TFnote/VGGNet.py at master · Paleve/TFnote · 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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
import tensorflow as tf
import math
import time
from datetime import datetime


# tf.Variable(tensor, trianable, name)
def conv_op(input_op, name, kh, kw, n_in, n_out):
    n_in = input_op.get_shape()[-1].value  #

    with tf.name_scope(name) as scope:
        kernel = tf.get_variable(scope + "w", shape=[kh, kw, n_in, n_out], dtype=tf.float32,
                                 initializer=tf.contrib.layers.xavire_initilizer_conv2d())
        conv = tf.nn.conv2d(input_op, kernel, (1, kh, kw, 1), padding='SAME')
        bias_init_val = tf.constant(0.0, shape=[n_out], dtype=tf.float32)
        biases = tf.Variable(bias_init_val, trainable=True, name='b')
        z = tf.nn.bias_add(conv, biases)
        activation = tf.nn.relu(z)
        p += [kernel, biases]
        return activation


def fc_op(input_op, name, n_out, p):
    n_in = input_op.get_shape()[-1].value()

    with tf.name_scope(name) as scope:
        kernel = tf.get_variable(scope + "w", shape=[n_in, n_out], dtype=tf.float32,
                                 initializer=tf.contrib.layers.xavire_initilizer())
        biases = tf.Variable(tf.constant(0.1, shape=[n_out],
                                         dtype=tf.float32, name='b'))
        activation = tf.nn.relu_layer(input_op, kernel, biases, name=scope)
        p += [kernel, biases]
        return activation


def mpool_op(input_op, name, kh, kw, dh, dw):
    return tf.nn.max_pool(input_op, ksize=[1, kh, kw, 1],
                          strides=[1, dh, dw, 1],
                          padding='SAME', name=name)


def inference_op(input_op, keep_prob):
    p = []


    conv1_1 = conv_op(input_op, name='conv1_1', kh=3, kw=3,
                      n_out=64, dh=1, dw=1, p=p)
    conv1_2 = conv_op(conv1_1, name='conv1_2', kh=3, kw=3,
                      n_out=64, dh=1, dw=1, p=p)
    pool1 = mpool_op(conv1_2, name="pool1", kh=2, kw=2, dw=2, dh=2)


    conv2_1 = conv_op(pool1, name='conv2_1', kh=3, kw=3,
                      n_out=128, dh=1, dw=1, p=p)
    conv2_2 = conv_op(conv2_1, name='conv2_2', kh=3, kw=3,
                      n_out=128, dh=1, dw=1, p=p)
    pool2 = mpool_op(conv2_2, name="pool2", kw=2, kh=2, dh=2, dw=2)


    conv3_1 = conv_op(pool2, name="conv3_1", kh=3, kw=3,
                      n_out=256, dh=1, dw=1, p=p)
    conv3_2 = conv_op(conv3_1, name="conv3_2", kh=3, kw=3,
                      n_out=256, dh=1, dw=1, p=p)
    conv3_3 = conv_op(conv3_2, name="conv3_3", kh=3, kw=3,
                      n_out=256, dh=1, dw=1, p=p)
    pool3 = mpool_op(conv3_3, name="pool3", kw=2, kh=2, dh=2, dw=2)


    conv4_1 = conv_op(pool3, name="conv4_1", kh=3, kw=3,
                      n_out=512, dh=1, dw=1, p=p)
    conv4_2 = conv_op(conv4_1, name="conv4_2", kh=3, kw=3,
                      n_out=512, dh=1, dw=1, p=p)
    conv4_3 = conv_op(conv4_2, name="conv4_3", kh=3, kw=3,
                      n_out=512, dh=1, dw=1, p=p)
    pool4 = mpool_op(conv4_3, name="pool4", kw=2, kh=2, dh=2, dw=2)

    conv5_1 = conv_op(pool4, name="conv5_1", kh=3, kw=3,
                      n_out=512, dh=1, dw=1, p=p)
    conv5_2 = conv_op(conv5_1, name="conv5_2", kh=3, kw=3,
                      n_out=512, dh=1, dw=1, p=p)
    conv5_3 = conv_op(conv5_2, name="conv5_3", kh=3, kw=3,
                      n_out=512, dh=1, dw=1, p=p)
    pool5 = mpool_op(conv5_3, name="pool5", kw=2, kh=2, dh=2, dw=2)


    shp = pool5.get_shape()
    flattened_shape = shp[1].value * shp[2].value * shp[3].value
    resh1 = tf.reshape(pool5, [-1, flattened_shape], name="resh1")


    fc6 = fc_op(resh1, name="fc6", n_out=4096, p=p)
    fc6_drop = tf.nn.dropout(fc6, keep_prob, name="fc6_drop")

    fc7 = fc_op(fc6_drop, name="fc7", n_out=4096, p=p)
    fc7_drop = tf.nn.dropout(fc7, keep_prob, name="fc7")


    fc8 = fc_op(fc7_drop, name="fc8", n_out=1000, p=p)
    softmax = tf.nn.softmax(fc8)
    prediction = tf.argmax(softmax, 1)
    return prediction, softmax, fc8, p


def time_tensorflow_run(session, target, feed, info_string):
    num_step_burn_in = 10
    total_duration = 0.0
    total_duration_squared = 0.0

    for i in range(num_batches + num_step_burn_in):
        start_time = time.time()
        _ = session.run(target, feed_dict=feed)
        duration = time.time() - start_time
        if i >= num_step_burn_in:
            if not i % 10:
                print('%s: step %d, duration = %.3f' %
                      (datatime.now(), i - num_step_burn_in, duration))
            total_duration += duration
            total_duration_squared += duration * duration


    mn = total_duration / num_batches
    vr = total_duration_squared / num_batches - mn * mn
    sd = math.sqrt(vr)
    print('%s: %s across %d step, %.3f +/- %.3f sec / batch' %
          (datatime.now(), info_string, num_batches, mn, sd))


def run_benchmark():
    with tf.Graph().as_default():
        image_size = 224

        images = tf.Variable(tf.random_normal([batch_size, image_size, image_size, 3],
                                              dtype=tf.float32, stddev=1e-1))

        keep_prob = tf.placeholder(tf.float32)
        prediction, softmax, fc8, p = inference_op(images, keep_prob)

        init = tf.global_variables_initializer()
        sess = tf.Sessin()
        sess.run(init)

        time_tensorflow_run(sess, prediction, {keep_prob: 1.0}, "Forward")
        objective = tf.nn.l2_loss(fc8)
        grad = tf.gradients(objective, p)
        time_tensorflow_run(sess, grad, {keep_prob: 0.5}, "Forward-backward")


batch_size = 32
num_batches = 100

run_benchmark()