AutoEncoder是包含一个压缩和解压缩的过程，属于一种无监督学习的降维技术。

神经网络接受大量信息，有时候接受的数据达到上千万，可以通过压缩

提取原图片最具有代表性的信息，压缩输入的信息量，在将缩减后的数据放入神经网络中学习，如此学习起来变得轻松了

自编码在这个时候使用，可以将自编码归为无监督学习，类似于PCA，自编码可以为属性降维

手写体识别代码AutoEncoder

from __future__ import division, print_function, absolute_import

import tensorflow as tf

import numpy as np

import matplotlib.pyplot as plt

# Import MNIST data

from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('MNIST_data', one_hot=False)

# Visualize decoder setting

# Parameters

learning_rate = 0.01

training_epochs = 5

batch_size = 256

display_step = 1

examples_to_show = 10

# Network Parameters

n_input = 784  # MNIST data input (img shape: 28*28)

# tf Graph input (only pictures)

X = tf.placeholder("float", [None, n_input])

# hidden layer settings

n_hidden_1 = 256 # 1st layer num features

n_hidden_2 = 128 # 2nd layer num features

weights = {

    'encoder_h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),

    'encoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),

    'decoder_h1': tf.Variable(tf.random_normal([n_hidden_2, n_hidden_1])),

    'decoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_input])),

}

biases = {

    'encoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),

    'encoder_b2': tf.Variable(tf.random_normal([n_hidden_2])),

    'decoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),

    'decoder_b2': tf.Variable(tf.random_normal([n_input])),

}

# Building the encoder

def encoder(x):

    # Encoder Hidden layer with sigmoid activation #1

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']),

                                   biases['encoder_b1']))

    # Decoder Hidden layer with sigmoid activation #2

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']),

                                   biases['encoder_b2']))

    return layer_2

# Building the decoder

def decoder(x):

    # Encoder Hidden layer with sigmoid activation #1

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']),

                                   biases['decoder_b1']))

    # Decoder Hidden layer with sigmoid activation #2

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']),

                                   biases['decoder_b2']))

    return layer_2

"""

# Visualize encoder setting

# Parameters

learning_rate = 0.01    # 0.01 this learning rate will be better! Tested

training_epochs = 10

batch_size = 256

display_step = 1

# Network Parameters

n_input = 784  # MNIST data input (img shape: 28*28)

# tf Graph input (only pictures)

X = tf.placeholder("float", [None, n_input])

# hidden layer settings

n_hidden_1 = 128

n_hidden_2 = 64

n_hidden_3 = 10

n_hidden_4 = 2  #2D show

weights = {

    'encoder_h1': tf.Variable(tf.truncated_normal([n_input, n_hidden_1],)),

    'encoder_h2': tf.Variable(tf.truncated_normal([n_hidden_1, n_hidden_2],)),

    'encoder_h3': tf.Variable(tf.truncated_normal([n_hidden_2, n_hidden_3],)),

    'encoder_h4': tf.Variable(tf.truncated_normal([n_hidden_3, n_hidden_4],)),

    'decoder_h1': tf.Variable(tf.truncated_normal([n_hidden_4, n_hidden_3],)),

    'decoder_h2': tf.Variable(tf.truncated_normal([n_hidden_3, n_hidden_2],)),

    'decoder_h3': tf.Variable(tf.truncated_normal([n_hidden_2, n_hidden_1],)),

    'decoder_h4': tf.Variable(tf.truncated_normal([n_hidden_1, n_input],)),

}

biases = {

    'encoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),

    'encoder_b2': tf.Variable(tf.random_normal([n_hidden_2])),

    'encoder_b3': tf.Variable(tf.random_normal([n_hidden_3])),

    'encoder_b4': tf.Variable(tf.random_normal([n_hidden_4])),

    'decoder_b1': tf.Variable(tf.random_normal([n_hidden_3])),

    'decoder_b2': tf.Variable(tf.random_normal([n_hidden_2])),

    'decoder_b3': tf.Variable(tf.random_normal([n_hidden_1])),

    'decoder_b4': tf.Variable(tf.random_normal([n_input])),

}

def encoder(x):

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']),

                                   biases['encoder_b1']))

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']),

                                   biases['encoder_b2']))

    layer_3 = tf.nn.sigmoid(tf.add(tf.matmul(layer_2, weights['encoder_h3']),

                                   biases['encoder_b3']))

    layer_4 = tf.add(tf.matmul(layer_3, weights['encoder_h4']),

                                    biases['encoder_b4'])

    return layer_4

def decoder(x):

