算法原理:
VGGNet探索了卷积神经网络深度与其性能之间的关系,通过反复的堆叠3*3的小型卷积核和2*2的最大池化层,VGGNet成功的构建了16-19层深的卷积神经网络。。
VGGNet拥有5段卷积,每一段内有2-3个卷积层,同时尾部会连接一个最大池化
实验代码:
# -*- coding: utf-8 -*-
"""
Created on Tue Jan 23 18:57:20 2018
@author: Administrator
"""
from datetime import datetime
import math
import time
import tensorflow as tf
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
batch_size=32
num_batches=100
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')
biases_init_val=tf.constant(0.0,shape=[n_out],dtype=tf.float32)
biases=tf.Variable(biases_init_val,trainable=True,name='b')
z=tf.nn.bias_add(conv,biases)
activtion=tf.nn.relu(z,name=scope)
p+=[kernel,biases]
return activtion
#全连接层
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_conv2d())
biases_init_val=tf.constant(0.1,shape=[n_out],dtype=tf.float32)
biases=tf.Variable(biases_init_val,trainable=True,name='b')
activtion=tf.nn.relu_layer(input_op,kernel,biases,name=scope)
p+=[kernel,biases]
return activtion
def mpool_op(inout_op,name,kh,kw,dh,dw):
return tf.nn.max_pool(inout_op,ksize=[1,kh,kw,1],
strides=[1,dh,dw,1],padding='SAME',name=name)
def interfence_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,dh=2,dw=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,dh=2,dw=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_3",kh=3,kw=3,n_out=256,dh=1,dw=1,p=p)
pool3=mpool_op(conv3_3,name="pool3",kh=2,kw=2,dh=2,dw=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,dh=2,dw=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,dh=2,dw=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")
#全连接层
fc6=fc_op(resh1,name='fc6',n_out=4096,p=p)
fc6_drop=tf.nn.dropout(fc6,keep_prob,name='fc6_drop')
#全连接层
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_brun_in=10
total_duration=0.0
total_duration_squared=0.0
for i in range(num_batches+num_steps_brun_in):
start_time=time.time()
_=session.run(target,feed_dict=feed)
duration=time.time()-start_time
if i>=num_steps_brun_in:
if not i%10:
print('%s:step %d,duration=%3f'%(datetime.now(),
i-num_steps_brun_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=interfence_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,"forward-backward")
run_benchmark()
遇到的错误:
Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
Found device 0 with properties:
name: GeForce 820M major: 2 minor: 1 memoryClockRate(GHz): 1.25
pciBusID: 0000:01:00.0
totalMemory: 2.00GiB freeMemory: 1.94GiB
Ignoring visible gpu device (device: 0, name: GeForce 820M, pci bus id: 0000:01:00.0, compute capability: 2.1) with Cuda compute capability 2.1. The minimum required Cuda capability is 3.0.
Found device 0 with properties:
name: GeForce 820M major: 2 minor: 1 memoryClockRate(GHz): 1.25
pciBusID: 0000:01:00.0
totalMemory: 2.00GiB freeMemory: 1.94GiB
Ignoring visible gpu device (device: 0, name: GeForce 820M, pci bus id: 0000:01:00.0, compute capability: 2.1) with Cuda compute capability 2.1. The minimum required Cuda capability is 3.0.