添加层

def add_layer(inputs,in_size,out_size,activation_function=None): #添加神经层

    Weights=tf.Variable(tf.random_normal([in_size,outsize]))  #行 列

    biases=tf.Variable(tf.zeros([1.out_size])+0.1)

    Wx_plus_b=tf.matmul(inputs,Weights)+biases #预测出来的值（未激活）

    if activation_function is None:

        outputs=Wx_plus_b

    else:

        outputs=activation_function(Wx_plus_b)

    return outputs

建造神经网络

x_data=np.linsapace(-1,1,300)[:,np.newaxis]

noise=np.random.normal(0,0.05,x_data.shape) #噪声

y_data=np.square(x_data)-0.5+noise

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

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

## input layer 1

## hidden layer 10

l1=add_layer(xs,1,10,activation_function=tf.tf.nn.relu)

## output layer

prediction=add_layer(ys,10,1,activation_function=None)

loss=tf.reduce_mean(tf.reduce_sum(tf.square(y_data-prediction),

                    reduction_indices=[1])) ##对每一个误差求和 再求平均

train_step=tf.train.GradientDeascentOptimizier(0.1).minimize(loss)#optimizer的作用是用0.1的学习率减少loss

init=tf.initialize_all_variables()

sess=tf.Session()

sess.run(init)  # 开始进行运算

for i in range(1000):

    sess.run(train_step,feed_dict={xs:x_data,ys:y_data})

    if i%50==0:

        print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))