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']),

                                   biases['decoder_b1']))

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']),

                                   biases['decoder_b2']))

    layer_3 = tf.nn.sigmoid(tf.add(tf.matmul(layer_2, weights['decoder_h3']),

                                biases['decoder_b3']))

    layer_4 = tf.nn.sigmoid(tf.add(tf.matmul(layer_3, weights['decoder_h4']),

                                biases['decoder_b4']))

    return layer_4

"""

# Construct model

encoder_op = encoder(X)

decoder_op = decoder(encoder_op)

# Prediction

y_pred = decoder_op

# Targets (Labels) are the input data.

y_true = X

# Define loss and optimizer, minimize the squared error

cost = tf.reduce_mean(tf.pow(y_true - y_pred, 2))

optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)

# Launch the graph

with tf.Session() as sess:

    # tf.initialize_all_variables() no long valid from

    # 2017-03-02 if using tensorflow >= 0.12

    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:

        init = tf.initialize_all_variables()

    else:

        init = tf.global_variables_initializer()

    sess.run(init)

    total_batch = int(mnist.train.num_examples/batch_size)

    # Training cycle

    for epoch in range(training_epochs):

        # Loop over all batches

        for i in range(total_batch):

            batch_xs, batch_ys = mnist.train.next_batch(batch_size)  # max(x) = 1, min(x) = 0

            # Run optimization op (backprop) and cost op (to get loss value)

            _, c = sess.run([optimizer, cost], feed_dict={X: batch_xs})

        # Display logs per epoch step

        if epoch % display_step == 0:

            print("Epoch:", '%04d' % (epoch+1),

                  "cost=", "{:.9f}".format(c))

    print("Optimization Finished!")

    # # Applying encode and decode over test set

    encode_decode = sess.run(

        y_pred, feed_dict={X: mnist.test.images[:examples_to_show]})

    # Compare original images with their reconstructions

    f, a = plt.subplots(2, 10, figsize=(10, 2))

    for i in range(examples_to_show):

        a[0][i].imshow(np.reshape(mnist.test.images[i], (28, 28)))

        a[1][i].imshow(np.reshape(encode_decode[i], (28, 28)))

    plt.show()

    # encoder_result = sess.run(encoder_op, feed_dict={X: mnist.test.images})

    # plt.scatter(encoder_result[:, 0], encoder_result[:, 1], c=mnist.test.labels)

    # plt.colorbar()

    # plt.show()

利用AutoEncoder进行类似于PCA的降维

代码：

from __future__ import division, print_function, absolute_import

import tensorflow as tf

import numpy as np

import matplotlib.pyplot as plt

# Import MNIST data

from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('MNIST_data', one_hot=False)

"""

# Visualize decoder setting

# Parameters

learning_rate = 0.01

training_epochs = 5

batch_size = 256

display_step = 1

examples_to_show = 10

# Network Parameters

n_input = 784  # MNIST data input (img shape: 28*28)

# tf Graph input (only pictures)

X = tf.placeholder("float", [None, n_input])

# hidden layer settings

n_hidden_1 = 256 # 1st layer num features

n_hidden_2 = 128 # 2nd layer num features

weights = {

    'encoder_h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),

    'encoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),

    'decoder_h1': tf.Variable(tf.random_normal([n_hidden_2, n_hidden_1])),

    'decoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_input])),

}

biases = {

    'encoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),

    'encoder_b2': tf.Variable(tf.random_normal([n_hidden_2])),

    'decoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),

    'decoder_b2': tf.Variable(tf.random_normal([n_input])),

}

# Building the encoder

def encoder(x):

    # Encoder Hidden layer with sigmoid activation #1

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']),

                                   biases['encoder_b1']))

    # Decoder Hidden layer with sigmoid activation #2

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']),

                                   biases['encoder_b2']))

    return layer_2

# Building the decoder

def decoder(x):

    # Encoder Hidden layer with sigmoid activation #1

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']),

                                   biases['decoder_b1']))

    # Decoder Hidden layer with sigmoid activation #2

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']),

                                   biases['decoder_b2']))

    return layer_2

"""

# Visualize encoder setting

# Parameters

learning_rate = 0.01    # 0.01 this learning rate will be better! Tested

training_epochs = 10

batch_size = 256

display_step = 1

# Network Parameters

n_input = 784  # MNIST data input (img shape: 28*28)

