利用tensorflow实现自编码

1、原理

    监督神经网络的本质就是对特征的不断学习挖掘的过程，而中间层就可以理解为对上一层特征的提取，自编码就是对神经网络中间层的提取，所以我们可以把高维的数据经过几层映射到低维，在进行还原的过程

2、测试数据

    构建2个三维的球，将其映射到2维，查看数据分布

def make_ball(R = 2,a=0,b=0,c=0):
    points = []
    for i in range(400):
        t = np.random.choice(360)
        t2 = np.random.choice(180)
#        R = np.random.random() * R
        
        x = R * np.sin(t2 * np.pi / 180) * np.cos(t * np.pi / 180) + a
        y = R * np.sin(t2 * np.pi / 180) * np.sin(t * np.pi / 180) + b
        z = R * np.cos(t2 * np.pi / 180) + c
        
        points.append([x,y,z])
    return np.array(points)

3、模型搭建

    由于例子的数据比较简单，所以就只用了1层的隐藏层，这个隐藏层就是我们要提取的主成分了，用梯度下降法进行优化，损失函数用还原数据与原数据的差的均方误差，最后模型收敛即完成训练

def build_autoencode(X):
    l,w = X.shape
    x_input = tf.placeholder(dtype=tf.float32,shape=[None,w])
    
    # decode
    with tf.name_scope("decode"):
        W,b = init_wb(shape=[w,2])
        decode = tf.nn.softplus(tf.matmul(x_input,W) + b)
        
    # encode
    with tf.name_scope("encode"):
        W,b = init_wb(shape=[2,w])
        encode = tf.matmul(decode,W) + b
        
    with tf.name_scope("loss"):
        loss = tf.reduce_mean(tf.square(tf.subtract(x_input,encode)))
        
    with tf.name_scope("train"):
        train_op = tf.train.GradientDescentOptimizer(1e-3).minimize(loss)
        init = tf.global_variables_initializer()
        sess = tf.Session()
        sess.run(init)
        for i in range(10000):
            sess.run(train_op,feed_dict = {x_input:X})
            if i % 100 == 0:
                loss_val = sess.run(loss,feed_dict={x_input:X})
                encode_val,decode_val = sess.run([encode,decode],feed_dict={x_input:X})
                print("iter:",i,"loss:",loss_val)
    return sess,decode,encode,x_input

完整代码：

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import cm
from mpl_toolkits.mplot3d import Axes3D



def make_ball(R = 2,a=0,b=0,c=0):
    points = []
    for i in range(400):
        t = np.random.choice(360)
        t2 = np.random.choice(180)
        x = R * np.sin(t2 * np.pi / 180) * np.cos(t * np.pi / 180) + a
        y = R * np.sin(t2 * np.pi / 180) * np.sin(t * np.pi / 180) + b
        z = R * np.cos(t2 * np.pi / 180) + c
        
        points.append([x,y,z])
    return np.array(points)


points = make_ball()

points2 = make_ball(R=2,a=3,b=3,c=3)

points3 = np.concatenate((points,points2),axis=0)

def plot3d(points):
    fig = plt.figure()
    ax = Axes3D(fig)
    ax.plot_trisurf(points[:,0],points[:,1],points[:,2],cmap=cm.jet,linewidth=0.9)
    plt.show()
    
def plot2d(point):
    if len(point) > 400:
        plt.scatter(point[:400,0],point[:400,1])
        plt.scatter(point[400:,0],point[400:,1])
    else:
        plt.scatter(point[:,0],point[:,1])
    plt.show()
    

def init_wb(shape):
    W = tf.Variable(tf.truncated_normal(shape=shape,stddev=0.1),dtype=tf.float32)
    b = tf.Variable(0.,dtype=tf.float32)
    return W,b

# 构建自编码器
def build_autoencode(X):
    l,w = X.shape
    x_input = tf.placeholder(dtype=tf.float32,shape=[None,w])
    
    # decode
    with tf.name_scope("decode"):
        W,b = init_wb(shape=[w,2])
        decode = tf.nn.softplus(tf.matmul(x_input,W) + b)
        
    # encode
    with tf.name_scope("encode"):
        W,b = init_wb(shape=[2,w])
        encode = tf.matmul(decode,W) + b
        
    with tf.name_scope("loss"):
        loss = tf.reduce_mean(tf.square(tf.subtract(x_input,encode)))
        
    with tf.name_scope("train"):
        train_op = tf.train.GradientDescentOptimizer(1e-3).minimize(loss)
        init = tf.global_variables_initializer()
        sess = tf.Session()
        sess.run(init)
        for i in range(10000):
            sess.run(train_op,feed_dict = {x_input:X})
            if i % 100 == 0:
                loss_val = sess.run(loss,feed_dict={x_input:X})
                encode_val,decode_val = sess.run([encode,decode],feed_dict={x_input:X})
                print("iter:",i,"loss:",loss_val)
    return sess,decode,encode,x_input

sess,decode,encode,x_input = build_autoencode(points3)

dd = sess.run(decode,feed_dict={x_input:points3})
plot2d(dd[:400])