第五天
tf.where 和tf.greater的用法
import tensorflow as tf
v1=tf.constant([1.0,2.0,3.0,4.0])
v2=tf.constant([4.0,3.0,2.0,1.0])
sess=tf.InteractiveSession()
print (tf.greater(v1,v2).eval())
print (tf.where(tf.greater(v1,v2),v1,v2).eval())
sess.close()
tf.where前面是条件,后面是true,false的选择
自定义损失函数
import tensorflow as tf
from numpy.random import RandomState
batch_size=8
x=tf.placeholder(tf.float32,shape=(None,2),name='x-input')
y_=tf.placeholder(tf.float32,shape=(None,1),name='y-input')
w1=tf.Variable(tf.random_normal([2,1],stddev=1,seed=1))
y=tf.matmul(x,w1)
loss_less=10
loss_more=1
loss=tf.reduce_sum(tf.where(tf.greater(y,y_),(y-y_)*loss_more,(y_-y)*loss_less))#自定义损失函数
train_step=tf.train.AdamOptimizer(0.001).minimize(loss)#目标让损失函数尽量小
rdm=RandomState(1)
dataset_size=128
X=rdm.rand(dataset_size,2)
Y=[[x1+x2+rdm.rand()/10.0-0.05] for (x1,x2) in X]
with tf.Session() as sess:
init_op=tf.initialize_all_variables()
sess.run(init_op)
STEPS=5000
for i in range(STEPS):
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]})
print(sess.run(w1))
输出:
[[ 1.01934695]
[ 1.04280889]]
在预测商品销量时,预测多了,损失制造成本,预测少了,损失销售成本。如果成本1元,销售利润10元,则预测少了,则损失更多。