TF2:基本模型

src website：https://github.com/aymericdamien/TensorFlow-Examples/
主要介绍下近邻分类，线性回归，逻辑回归

线性回归
简单来说，就是由一堆数据需要用一个线性函数拟合它们
大致过程就是用梯度下降算法最小化损失函数

#coding=utf-8
#线性回归
import tensorflow as tf
import numpy
import matplotlib.pyplot as plt

rng = numpy.random
# Parameters
learning_rate = 0.01#学习率
training_epochs = 2000#迭代次数
display_step = 50#显示频率

# Training Data原始序列
train_X = numpy.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,7.042,10.791,5.313,7.997,5.654,9.27,3.1])
train_Y = numpy.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,2.827,3.465,1.65,2.904,2.42,2.94,1.3])
n_samples = train_X.shape[0]

X = tf.placeholder("float")
Y = tf.placeholder("float")
W = tf.Variable(rng.randn(), name="weight")
b = tf.Variable(rng.randn(), name="bias")

# 创建一个线性模型
activation = tf.add(tf.mul(X, W), b)

# Minimize the squared errors
cost = tf.reduce_sum(tf.pow(activation-Y, 2))/(2*n_samples) #L2 loss？
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) #Gradient descent
init = tf.initialize_all_variables()
with tf.Session() as sess:
    sess.run(init)
    for epoch in range(training_epochs):
        # for (x, y) in zip(train_X, train_Y):
        #     sess.run(optimizer, feed_dict={X: x, Y: y})
        #原github是这样写的，但我认为没必要，欢迎评论指正
        sess.run(optimizer,feed_dict={X:train_X,Y:train_Y})
        #Display logs per epoch step
        if epoch % display_step == 0:
            print "Epoch:", '%04d' % (epoch+1), "cost=", \
                "{:.9f}".format(sess.run(cost, feed_dict={X: train_X, Y:train_Y})), \
                "W=", sess.run(W), "b=", sess.run(b)

    print "Optimization Finished!"
    print "cost=", sess.run(cost, feed_dict={X: train_X, Y: train_Y}),"W=", sess.run(W), "b=", sess.run(b)

    plt.plot(train_X, train_Y, 'ro', label='Original data')
    plt.plot(train_X, sess.run(W) * train_X + sess.run(b), label='Fitted line')
    #o表示数据点用圆表示，且不连线，ro表示红色圆圈
    #-数据点用实现连接
    plt.legend()#绘制图例
    plt.show()

再看一个线性例子

#coding=utf-8
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf

nump_points = 1000
vectors_set = []

lr=0.5#学习率
epoch=50
for i in xrange(nump_points):
    xl=np.random.normal(0.0,0.55)
    yl=xl*0.1+0.3+np.random.normal(0.0,0.03)#生成线性数据
    vectors_set.append([xl,yl])

x_data=[v[0] for v in vectors_set]
y_data=[v[1] for v in vectors_set]

W=tf.Variable(tf.random_uniform([1],-1.0,1.0))
b=tf.Variable(tf.zeros([1]))
y=W*x_data+b

loss=tf.reduce_mean(tf.square(y-y_data))
optimizer=tf.train.GradientDescentOptimizer(lr).minimize(loss)
init=tf.initialize_all_variables()

with tf.Session() as sess:
    sess.run(init)
    for step in range(epoch):
        sess.run(optimizer)
        if step%5==0:#每隔五次显示一次
            print "W=",sess.run(W),"loss==",sess.run(loss)
    print sess.run(W),sess.run(b)

    plt.figure(1)
    plt.title('src')
    plt.plot(x_data, y_data, 'ro', label='Original data')
    plt.legend()
    plt.figure(2)
    plt.title('dst')
    plt.plot(x_data, y_data, 'ro', label='Original data')
    plt.plot(x_data, sess.run(W) * x_data + sess.run(b))
    plt.show()