prev_layer, layer, layer_name):
"""
Return the Conv2D + RELU layer using the weights, biases from the VGG
model at 'layer'.
"""
return _relu(_conv2d(prev_layer, layer, layer_name))
def _avgpool(prev_layer):
"""
Return the AveragePooling layer.
"""
return tf.nn.avg_pool(prev_layer, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# Constructs the graph model.
graph = {}
graph['input'] = tf.Variable(np.zeros((1, CONFIG.IMAGE_HEIGHT, CONFIG.IMAGE_WIDTH, CONFIG.COLOR_CHANNELS)), dtype = 'float32')
graph['conv1_1'] = _conv2d_relu(graph['input'], 0, 'conv1_1')
graph['conv1_2'] = _conv2d_relu(graph['conv1_1'], 2, 'conv1_2')
graph['avgpool1'] = _avgpool(graph['conv1_2'])
graph['conv2_1'] = _conv2d_relu(graph['avgpool1'], 5, 'conv2_1')
graph['conv2_2'] = _conv2d_relu(graph['conv2_1'], 7, 'conv2_2')
graph['avgpool2'] = _avgpool(graph['conv2_2'])
graph['conv3_1'] = _conv2d_relu(graph['avgpool2'], 10, 'conv3_1')
graph['conv3_2'] = _conv2d_relu(graph['conv3_1'], 12, 'conv3_2')
graph['conv3_3'] = _conv2d_relu(graph['conv3_2'], 14, 'conv3_3')
graph['conv3_4'] = _conv2d_relu(graph['conv3_3'], 16, 'conv3_4')
graph['avgpool3'] = _avgpool(graph['conv3_4'])
graph['conv4_1'] = _conv2d_relu(graph['avgpool3'], 19, 'conv4_1')
graph['conv4_2'] = _conv2d_relu(graph['conv4_1'], 21, 'conv4_2')
graph['conv4_3'] = _conv2d_relu(graph['conv4_2'], 23, 'conv4_3')
graph['conv4_4'] = _conv2d_relu(graph['conv4_3'], 25, 'conv4_4')
graph['avgpool4'] = _avgpool(graph['conv4_4'])
graph['conv5_1'] = _conv2d_relu(graph['avgpool4'], 28, 'conv5_1')
graph['conv5_2'] = _conv2d_relu(graph['conv5_1'], 30, 'conv5_2')
graph['conv5_3'] = _conv2d_relu(graph['conv5_2'], 32, 'conv5_3')
graph['conv5_4'] = _conv2d_relu(graph['conv5_3'], 34, 'conv5_4')
graph['avgpool5'] = _avgpool(graph['conv5_4'])
return graph
def generate_noise_image(content_image, noise_ratio = CONFIG.NOISE_RATIO):
"""
Generates a noisy image by adding random noise to the content_image
"""
# Generate a random noise_image
noise_image = np.random.uniform(-20, 20, (1, CONFIG.IMAGE_HEIGHT, CONFIG.IMAGE_WIDTH, CONFIG.COLOR_CHANNELS)).astype('float32')
# Set the input_image to be a weighted average of the content_image and a noise_image
input_image = noise_image * noise_ratio + content_image * (1 - noise_ratio)
return input_image
def reshape_and_normalize_image(image):
"""
Reshape and normalize the input image (content or style)
"""
# Reshape image to mach expected input of VGG16
image = np.reshape(image, ((1,) + image.shape))
# Substract the mean to match the expected input of VGG16
image = image - CONFIG.MEANS
return image
def save_image(path, image):
# Un-normalize the image so that it looks good
image = image + CONFIG.MEANS
# Clip and Save the image
image = np.clip(image[0], 0, 255).astype('uint8')
scipy.misc.imsave(path, image)