VGGNet介绍

VGGNet介绍

1 简要概括

    VGGNet由牛津大学计算机视觉组合和Google DeepMind公司研究员一起研发的深度卷积神经网络。它探索了卷积神经网络的深度和其性能之间的关系，通过反复的堆叠3*3的小型卷积核和2*2的最大池化层，成功的构建了16~19层深的卷积神经网络。VGGNet获得了ILSVRC 2014年比赛的亚军和定位项目的冠军，在top5上的错误率为7.5%。目前为止，VGGNet依然被用来提取图像的特征。

2 创新点

    VGGNet全部使用3*3的卷积核和2*2的池化核，通过不断加深网络结构来提升性能。网络层数的增长并不会带来参数量上的爆炸，因为参数量主要集中在最后三个全连接层中。同时，两个3*3卷积层的串联相当于1个5*5的卷积层，3个3*3的卷积层串联相当于1个7*7的卷积层，即3个3*3卷积层的感受野大小相当于1个7*7的卷积层。但是3个3*3的卷积层参数量只有7*7的一半左右，同时前者可以有3个非线性操作，而后者只有1个非线性操作，这样使得前者对于特征的学习能力更强。

    使用1*1的卷积层来增加线性变换，输出的通道数量上并没有发生改变。这里提一下1*1卷积层的其他用法，1*1的卷积层常被用来提炼特征，即多通道的特征组合在一起，凝练成较大通道或者较小通道的输出，而每张图片的大小不变。有时1*1的卷积神经网络还可以用来替代全连接层。

    其他小技巧。VGGNet在训练的时候先训级别A的简单网络，再复用A网络的权重来初始化后面的几个复杂模型，这样收敛速度更快。VGGNet作者总结出LRN层作用不大，越深的网络效果越好，1*1的卷积也是很有效的，但是没有3*3的卷积效果好，因为3*3的网络可以学习到更大的空间特征。

3 网络结构

    VGGNet的网络结构如下图所示。VGGNet包含很多级别的网络，深度从11层到19层不等，比较常用的是VGGNet-16和VGGNet-19。VGGNet把网络分成了5段，每段都把多个3*3的卷积网络串联在一起，每段卷积后面接一个最大池化层，最后面是3个全连接层和一个softmax层。

4 代码实现

代码实现参考自tensorflow的开源实现

#%%
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
from datetime import datetime
import math
import time
import tensorflow as tf

def conv_op(input_op, name, kh, kw, n_out, dh, dw, p):
    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.xavier_initializer_conv2d())
        conv = tf.nn.conv2d(input_op, kernel, (1, dh, dw, 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, name=scope)
        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.xavier_initializer())
        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 = []
    # assume input_op shape is 224x224x3

    # block 1 -- outputs 112x112x64
    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)

    # block 2 -- outputs 56x56x128
    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",   kh=2, kw=2, dh=2, dw=2)

    # # block 3 -- outputs 28x28x256
    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",   kh=2, kw=2, dh=2, dw=2)

    # block 4 -- outputs 14x14x512
    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",   kh=2, kw=2, dh=2, dw=2)

    # block 5 -- outputs 7x7x512
    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",   kh=2, kw=2, dw=2, dh=2)

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

    # fully connected
    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_drop")

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


def time_tensorflow_run(session, target, feed, info_string):
    num_steps_burn_in = 10
    total_duration = 0.0
    total_duration_squared = 0.0
    for i in range(num_batches + num_steps_burn_in):
        start_time = time.time()
        _ = session.run(target, feed_dict=feed)
        duration = time.time() - start_time
        if i >= num_steps_burn_in:
            if not i % 10:
                print ('%s: step %d, duration = %.3f' %
                       (datetime.now(), i - num_steps_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 steps, %.3f +/- %.3f sec / batch' %
           (datetime.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)
        predictions, softmax, fc8, p = inference_op(images, keep_prob)

        init = tf.global_variables_initializer()

        config = tf.ConfigProto()
        config.gpu_options.allocator_type = 'BFC'
        sess = tf.Session(config=config)
        sess.run(init)

        time_tensorflow_run(sess, predictions, {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()

      

5 参考文献

[1]黄文坚,唐源.TensorFlow实战[M].北京:电子工业出版社,2017.

[2] https://arxiv.org/abs/1409.1556v6

[3]https://github.com/machrisaa/tensorflow-vgg