"""Simple tutorial for using TensorFlow to compute polynomial regression.

Parag K. Mital, Jan. 2016"""
# %% Imports
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

# %% Let's create some toy data
plt.ion()
n_observations = 100
fig, ax = plt.subplots(1, 1)
xs = np.linspace(-3, 3, n_observations)
ys = np.sin(xs) + np.random.uniform(-0.5, 0.5, n_observations)
ax.scatter(xs, ys)
fig.show()
plt.draw()

# %% tf.placeholders for the input and output of the network. Placeholders are
# variables which we need to fill in when we are ready to compute the graph.
X = tf.placeholder(tf.float32)
Y = tf.placeholder(tf.float32)

# %% Instead of a single factor and a bias, we'll create a polynomial function
# of different polynomial degrees.  We will then learn the influence that each
# degree of the input (X^0, X^1, X^2, ...) has on the final output (Y).
Y_pred = tf.Variable(tf.random_normal([1]), name='bias')
for pow_i in range(1, 5):
    W = tf.Variable(tf.random_normal([1]), name='weight_%d' % pow_i)
    Y_pred = tf.add(tf.mul(tf.pow(X, pow_i), W), Y_pred)

# %% Loss function will measure the distance between our observations
# and predictions and average over them.
cost = tf.reduce_sum(tf.pow(Y_pred - Y, 2)) / (n_observations - 1)

# %% if we wanted to add regularization, we could add other terms to the cost,
# e.g. ridge regression has a parameter controlling the amount of shrinkage
# over the norm of activations. the larger the shrinkage, the more robust
# to collinearity.
# cost = tf.add(cost, tf.mul(1e-6, tf.global_norm([W])))

# %% Use gradient descent to optimize W,b
# Performs a single step in the negative gradient
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# %% We create a session to use the graph
n_epochs = 1000
with tf.Session() as sess:
    # Here we tell tensorflow that we want to initialize all
    # the variables in the graph so we can use them
    sess.run(tf.initialize_all_variables())

    # Fit all training data
    prev_training_cost = 0.0
    for epoch_i in range(n_epochs):
        for (x, y) in zip(xs, ys):
            sess.run(optimizer, feed_dict={X: x, Y: y})

        training_cost = sess.run(
            cost, feed_dict={X: xs, Y: ys})
        print(training_cost)

        if epoch_i % 100 == 0:
            ax.plot(xs, Y_pred.eval(
                feed_dict={X: xs}, session=sess),
                    'k', alpha=epoch_i / n_epochs)
            fig.show()
            plt.draw()

        # Allow the training to quit if we've reached a minimum
        if np.abs(prev_training_cost - training_cost) < 0.000001:
            break
        prev_training_cost = training_cost
ax.set_ylim([-3, 3])
fig.show()
plt.waitforbuttonpress()

Simple tutorial for using TensorFlow to compute polynomial regression的更多相关文章

  1. Simple tutorial for using TensorFlow to compute a linear regression

    """Simple tutorial for using TensorFlow to compute a linear regression. Parag K. Mita ...

  2. NNs(Neural Networks,神经网络)和Polynomial Regression(多项式回归)等价性之思考,以及深度模型可解释性原理研究与案例

    1. Main Point 0x1:行文框架 第二章:我们会分别介绍NNs神经网络和PR多项式回归各自的定义和应用场景. 第三章:讨论NNs和PR在数学公式上的等价性,NNs和PR是两个等价的理论方法 ...

  3. TensorFlow实战之Softmax Regression识别手写数字

         关于本文说明,本人原博客地址位于http://blog.csdn.net/qq_37608890,本文来自笔者于2018年02月21日 23:10:04所撰写内容(http://blog.c ...

  4. machine learning (6)---how to choose features, polynomial regression

    how to choose features, polynomial regression:通过定义更适合我们的feature,选择更好的模型,使我们的曲线与数据更好的拟合(而不仅仅是一条直线) 可以 ...

  5. 机器学习-TensorFlow建模过程 Linear Regression线性拟合应用

    TensorFlow是咱们机器学习领域非常常用的一个组件,它在数据处理,模型建立,模型验证等等关于机器学习方面的领域都有很好的表现,前面的一节我已经简单介绍了一下TensorFlow里面基础的数据结构 ...

  6. Polynomial regression

  7. (转)The Road to TensorFlow

    Stephen Smith's Blog All things Sage 300… The Road to TensorFlow – Part 7: Finally Some Code leave a ...

  8. [Tensorflow] Object Detection API - retrain mobileNet

    前言 一.专注话题 重点话题 Retrain mobileNet (transfer learning). Train your own Object Detector. 这部分讲理论,下一篇讲实践. ...

  9. Ubuntu 14.04(64位)+GTX970+CUDA8.0+Tensorflow配置 (双显卡NVIDIA+Intel集成显卡) ------本内容是长时间的积累,有时间再详细整理

    (后面内容是本人初次玩GPU时,遇到很多坑的问题总结及尝试解决办法.由于买独立的GPU安装会涉及到设备的兼容问题,这里建议还是购买GPU一体机(比如https://item.jd.com/396477 ...

随机推荐

  1. 《cocos2d-x游戏开发之旅》问题2016-10-7

    今天按书上做,遇到问题卡住了 书P115 项目是 littlerunner

  2. c语言的第四次作业

    (一)改错题 输出三角形的面积和周长,输入三角形的三条边a.b.c,如果能构成一个三角形,输出面积area和周长perimeter(保留2位小数):否则,输出"These sides do ...

  3. dfsdf

    This project was bootstrapped with Create React App. Below you will find some information on how to ...

  4. GC机制

    java虚拟机中的垃圾回收机制是,一个类,当该对象没有更多的应用指向它时,就会被垃圾回收器给回收,从而释放资源.该机制不可以程序员手动调用去回收某个对象,系统自动会去调用,当然程序员可以建议垃圾回收器 ...

  5. 背景重复样式background-repeat

    一.background-repeat属性 在CSS中,使用background-repeat属性可以设置背景图像是否平铺,并且可以设置如何平铺. 语法: background-repeat:取值; ...

  6. Dapper.Contrib拓展及数据库生成实体

    1.关于Dapper.Contrib Dapper.Contrib是Dapper的一个拓展类库,Dapper是一个轻量级ORM框架,这个不了解的请自行收集资料,本文主要讲讲,数据库生成实体,并通过实体 ...

  7. eclipse的maven操作无反应

    第一 查eclipse能不能正常用 hi world.java 第二 查maven能不能正常用 cmd: mvn -v 第三 看看maven和eclipse是不是64位之类的 第四 maven和ecl ...

  8. java1.8十大新特性详解

    "Java is still not dead-and people are starting to figure that out." 本教程将用带注释的简单代码来描述新特性,你 ...

  9. Python小代码_3_购物车

    product_list = [ ('MacBook', 9000), ('kindle', 500), ('tesla', 900000), ('book', 100), ('bike', 2000 ...

  10. dnc开源梦之队2018 开源项目精选集

    dnc开源梦之队2018 dnc开源项目选择标准 dnc = .NET Core.dotnet core 1.支持dnc 2.x,Github star数量100以上,最近2月活跃更新 2.轻量级.示 ...