代码及注释
from datetime import datetime
import math
import time
import tensorflow as tf
c:\program files\python\python36\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
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()
cpu运行结果:
conv1 [32, 56, 56, 64]
conv1/pool1 [32, 27, 27, 64]
conv2 [32, 27, 27, 192]
conv2/pool2 [32, 13, 13, 192]
conv3 [32, 13, 13, 384]
conv4 [32, 13, 13, 256]
conv5 [32, 13, 13, 256]
conv5/pool5 [32, 6, 6, 256]
2018-04-07 22:04:02.078231: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:03.381361: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:04.645201: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:05.934559: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:07.261441: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:08.600831: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:09.864171: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:11.132014: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:12.440383: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:13.715730: Forward across 100 steps, 0.000 +/- 0.000 sec / batch
2018-04-07 22:04:15.047116:step 0, duration = 1.330
2018-04-07 22:04:15.047616: Forward across 100 steps, 0.013 +/- 0.132 sec / batch
2018-04-07 22:04:16.427534: Forward across 100 steps, 0.027 +/- 0.190 sec / batch
2018-04-07 22:04:17.825463: Forward across 100 steps, 0.041 +/- 0.234 sec / batch
2018-04-07 22:04:19.149843: Forward across 100 steps, 0.054 +/- 0.266 sec / batch
2018-04-07 22:04:20.465219: Forward across 100 steps, 0.067 +/- 0.294 sec / batch
2018-04-07 22:04:21.931704: Forward across 100 steps, 0.082 +/- 0.325 sec / batch
2018-04-07 22:04:23.300113: Forward across 100 steps, 0.096 +/- 0.349 sec / batch
2018-04-07 22:04:24.705568: Forward across 100 steps, 0.110 +/- 0.373 sec / batch
2018-04-07 22:04:26.021455: Forward across 100 steps, 0.123 +/- 0.391 sec / batch
2018-04-07 22:04:27.387037: Forward across 100 steps, 0.137 +/- 0.410 sec / batch
2018-04-07 22:04:28.670890:step 10, duration = 1.283
2018-04-07 22:04:28.671891: Forward across 100 steps, 0.149 +/- 0.425 sec / batch
2018-04-07 22:04:29.951741: Forward across 100 steps, 0.162 +/- 0.440 sec / batch
2018-04-07 22:04:31.253607: Forward across 100 steps, 0.175 +/- 0.454 sec / batch
2018-