Mutiple-layer_perceptron(MLP)

# coding=utf-8
from tensorflow.examples.tutorials.mnist import  input_data
import tensorflow as tf
mnist = input_data.read_data_sets('/home/star/MNIST_data/', one_hot= True)
sess = tf.InteractiveSession()
#forward
in_units = 784
h1_units = 300
w1 = tf.Variable(tf.truncated_normal([in_units, h1_units], stddev= 0.1))
b1 = tf.Variable(tf.zeros([h1_units]))
w2 = tf.Variable(tf.zeros([h1_units, 10]))
b2 = tf.Variable(tf.zeros([10]))
x = tf.placeholder(dtype=tf.float32, shape=[None, in_units])
#keep_prob(0, 1)
keep_prob = tf.placeholder(tf.float32)
#Relu as activition funtion
hidden1 = tf.nn.relu(tf.matmul(x,w1)+b1)
#Dropout is added
hidden1_drop = tf.nn.dropout(hidden1, keep_prob)
y = tf.nn.softmax(tf.matmul(hidden1_drop, w2)+b2)
#loss
y_ = tf.placeholder(dtype= tf.float32, shape=[None,10])
cross_entropy = tf.reduce_mean(tf.reduce_sum(-y_*tf.log(y),reduction_indices=[1]))
train_step = tf.train.AdagradOptimizer(0.3).minimize(cross_entropy)

#train
tf.global_variables_initializer().run()
for i in range(3000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    train_step.run({x: batch_xs, y_:batch_ys, keep_prob: 0.75})

#test
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, dtype= tf.float32))
print(accuracy.eval({x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0}))