Tensorflow学习之卷积神经网络实现（四）

本次主要实现的是VGGNet，这个网络所有的卷积核大小都为3x3，最大池化层都用的2x2的大小，正是由于VGGNet的探索，发现小型的卷积核在效果比5x5,7x7等大卷积核效率（两个3x3的卷积层串联相当于一个5x5的卷积层，即一个像素会跟周围5x5的像素产生关联，但3x3的参数量更少，3x3x2<5x5，并且拥有更多的非线性变换，使得CNN对特征的学习能力更强）差不多的情况下，更有助于网络深度的提升，并且网络结构非常简洁，详细见

下面就实现一个VGG-16，构造出VGGNet网络结构，并评测其forward(inference)耗时和backward(training)耗时

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

def conv_op(input_op,name,kh,kw,n_out,dh,dw,p):
n_in = input_op.get_shape()[-1].value

with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope+"w",shape=[kh,kw,n_in,n_out],dtype=tf.float32,initializer=tf.contrib.layers.xavier_initializer_conv2d())
conv = tf.nn.conv2d(input_op,kernel,(1,dh,dw,1),padding='SAME')
bias_init_val = tf.constant(0.0,shape=[n_out],dtype=tf.float32)
biases = tf.Variable(bias_init_val,trainable=True,name='b')
z = tf.nn.bias_add(conv,biases)
activation = tf.nn.relu(z,name=scope)
p += [kernel,biases]
return activation
def fc_op(input_op,name,n_out,p):
n_in = input_op.get_shape()[-1].value
with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope+"w",shape = [n_in,n_out],dtype = tf.float32,initializer = tf.contrib.layers.xavier_initializer())
biases = tf.Variable(tf.constant(0.1,shape=[n_out],dtype=tf.float32),name = 'b')
activation = tf.nn.relu_layer(input_op,kernel,biases,name=scope)
p += [kernel,biases]
return activation
def mpool_op(input_op,name,kh,kw,dh,dw):
return tf.nn.max_pool(input_op,ksize=[1,kh,kw,1],strides=[1,dh,dw,1],padding='SAME',name=name)

def inference_op(input_op,keep_prob):
p = []
conv1_1 = conv_op(input_op,name="conv1_1",kh=3,kw=3,n_out=64,dh=1,dw=1,p=p)
conv1_2 = conv_op(conv1_1,name="conv1_2",kh=3,kw=3,n_out=64,dh=1,dw=1,p=p)
pool1 = mpool_op(conv1_2,name="pool1",kh=2,kw=2,dw=2,dh=2)

conv2_1 = conv_op(pool1,name="conv2_1",kh=3,kw=3,n_out=128,dh=1,dw=1,p=p)
conv2_2 = conv_op(conv2_1,name="conv2_2",kh=3,kw=3,n_out=128,dh=1,dw=1,p=p)
pool2 = mpool_op(conv2_2,name="pool2",kh=2,kw=2,dw=2,dh=2)

conv3_1 = conv_op(pool2, name="conv3_1", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_2 = conv_op(conv3_1, name="conv3_2", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_3 = conv_op(conv3_2, name="conv3_2", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
pool3 = mpool_op(conv3_3, name="pool3", kh=2, kw=2, dw=2, dh=2)

conv4_1 = conv_op(pool3, name="conv4_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_2 = conv_op(conv4_1, name="conv4_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_3 = conv_op(conv4_2, name="conv4_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool4 = mpool_op(conv4_3, name="pool4", kh=2, kw=2, dw=2, dh=2)

conv5_1 = conv_op(pool4, name="conv5_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_2 = conv_op(conv5_1, name="conv5_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_3 = conv_op(conv5_2, name="conv5_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool5 = mpool_op(conv5_3, name="pool5", kh=2, kw=2, dw=2, dh=2)

shp = pool5.get_shape()
flattened_shape = shp[1].value * shp[2].value * shp[3].value
resh1 = tf.reshape(pool5,[-1,flattened_shape],name = "resh1")

fc6 = fc_op(resh1,name="fc6",n_out=4096,p=p)
fc6_drop = tf.nn.dropout(fc6,keep_prob,name="fc6_drop")

fc7 = fc_op(fc6_drop,name = "fc7",n_out = 4096,p=p)
fc7_drop = tf.nn.dropout(fc7,keep_prob,name="fc7_drop")

fc8 = fc_op(fc7_drop,name="fc8",n_out=1000,p=p)

softmax = tf.nn.softmax(fc8)

predictions = tf.argmax(softmax,1)

return predictions,softmax,fc8,p

def time_tensorflow_run(session,target,feed,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,feed_dict=feed)
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))

keep_prob = tf.placeholder(tf.float32)
predictions,softmax,fc8,p = inference_op(images,keep_prob)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

time_tensorflow_run(sess,predictions,{keep_prob:1.0},"Forward")
objective = tf.nn.l2_loss(fc8)
grad = tf.gradients(objective,p)
time_tensorflow_run(sess,grad,{keep_prob:0.5},"Forward-backward")
batch_size = 32
num_batches = 100
run_benchmark()

结果如下：

/usr/local/Cellar/anaconda/bin/python /Users/new/Documents/JLIFE/Tensorflow/training/mnist_train.py
2017-09-01 14:22:53.286299: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-09-01 14:22:53.286338: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-09-01 14:22:53.286345: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-09-01 14:22:53.286352: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2017-09-01 14:30:53.298980:step 0,duration = 29.278
2017-09-01 14:36:11.613342:step 10,duration = 37.400

Process finished with exit code 137 (interrupted by signal 9: SIGKILL)

由于运行时间实在太长了，，Mac CPU无奈啊。。看着别人跑的forward计算平均每个batch的耗时为0.152s，相比同样batch size的AlexNet的0.026s(如果无LRN层则是0.007s)，backward求解梯度时，每个batch的平均耗时达到了0.617s，相比于AlexNet的0.078s也高了很多，竟无语凝噎。。。不过这说明了VGGNet-16的计算复杂度还是比AlexNet确实高了不少，不过根据比赛结果也能看到准确率带来了很大的提升。VGGNet的模型参数虽然比AlexNet多，但是反而只需要较少的迭代次数就可以收敛，主要原因是更深的网络和更小的卷积核带来的隐式的正则化效果。