tensorflow 简单样例与自定义损失函数

"""
一个简单的完整神经网络样例
"""

import tensorflow as tf
from numpy.random import RandomState
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'


batch_size=8
w2=tf.Variable(tf.random_normal([3,1],stddev=1,seed=1))
w1=tf.Variable(tf.random_normal([2,3],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')
a=tf.matmul(x,w1)
y=tf.matmul(a,w2)



#定义损失函数和反向传播算法
#自定义交叉熵
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)
#模拟生成训练集
rdm=RandomState(1)
dataset_size=128
X=rdm.rand(dataset_size,2)

Y=[[int(x1+x2<1)]for (x1,x2) in X]
print(X.shape)
print(Y)
with tf.Session() as sess:
    init_op=tf.global_variables_initializer()
    sess.run(init_op)
    print(sess.run(w1))
    print(sess.run(w2))

    STEPS=5000
    for i in range(STEPS):
        
        start = ( i* batch_size)%dataset_size
        end= min(start+batch_size,dataset_size)
        #通过选取的样本训练神经网络或训练参数
        sess.run(train_step,feed_dict={x: X[start:end], y_ : Y[start:end]})

        if i % 1000 == 0:
            #计算每隔一段时间所有数据的交叉熵并输出
            total_cross_entropy=sess.run(cross_entropy,feed_dict={x:X,y_:Y})
            print("After %d training steps,cross entropy on all data is %g"%(i,total_cross_entropy))
    print(sess.run(w1))
    print(sess.run(w2))

import tensorflow as tf
from numpy.random import RandomState
"""
自定义损失函数 
"""
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')#真值

w1=tf.Variable(tf.random_normal([2,1],stddev=1,seed=1))
y=tf.matmul(x,w1)#预测值

loss_less=10
loss_more=1
loss=tf.reduce_sum(tf.where(tf.greater(y,y_),(y-y_)*loss_more,(y_-y)*loss_less))

train_step=tf.train.AdamOptimizer(0.001).minimize(loss)
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.global_variables_initializer()
    sess.run(init_op)
    STEPS=5000
    for i in range(STEPS):
        start = (i * batch_size) % dataset_size
        end= min(start+batch_size,dataset_size)
        #通过选取的样本训练神经网络或训练参数
        sess.run(train_step,feed_dict={x: X[start:end], y_ : Y[start:end]})

    print(sess.run(w1))

来自《tensorflow 实战Google深度学习框架》