Tensorflow实现AlexNet卷积神经网络及运算时间评测

本文实例为大家分享了Tensorflow实现AlexNet卷积神经网络的具体实现代码，供大家参考，具体内容如下

之前已经介绍过了AlexNet的网络构建了，这次主要不是为了训练数据，而是为了对每个batch的前馈（Forward）和反馈（backward）的平均耗时进行计算。在设计网络的过程中，分类的结果很重要，但是运算速率也相当重要。尤其是在跟踪（Tracking）的任务中，如果使用的网络太深，那么也会导致实时性不好。

from datetime import datetime
import math
import time
import tensorflow as tf

batch_size = 32
num_batches = 100

def print_activations(t):
 print(t.op.name, '', t.get_shape().as_list())

def inference(images):
 parameters = []

 with tf.name_scope('conv1') as scope:
  kernel = tf.Variable(tf.truncated_normal([11, 11, 3, 64], dtype = tf.float32, stddev = 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]

  lrn1 = tf.nn.lrn(conv1, 4, bias = 1.0, alpha = 0.001 / 9, beta = 0.75, name = 'lrn1')
  pool1 = tf.nn.max_pool(lrn1, ksize = [1, 3, 3, 1], strides = [1, 2, 2, 1], padding = 'VALID', name = 'pool1')
  print_activations(pool1)

 with 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)

  lrn2 = tf.nn.lrn(conv2, 4, bias = 1.0, alpha = 0.001 / 9, 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)

 with 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)

 with 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)

 with 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)

  pool5 = 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

def time_tensorflow_run(session, target, 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)
  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))
  pool5, parameters = inference(images)

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

  time_tensorflow_run(sess, pool5, "Forward")

  objective = tf.nn.l2_loss(pool5)
  grad = tf.gradients(objective, parameters)
  time_tensorflow_run(sess, grad, "Forward-backward")


run_benchmark()

这里的代码都是之前讲过的，只是加了一个计算时间和现实网络的卷积核的函数，应该很容易就看懂了，就不多赘述了。我在GTX TITAN X上前馈大概需要0.024s, 反馈大概需要0.079s。哈哈，自己动手试一试哦。