import tensorflow as tfimport numpy as np

def add_layer(inputs,in_size,out_size,activation_function=None):　　　　"""initialize the Weights and biases"""　　Weights=tf.Variable(tf.random_normal([in_size,out_size]))　　biases=tf.Variable(tf.zeros([1,out_size])+0.1)　　　　W_biases=tf.matmul(inputs,Weights)+biases　　if activation_function is None:　　　　outputs=W_biases　　else:　　　　outputs=activation_function(W_biases)　　return outputs

x_data=np.linspace(-1,1,300)[:,newaxis]noise=np.random.normal(0,0.05,x_data.shape)y_data=np.square(x_data)-0.5+noise

x_batch=tf.placeholder(tf.float32,[None,1])y_batch=tf.placeholder(tf.float32,[None,1])

l1=add_layer(xs,1,10,activation_function=tf.nn.relu)prediction=(l1,10,1,activation_function=None)loss=tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))

train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init=tf.initialize_all_variables()sess=tf.Session()sess.run(init)

for i in range(1500):　　sess.run(train_step,feed_dict={xs:x_data,ys:y_data})　　if i%100==0:　　　　print(sess.run(loss,feen_dict={xs:x_data,ys:y_data}))