import tensorflow as tf
from numpy.random import RandomState
def test():
print("test start")
#定义训练数据batch的大小
batch_size = 8
#定义神经网络参数
w1 = tf.Variable(tf.random_normal([2,3],stddev = 1 , seed = 1))
w2 = tf.Variable(tf.random_normal([3,1],stddev = 1 , seed = 1))
x = tf.placeholder(tf.float32,shape = (None,2),name="x-input")
y_ = tf.placeholder(tf.float32,shape = (None,1),name="y_input")
#定义神经网络向前传播的过程
a = tf.matmul(x,w1)
y = tf.matmul(a,w2)
#定义损失函数(没看懂)
cross_entropy = -tf.reduce_mean( y_ * tf.log( tf.clip_by_value( y , 1e-10 , 1.0 )))
train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy)
rdm = RandomState(1)
dataset_size = 128
X = rdm.rand(dataset_size,2)
print(X)
Y = [ [int( x1 + x2 < 1)] for (x1, x2) in X]
print(Y)
#创建会话
with tf.Session() as sess:
#初始化变量;
init_op = tf.initialize_all_variables()
sess.run(init_op)
print( sess.run(w1) )
print( sess.run(w2) )
#设定训练次数;
step = 5000
for i in range(step):
start = (i * batch_size) % dataset_size
end = min(start+batch_size,dataset_size)
sess.run( train_step , feed_dict = { x : X[ start : end ] , y_ : Y [start : end ]})
if i % 1000 == 0:
total_cross_entropy = sess.run( cross_entropy,feed_dict = { x : X ,y_: Y})
print ("After %d tranining setp(s),cross entropy on all data is %g"% ( i , total_cross_entropy) )
print( sess.run(w1) )
print( sess.run(w2) )
if __name__=="__main__":
test()