tensorflow手写数字识别添加来l2正则化

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

x_input=tf.placeholder(dtype=tf.float32,shape=[None,784])
y_input=tf.placeholder(dtype=tf.float32,shape=[None,10])

w1=tf.Variable(tf.truncated_normal([784,1024],mean=0,stddev=0.1))
b1=tf.Variable(tf.zeros([1024])+0.1)
layer1=tf.nn.sigmoid(tf.add(tf.matmul(x_input,w1),b1))
reg1=tf.contrib.layers.l2_regularizer(0.001)(w1)

w2=tf.Variable(tf.truncated_normal([1024,512],mean=0,stddev=0.1))
b2=tf.Variable(tf.zeros([512])+0.1)
layer2=tf.nn.sigmoid(tf.add(tf.matmul(layer1,w2),b2))
reg2=tf.contrib.layers.l2_regularizer(0.001)(w2)

w3=tf.Variable(tf.truncated_normal([512,10],mean=0,stddev=0.1))
b3=tf.Variable(tf.zeros([10])+0.1)
layer3=tf.add(tf.matmul(layer2,w3),b3)
reg3=tf.contrib.layers.l2_regularizer(0.001)(w3)
logit=layer3

regulariztion=reg1+reg2+reg3
loss=tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y_input,logits=logit))+regulariztion
train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)
precise=tf.reduce_mean(tf.cast(tf.equal(tf.argmax(logit,1),tf.argmax(y_input,1)),dtype=tf.float32))


mnist=input_data.read_data_sets("MNIST_data",one_hot=True)
batch_size=1000
n_batch_size=mnist.train.num_examples//batch_size

with tf.Session() as sess:
    init=tf.global_variables_initializer()
    sess.run(init)
    for i in range(10):
        for j in range(n_batch_size):
            x_train_input,y_train_input=mnist.train.next_batch(batch_size)
            x_test_input,y_test_input=mnist.test.next_batch(batch_size)
            sess.run(train_step,feed_dict={x_input:x_train_input,y_input:y_train_input})
            precise_test=sess.run(precise,{x_input:x_train_input,y_input:y_train_input})
            print(precise_test)