学习笔记3

#一个简单的程序
import tensorflow as tf

#定义网络结构和前向传播算法
def get_weight(shape):
    w=tf.Variable()
    return w
def get_bias(shape):
    b=tf.Variable()
    return b
def forward(x,shape):
    w1=get_weight(shape)
    b1=get_bias(shape)
    y1=tf.nn.relu(tf.matmul(x,w1)+b1)

    w2=get_weight(shape)
    b2=get_bias(shape)
    y=tf.matmul(y1,w2)+b2
    return y

#定义损失函数和反向传播算法

#载入数据集X和Y_#

x=tf.placeholder(tf.float32,shape=[None,],name)
y_=tf.placeholder(tf.float32,shape=[None,],name)

loss=tf.reduce_mean(tf.square(y-y_))

train_step=tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(loss)


#生成会话，运行反向传播算法
with tf.Session() as sess:
    init_op=tf.global_variables_initializer()
    sess.run(init_op)
    steps=20000
    batch_size=8
    data_size=128
    for i in range(steps):
        start=(i*batch_size)%data_size
        end=min(start+batch_size,data_szie)

        sess.run(train_step,feed_dict={x:X[start:end],y_:Y_[start:end]})

        if i%200==0:
            loss_val=sess.run(loss,feed_dict={x:X,y_:Y_})
            print "After %d steps,loss is: %g " % (i,loss_val)