from datetime import datetime
import math
import time
import tensorflow as tfbatch_size=32
num_batches=100# 该函数接受一个tensor作为输入，并显示其名称和tensor尺寸
# 目的是展示每一个卷积层或池化层输出的tensor尺寸
def print_activations(t):print(t.op.name, ' ', t.get_shape().as_list())# 该函数接受image作为输入，返回第5个池化层及parameters（AlexNet中所有需要训练的模型参数）
def inference(images):parameters = []# conv1with tf.name_scope('conv1') as scope:kernel = tf.Variable(tf.truncated_normal([11, 11, 3, 64], dtype=tf.float32,   # 截断的正态分布函数初始化卷积核kernelstddev=1e-1), name='weights')conv = tf.nn.conv2d(images, kernel, [1, 4, 4, 1], padding='SAME')biases = tf.Variable(tf.constant(0.0, shape=[64], dtype=tf.float32),trainable=True, name='biases')bias = tf.nn.bias_add(conv, biases)conv1 = tf.nn.relu(bias, name=scope)print_activations(conv1)parameters += [kernel, biases]# pool1lrn1 = tf.nn.lrn(conv1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='lrn1') # LRN层，depth_radius设为4。其它经典CNN不适用LRNpool1 = tf.nn.max_pool(lrn1,ksize=[1, 3, 3, 1],strides=[1, 2, 2, 1],padding='VALID',name='pool1')print_activations(pool1)# conv2with tf.name_scope('conv2') as scope:kernel = tf.Variable(tf.truncated_normal([5, 5, 64, 192], dtype=tf.float32,stddev=1e-1), name='weights')conv = tf.nn.conv2d(pool1, kernel, [1, 1, 1, 1], padding='SAME')biases = tf.Variable(tf.constant(0.0, shape=[192], dtype=tf.float32),trainable=True, name='biases')bias = tf.nn.bias_add(conv, biases)conv2 = tf.nn.relu(bias, name=scope)parameters += [kernel, biases]print_activations(conv2)# pool2lrn2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='lrn2')pool2 = tf.nn.max_pool(lrn2,ksize=[1, 3, 3, 1],strides=[1, 2, 2, 1],padding='VALID',name='pool2')print_activations(pool2)# conv3with tf.name_scope('conv3') as scope:kernel = tf.Variable(tf.truncated_normal([3, 3, 192, 384],dtype=tf.float32,stddev=1e-1), name='weights')conv = tf.nn.conv2d(pool2, kernel, [1, 1, 1, 1], padding='SAME')biases = tf.Variable(tf.constant(0.0, shape=[384], dtype=tf.float32),trainable=True, name='biases')bias = tf.nn.bias_add(conv, biases)conv3 = tf.nn.relu(bias, name=scope)parameters += [kernel, biases]print_activations(conv3)# conv4with tf.name_scope('conv4') as scope:kernel = tf.Variable(tf.truncated_normal([3, 3, 384, 256],dtype=tf.float32,stddev=1e-1), name='weights')conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding='SAME')biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),trainable=True, name='biases')bias = tf.nn.bias_add(conv, biases)conv4 = tf.nn.relu(bias, name=scope)parameters += [kernel, biases]print_activations(conv4)# conv5with tf.name_scope('conv5') as scope:kernel = tf.Variable(tf.truncated_normal([3, 3, 256, 256],dtype=tf.float32,stddev=1e-1), name='weights')conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding='SAME')biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),trainable=True, name='biases')bias = tf.nn.bias_add(conv, biases)conv5 = tf.nn.relu(bias, name=scope)parameters += [kernel, biases]print_activations(conv5)# pool5pool5 = tf.nn.max_pool(conv5,ksize=[1, 3, 3, 1],strides=[1, 2, 2, 1],padding='VALID',name='pool5')print_activations(pool5)return pool5, parameters

# 该函数用于评估AlexNet每轮计算的时间
def time_tensorflow_run(session, target, info_string):
#  """Run the computation to obtain the target tensor and print timing stats.
#
#  Args:
#    session: the TensorFlow session to run the computation under.
#    target: the target Tensor that is passed to the session's run() function.
#    info_string: a string summarizing this run, to be printed with the stats.
#
#  Returns:
#    None
#  """num_steps_burn_in = 10total_duration = 0.0total_duration_squared = 0.0for i in range(num_batches + num_steps_burn_in):start_time = time.time()_ = session.run(target)duration = time.time() - start_timeif 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 += durationtotal_duration_squared += duration * durationmn = total_duration / num_batchesvr = total_duration_squared / num_batches - mn * mnsd = math.sqrt(vr)print ('%s: %s across %d steps, %.3f +/- %.3f sec / batch' %(datetime.now(), info_string, num_batches, mn, sd))# 主函数。输入是随机生成的图片
def run_benchmark():
#  """Run the benchmark on AlexNet."""
    with tf.Graph().as_default():# Generate some dummy images.image_size = 224# Note that our padding definition is slightly different the cuda-convnet.# In order to force the model to start with the same activations sizes,# we add 3 to the image_size and employ VALID padding above.images = tf.Variable(tf.random_normal([batch_size,image_size,image_size, 3],dtype=tf.float32,stddev=1e-1))# Build a Graph that computes the logits predictions from the# inference model.pool5, parameters = inference(images)# Build an initialization operation.init = tf.global_variables_initializer()# Start running operations on the Graph.config = tf.ConfigProto()config.gpu_options.allocator_type = 'BFC'sess = tf.Session(config=config)sess.run(init)# Run the forward benchmark.前向的评估time_tensorflow_run(sess, pool5, "Forward")# Add a simple objective so we can calculate the backward pass.训练过程的评估objective = tf.nn.l2_loss(pool5)# Compute the gradient with respect to all the parameters.grad = tf.gradients(objective, parameters)# Run the backward benchmark.time_tensorflow_run(sess, grad, "Forward-backward")run_benchmark()