1.drop_out的原理为:通过将某神经元的输出设置为0,达到使其失活的效果,消除网络中过分依赖某个神经元
2.过拟合一般出现在网络过分复杂,且训练数据较少的情况,数据较少而未知参数太多,则较易产生过拟合
3.核心代码:layer1=tf.nn.dropout(layer1,drop_out)
#3-3 MNIst数据集使用drop-out提升准确率,消除部分过拟合
import tensorflow
as tf;
import numpy
as np;
from tensorflow.examples.tutorials.mnist
import input_data
#原始数据
mnist
=input_data.read_data_sets(
"MNIST_data",
one_hot
=
True)
x
=tf.placeholder(tf.float32,
shape
=[
None,
784])
y
=tf.placeholder(tf.float32,
shape
=[
None,
10])
drop_out
=tf.placeholder(tf.float32)
batch_size
=
100;
n_batch
=mnist.train.num_examples
//batch_size
#获取共有多少批次
#创建神经网络计算图
w1
=tf.Variable(tf.truncated_normal(
shape
=[
784,
1000],
stddev
=
0.1))
b1
=tf.Variable(tf.constant(
0.1,
shape
=[
1000]))
layer1
=tf.nn.relu(tf.matmul(x,w1)
+b1)
layer1
=tf.nn.dropout(layer1,drop_out)
w2
=tf.Variable(tf.truncated_normal(
shape
=[
1000,
2000],
stddev
=
0.1))
b2
=tf.Variable(tf.constant(
0.1,
shape
=[
2000]))
layer2
=tf.nn.relu(tf.matmul(layer1,w2)
+b2)
layer2
=tf.nn.dropout(layer2,drop_out)
w3
=tf.Variable(tf.truncated_normal(
shape
=[
2000,
10],
stddev
=
0.1))
b3
=tf.Variable(tf.constant(
0.1,
shape
=[
10]))
layer3
=tf.nn.relu(tf.matmul(layer2,w3)
+b3)
layer3
=tf.nn.dropout(layer3,drop_out)
prediction
=tf.nn.softmax(layer3)
#定义损失函数
loss
=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits
=prediction,
labels
=y))
train_step
=tf.train.GradientDescentOptimizer(
0.2).minimize(loss)
currect_rate
=tf.reduce_mean(tf.cast(tf.equal(tf.arg_max(y,
1),tf.arg_max(prediction,
1)),tf.float32))
init
=tf.global_variables_initializer()
with tf.Session()
as sess:
sess.run(init)
for epoch
in
range(
1221):
for batch
in
range(n_batch):
x_batch,y_batch
=mnist.train.next_batch(batch_size)
sess.run(train_step,
feed_dict
={x:x_batch,y:y_batch,drop_out:
0.7})
acc
=sess.run(currect_rate,
feed_dict
={x:mnist.test.images,y:mnist.test.labels,drop_out:
1.0})
acc_train
=sess.run(currect_rate,
feed_dict
={x:mnist.train.images,y:mnist.train.labels,drop_out:
1.0})
print(
"epoch:
{0}
,acc:
{1}
,train_acc:
{1}
".format(epoch,acc,acc_train))