tensorflow04 《TensorFlow实战Google深度学习框架》笔记-04-02自定义损失函数
来源:互联网 发布:桥梁bim软件 编辑:程序博客网 时间:2024/05/22 03:09
# 《TensorFlow实战Google深度学习框架》04 深层神经网络# win10 Tensorflow1.0.1 python3.5.3# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1# filename:ts04.02.py 自定义损失函数# 不同的损失函数会对训练模型产生重要影响import tensorflow as tffrom numpy.random import RandomState# 1. 定义神经网络的相关参数和变量batch_size = 8x = 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)# 2. 设置自定义的损失函数# 定义损失函数使得预测少了的损失大,于是模型应该偏向多的方向预测。loss_less = 10loss_more = 1loss = 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)# 3. 生成模拟数据集rdm = RandomState(1)X = rdm.rand(128,2)Y = [[x1+x2+(rdm.rand()/10.0-0.05)] for (x1, x2) in X]# 4. 训练模型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) % 128 end = (i*batch_size) % 128 + batch_size sess.run(train_step, feed_dict={x: X[start:end], y_: Y[start:end]}) if i % 1000 == 0: print("After %d training step(s), w1 is: " % (i)) print(sess.run(w1), "\n") print("[loss_less=10 loss_more=1] Final w1 is: \n", sess.run(w1))'''After 0 training step(s), w1 is: [[-0.81031823] [ 1.4855988 ]] After 1000 training step(s), w1 is: [[ 0.01247113] [ 2.13854504]] After 2000 training step(s), w1 is: [[ 0.45567426] [ 2.17060685]] After 3000 training step(s), w1 is: [[ 0.69968736] [ 1.84653103]] After 4000 training step(s), w1 is: [[ 0.89886677] [ 1.29736042]] [loss_less=10 loss_more=1] Final w1 is: [[ 1.01934707] [ 1.04280913]] '''# 5. 重新定义损失函数,使得预测多了的损失大,于是模型应该偏向少的方向预测loss_less = 1loss_more = 10loss = 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)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) % 128 end = (i*batch_size) % 128 + batch_size sess.run(train_step, feed_dict={x: X[start:end], y_: Y[start:end]}) if i % 1000 == 0: print("After %d training step(s), w1 is: " % (i)) print(sess.run(w1), "\n") print("[loss_less=1 loss_more=10] Final w1 is: \n", sess.run(w1))'''After 0 training step(s), w1 is: [[-0.81231821] [ 1.48359871]] After 1000 training step(s), w1 is: [[ 0.18643527] [ 1.07393336]] After 2000 training step(s), w1 is: [[ 0.95444274] [ 0.98088616]] After 3000 training step(s), w1 is: [[ 0.95574027] [ 0.9806633 ]] After 4000 training step(s), w1 is: [[ 0.95466018] [ 0.98135227]] [loss_less=1 loss_more=10] Final w1 is: [[ 0.95525807] [ 0.9813394 ]]'''# 6. 定义损失函数为MSEloss = tf.losses.mean_squared_error(y, y_)train_step = tf.train.AdamOptimizer(0.001).minimize(loss)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) % 128 end = (i*batch_size) % 128 + batch_size sess.run(train_step, feed_dict={x: X[start:end], y_: Y[start:end]}) if i % 1000 == 0: print("After %d training step(s), w1 is: " % (i)) print(sess.run(w1), "\n") print("[losses.mean_squared_error]Final w1 is: \n", sess.run(w1))'''After 0 training step(s), w1 is: [[-0.81031823] [ 1.4855988 ]] After 1000 training step(s), w1 is: [[-0.13337614] [ 1.81309223]] After 2000 training step(s), w1 is: [[ 0.32190299] [ 1.52463484]] After 3000 training step(s), w1 is: [[ 0.67850214] [ 1.25297272]] After 4000 training step(s), w1 is: [[ 0.89473999] [ 1.08598232]] [losses.mean_squared_error]Final w1 is: [[ 0.97437561] [ 1.0243336 ]]'''
1 0
- tensorflow04 《TensorFlow实战Google深度学习框架》笔记-04-02自定义损失函数
- Tensorflow实战Google深度学习框架 笔记
- tensorflow03 《TensorFlow实战Google深度学习框架》笔记-04-01
- tensorflow19《TensorFlow实战Google深度学习框架》笔记-08-04 预测正弦函数 code
- Tensorflow实战Google深度学习框架-学习笔记
- tensorflow02 《TensorFlow实战Google深度学习框架》笔记-03
- TensorFlow实战Google深度学习框架(一)
- 关于《TensorFlow 实战Google深度学习框架》
- TensorFlow实战Google深度学习框架
- tensorflow05 《TensorFlow实战Google深度学习框架》笔记-04-03学习率设置
- tensorflow06 《TensorFlow实战Google深度学习框架》笔记-04-04正则化
- tensorflow09 《TensorFlow实战Google深度学习框架》笔记-05-02变量管理(命名空间)code
- tensorflow13《TensorFlow实战Google深度学习框架》笔记-06-02mnist LeNet5卷积神经网络 code
- tensorflow21《TensorFlow实战Google深度学习框架》笔记-09-02 TensorBoard命名空间 code
- tensorflow25《TensorFlow实战Google深度学习框架》笔记-10-02 多GPU并行 code
- tensorflow07 《TensorFlow实战Google深度学习框架》笔记-04-05滑动平均模型
- tensorflow11 《TensorFlow实战Google深度学习框架》笔记-05-04mnist-nn最佳实践code
- tensorflow23《TensorFlow实战Google深度学习框架》笔记-09-04 TensorBoard 监控指标可视化 code
- C语言typeof详解
- div contenteditable=“true”后,placeholder的样式。
- 100多个基础常用JS函数和语法集合大全
- 九度OJ题目1064:反序数
- [BZOJ 1911][Apio2010]特别行动队:DP斜率优化
- tensorflow04 《TensorFlow实战Google深度学习框架》笔记-04-02自定义损失函数
- 剧终
- C# Serializable对象序列化的作用
- org.apache.jasper.JasperException --The JSP specification requires that an attribute name is precede
- UIView
- 正确应对系统内存不足,使用OnLowMemory和OnTrimMemory回调
- 关于WEB页面刷新重复提交问题
- Android实现APK下载安装
- 下载 m3u8 视频脚本