Style-Transfer-Algorithm/src/custom_vgg19.py at master · mkeid/Style-Transfer-Algorithm · GitHub

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
import os
import tensorflow as tf
import numpy as np
import inspect
import urllib.request

VGG_MEAN = [103.939, 116.779, 123.68]
data = None
dir_path = os.path.dirname(os.path.realpath(__file__))
weights_name = dir_path + "/../lib/weights/vgg19.npy"
weights_url = "https://www.dropbox.com/s/68opci8420g7bcl/vgg19.npy?dl=1"


class Vgg19:
    def __init__(self, vgg19_npy_path=None):
        global data

        if vgg19_npy_path is None:
            path = inspect.getfile(Vgg19)
            path = os.path.abspath(os.path.join(path, os.pardir))
            path = os.path.join(path, weights_name)

            if os.path.exists(path):
                vgg19_npy_path = path
            else:
                print("VGG19 weights were not found in the project directory")

                answer = 0
                while answer is not 'y' and answer is not 'N':
                    answer = input("Would you like to download the 548 MB file? [y/N] ").replace(" ", "")

                # Download weights if yes, else exit the program
                if answer == 'y':
                    print("Downloading. Please be patient...")
                    urllib.request.urlretrieve(weights_url, weights_name)
                    vgg19_npy_path = path
                elif answer == 'N':
                    print("Exiting the program..")
                    exit(0)

        if data is None:
            data = np.load(vgg19_npy_path, encoding='latin1')
            self.data_dict = data.item()
            print("VGG19 weights loaded")

        else:
            self.data_dict = data.item()

    def build(self, rgb, shape):
        rgb_scaled = rgb * 255.0
        num_channels = shape[2]
        channel_shape = shape
        channel_shape[2] = 1

        # Convert RGB to BGR
        red, green, blue = tf.split(axis=3, num_or_size_splits=3, value=rgb_scaled)

        assert red.get_shape().as_list()[1:] == channel_shape
        assert green.get_shape().as_list()[1:] == channel_shape
        assert blue.get_shape().as_list()[1:] == channel_shape

        bgr = tf.concat(axis=3, values=[
            blue - VGG_MEAN[0],
            green - VGG_MEAN[1],
            red - VGG_MEAN[2],
        ])

        shape[2] = num_channels
        assert bgr.get_shape().as_list()[1:] == shape

        self.conv1_1 = self.conv_layer(bgr, "conv1_1")
        self.conv1_2 = self.conv_layer(self.conv1_1, "conv1_2")
        self.pool1 = self.avg_pool(self.conv1_2, 'pool1')

        self.conv2_1 = self.conv_layer(self.pool1, "conv2_1")
        self.conv2_2 = self.conv_layer(self.conv2_1, "conv2_2")
        self.pool2 = self.avg_pool(self.conv2_2, 'pool2')

        self.conv3_1 = self.conv_layer(self.pool2, "conv3_1")
        self.conv3_2 = self.conv_layer(self.conv3_1, "conv3_2")
        self.conv3_3 = self.conv_layer(self.conv3_2, "conv3_3")
        self.conv3_4 = self.conv_layer(self.conv3_3, "conv3_4")
        self.pool3 = self.avg_pool(self.conv3_4, 'pool3')

        self.conv4_1 = self.conv_layer(self.pool3, "conv4_1")
        self.conv4_2 = self.conv_layer(self.conv4_1, "conv4_2")
        self.conv4_3 = self.conv_layer(self.conv4_2, "conv4_3")
        self.conv4_4 = self.conv_layer(self.conv4_3, "conv4_4")
        self.pool4 = self.avg_pool(self.conv4_4, 'pool4')

        self.conv5_1 = self.conv_layer(self.pool4, "conv5_1")
        self.conv5_2 = self.conv_layer(self.conv5_1, "conv5_2")
        self.conv5_3 = self.conv_layer(self.conv5_2, "conv5_3")
        self.conv5_4 = self.conv_layer(self.conv5_3, "conv5_4")

        self.data_dict = None

    def avg_pool(self, bottom, name):
        return tf.nn.avg_pool(bottom, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', name=name)

    def max_pool(self, bottom, name):
        return tf.nn.max_pool(bottom, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', name=name)

    def conv_layer(self, bottom, name):
        with tf.variable_scope(name):
            filt = self.get_conv_filter(name)

            conv = tf.nn.conv2d(bottom, filt, [1, 1, 1, 1], padding='SAME')

            conv_biases = self.get_bias(name)
            bias = tf.nn.bias_add(conv, conv_biases)

            relu = tf.nn.relu(bias)
            return relu

    def fc_layer(self, bottom, name):
        with tf.variable_scope(name):
            shape = bottom.get_shape().as_list()
            dim = 1
            for d in shape[1:]:
                dim *= d
            x = tf.reshape(bottom, [-1, dim])

            weights = self.get_fc_weight(name)
            biases = self.get_bias(name)

            # Fully connected layer. Note that the '+' operation automatically
            # broadcasts the biases.
            fc = tf.nn.bias_add(tf.matmul(x, weights), biases)

            return fc

    def get_conv_filter(self, name):
        return tf.constant(self.data_dict[name][0], name="filter")

    def get_bias(self, name):
        return tf.constant(self.data_dict[name][1], name="biases")

    def get_fc_weight(self, name):
        return tf.constant(self.data_dict[name][0], name="weights")