Tensorflow實(shí)現(xiàn)AlexNet卷積神經(jīng)網(wǎng)絡(luò)及運(yùn)算時(shí)間評(píng)測(cè)-創(chuàng)新互聯(lián)

本文實(shí)例為大家分享了Tensorflow實(shí)現(xiàn)AlexNet卷積神經(jīng)網(wǎng)絡(luò)的具體實(shí)現(xiàn)代碼，供大家參考，具體內(nèi)容如下

創(chuàng)新互聯(lián)建站堅(jiān)持“要么做到，要么別承諾”的工作理念，服務(wù)領(lǐng)域包括：網(wǎng)站建設(shè)、成都做網(wǎng)站、企業(yè)官網(wǎng)、英文網(wǎng)站、手機(jī)端網(wǎng)站、網(wǎng)站推廣等服務(wù)，滿足客戶于互聯(lián)網(wǎng)時(shí)代的青縣網(wǎng)站設(shè)計(jì)、移動(dòng)媒體設(shè)計(jì)的需求，幫助企業(yè)找到有效的互聯(lián)網(wǎng)解決方案。努力成為您成熟可靠的網(wǎng)絡(luò)建設(shè)合作伙伴！

之前已經(jīng)介紹過了AlexNet的網(wǎng)絡(luò)構(gòu)建了，這次主要不是為了訓(xùn)練數(shù)據(jù)，而是為了對(duì)每個(gè)batch的前饋（Forward）和反饋（backward）的平均耗時(shí)進(jìn)行計(jì)算。在設(shè)計(jì)網(wǎng)絡(luò)的過程中，分類的結(jié)果很重要，但是運(yùn)算速率也相當(dāng)重要。尤其是在跟蹤（Tracking）的任務(wù)中，如果使用的網(wǎng)絡(luò)太深，那么也會(huì)導(dǎo)致實(shí)時(shí)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()

另外有需要云服務(wù)器可以了解下創(chuàng)新互聯(lián)scvps.cn，海內(nèi)外云服務(wù)器15元起步，三天無理由+7*72小時(shí)售后在線，公司持有idc許可證，提供“云服務(wù)器、裸金屬服務(wù)器、高防服務(wù)器、香港服務(wù)器、美國服務(wù)器、虛擬主機(jī)、免備案服務(wù)器”等云主機(jī)租用服務(wù)以及企業(yè)上云的綜合解決方案，具有“安全穩(wěn)定、簡(jiǎn)單易用、服務(wù)可用性高、性價(jià)比高”等特點(diǎn)與優(yōu)勢(shì)，專為企業(yè)上云打造定制，能夠滿足用戶豐富、多元化的應(yīng)用場(chǎng)景需求。

名稱欄目：Tensorflow實(shí)現(xiàn)AlexNet卷積神經(jīng)網(wǎng)絡(luò)及運(yùn)算時(shí)間評(píng)測(cè)-創(chuàng)新互聯(lián)
本文來源：http://muchs.cn/article4/ddhsoe.html

成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián)，為您提供虛擬主機(jī)、企業(yè)建站、用戶體驗(yàn)、網(wǎng)頁設(shè)計(jì)公司、微信小程序、商城網(wǎng)站

廣告

聲明：本網(wǎng)站發(fā)布的內(nèi)容（圖片、視頻和文字）以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主，如果涉及侵權(quán)請(qǐng)盡快告知，我們將會(huì)在第一時(shí)間刪除。文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng)，如需處理請(qǐng)聯(lián)系客服。電話：028-86922220；郵箱：631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載，或轉(zhuǎn)載時(shí)需注明來源： 創(chuàng)新互聯(lián)

成都網(wǎng)站建設(shè)