2018-08-07VGGNet-16实现详解
A结构
B代码
A结构:
结构为8段。(不包含LRN与池化层)
conv1_1+conv1_2+pool1 ----->conv2_1+conv2_2+pool2----->conv3_1+conv3_2+conv3_3+pool3----->conv4_1+conv4_2+conv4_3+pool4------>conv5_1+conv5_2+conv5_3+pool5---->3个全连接(fc6&dropout---->fc7&dropout---->fc8)
其中输入结构【32,224,224,3】其中32为batchsize,224x224是图像大小,深度为3
conv1_1输出的结构【32,224,224,64】
pool1输出的结构【32,112,112,64】
也就是说 第一段统称co4nv1输出的结构是【32,112,112,64】
conv2输出的结构【32,56,56,128】
conv3输出的结构【32,28,28,256】
conv4输出的结构【32,14,14,512】
conv5输出的结构【32,7,7,512】一共25088个向量
fc6 4096
fc7 4096
fc8 1000
从上面结构也可以看出,前四层每一段卷积都将边长缩小一半,输出通道翻倍。
上述中
卷积结构【3,3,,64】,步长结构【1,1,1,1】
卷积结构【3,3,,64】,步长结构【1,1,1,1】
池化结构【1,2,2,1】,步长结构【1,2,2,1】
卷积结构【3,3,,128】,步长结构【1,1,1,1】
卷积结构【3,3,,128】,步长结构【1,1,1,1】
池化结构【1,2,2,1】,步长结构【1,2,2,1】
卷积结构【3,3,,256】,步长结构【1,1,1,1】
卷积结构【3,3,,256】,步长结构【1,1,1,1】
卷积结构【3,3,_,256】,步长结构【1,1,1,1】
池化结构【1,2,2,1】,步长结构【1,2,2,1】
卷积结构【3,3,,512】,步长结构【1,1,1,1】
卷积结构【3,3,,512】,步长结构【1,1,1,1】
卷积结构【3,3,_,512】,步长结构【1,1,1,1】
池化结构【1,2,2,1】,步长结构【1,2,2,1】
卷积结构【3,3,,512】,步长结构【1,1,1,1】
卷积结构【3,3,,512】,步长结构【1,1,1,1】
卷积结构【3,3,_,512】,步长结构【1,1,1,1】
池化结构【1,2,2,1】,步长结构【1,2,2,1】
全链接3层节点分别4096,4096,1000。到这里,是不是可以根据所有信息自己实现代码了呢~
B代码:
测试结果:
书 GPU:每10步0.15分钟
我CPU:每10步26分钟
from datetime import datetime
import math
import time
import tensorflow as tf
#用来创建卷积层并把参数存入参数列表
#输入的tensor
#这一层的名字
#kh是卷积核的高
#kw是卷积核的宽
#n_out是卷积核的数量,输出通道数
#dh是步长的高
#dw是步长的宽
#p是参数列表
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 = []
# assume input_op shape is 224x224x3
# block 1 -- outputs 112x112x64
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)
# block 2 -- outputs 56x56x128
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)
# # block 3 -- outputs 28x28x256
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)
# block 4 -- outputs 14x14x512
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)
# block 5 -- outputs 7x7x512
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)
# flatten
shp = pool5.get_shape()
flattened_shape = shp[1].value * shp[2].value * shp[3].value
resh1 = tf.reshape(pool5, [-1, flattened_shape], name="resh1")
# fully connected
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()
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
sess = tf.Session(config=config)
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()