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。
fromdatetimeimportdatetime
importmath
importtime
importtensorflowastf
batch_size=32
num_batches=100
defprint_activations(t):
print(t.op.name,'',t.get_shape().as_list())
definference(images):
parameters=[]
withtf.name_scope('conv1')asscope:
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)
withtf.name_scope('conv2')asscope:
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)
withtf.name_scope('conv3')asscope:
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)
withtf.name_scope('conv4')asscope:
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)
withtf.name_scope('conv5')asscope:
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)
returnpool5,parameters
deftime_tensorflow_run(session,target,info_string):
num_steps_burn_in=10
total_duration=0.0
total_duration_squared=0.0
foriinrange(num_batches+num_steps_burn_in):
start_time=time.time()
_=session.run(target)
duration=time.time()-start_time
ifi>=num_steps_burn_in:
ifnoti%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:%sacross%dsteps,%.3f+/-%.3fsec/batch'%(datetime.now(),info_string,num_batches,mn,sd))
defrun_benchmark():
withtf.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GTXTITANX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。
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持毛票票。