Tensorflow实现VGGNet

from datetime import datetimeimport mathimport timeimport tensorflow as tf#创建卷积层并把本层的参数存入参数列表#input_op是输入的tennsor，name是这一层的名称,kh是kernel height即卷积核的高，kw是kernel width#即卷积核的宽，n_out是卷积核数量即输出通道数，dh是步长的高，dw是步长的宽，p是参数列表def conv_op(input_op, name, kh, kw, n_out, dh, dw, p):    n_in = input_op.get_shape()[-1].value#获得通道数    with tf.name_scope(name) as scope:#使用scope避免命名冲突；注释1        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#全连接层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())#将biases赋一个较小值0.1，避免dead neuron        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#最大池化层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#第一层Input_op 224*224*3,output_op 224*24*64#第二层输入输出都为224*24*64# max_pool-- outputs 112x112x64 2*2    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#连接一个隐含节点数为4096的全连接层，激活函数为ReLU#连接一个Dropout层，在训练时节点保留率为0.5，预测时为1.0    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#评测函数#并不使用数据集训练，而是使用随机图片数据测试前馈和反馈的计算耗时def time_tensorflow_run(session, target, feed, info_string):#每轮计算时间    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 = 32num_batches = 100run_benchmark()

    注释1：Xavier初始化器。如果深度学习模型的权重初始化得太小，那信号将在每层间传递时逐渐缩小而难以产生作用，但如果权重初始化得太大，那信号将在每层间传递时逐渐放大并导致发散和失效。而Xavier初始化器做的事情就是让权重被初始化得不大不小，正好合适。即Xavier就是让权重满足0均值，同时方差为2/(n_in+n_out)