# tf Graph input (only pictures)

X = tf.placeholder("float", [None, n_input])

# hidden layer settings

n_hidden_1 = 128

n_hidden_2 = 64

n_hidden_3 = 10

n_hidden_4 = 2  #2D show

weights = {

    'encoder_h1': tf.Variable(tf.truncated_normal([n_input, n_hidden_1],)),

    'encoder_h2': tf.Variable(tf.truncated_normal([n_hidden_1, n_hidden_2],)),

    'encoder_h3': tf.Variable(tf.truncated_normal([n_hidden_2, n_hidden_3],)),

    'encoder_h4': tf.Variable(tf.truncated_normal([n_hidden_3, n_hidden_4],)),

    'decoder_h1': tf.Variable(tf.truncated_normal([n_hidden_4, n_hidden_3],)),

    'decoder_h2': tf.Variable(tf.truncated_normal([n_hidden_3, n_hidden_2],)),

    'decoder_h3': tf.Variable(tf.truncated_normal([n_hidden_2, n_hidden_1],)),

    'decoder_h4': tf.Variable(tf.truncated_normal([n_hidden_1, n_input],)),

}

biases = {

    'encoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),

    'encoder_b2': tf.Variable(tf.random_normal([n_hidden_2])),

    'encoder_b3': tf.Variable(tf.random_normal([n_hidden_3])),

    'encoder_b4': tf.Variable(tf.random_normal([n_hidden_4])),

    'decoder_b1': tf.Variable(tf.random_normal([n_hidden_3])),

    'decoder_b2': tf.Variable(tf.random_normal([n_hidden_2])),

    'decoder_b3': tf.Variable(tf.random_normal([n_hidden_1])),

    'decoder_b4': tf.Variable(tf.random_normal([n_input])),

}

def encoder(x):

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']),

                                   biases['encoder_b1']))

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']),

                                   biases['encoder_b2']))

    layer_3 = tf.nn.sigmoid(tf.add(tf.matmul(layer_2, weights['encoder_h3']),

                                   biases['encoder_b3']))

    layer_4 = tf.add(tf.matmul(layer_3, weights['encoder_h4']),

                                    biases['encoder_b4'])

    return layer_4

def decoder(x):

    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']),

                                   biases['decoder_b1']))

    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']),

                                   biases['decoder_b2']))

    layer_3 = tf.nn.sigmoid(tf.add(tf.matmul(layer_2, weights['decoder_h3']),

                                biases['decoder_b3']))

    layer_4 = tf.nn.sigmoid(tf.add(tf.matmul(layer_3, weights['decoder_h4']),

                                biases['decoder_b4']))

    return layer_4

# Construct model

encoder_op = encoder(X)

decoder_op = decoder(encoder_op)

# Prediction

y_pred = decoder_op

# Targets (Labels) are the input data.

y_true = X

# Define loss and optimizer, minimize the squared error

cost = tf.reduce_mean(tf.pow(y_true - y_pred, 2))

optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)

# Launch the graph

with tf.Session() as sess:

    # tf.initialize_all_variables() no long valid from

    # 2017-03-02 if using tensorflow >= 0.12

    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:

        init = tf.initialize_all_variables()

    else:

        init = tf.global_variables_initializer()

    sess.run(init)

    total_batch = int(mnist.train.num_examples/batch_size)

    # Training cycle

    for epoch in range(training_epochs):

        # Loop over all batches

        for i in range(total_batch):

            batch_xs, batch_ys = mnist.train.next_batch(batch_size)  # max(x) = 1, min(x) = 0

            # Run optimization op (backprop) and cost op (to get loss value)

            _, c = sess.run([optimizer, cost], feed_dict={X: batch_xs})

        # Display logs per epoch step

        if epoch % display_step == 0:

            print("Epoch:", '%04d' % (epoch+1),

                  "cost=", "{:.9f}".format(c))

    print("Optimization Finished!")

#     # # Applying encode and decode over test set

#     encode_decode = sess.run(

#         y_pred, feed_dict={X: mnist.test.images[:examples_to_show]})

#     # Compare original images with their reconstructions

#     f, a = plt.subplots(2, 10, figsize=(10, 2))

#     for i in range(examples_to_show):

#         a[0][i].imshow(np.reshape(mnist.test.images[i], (28, 28)))

#         a[1][i].imshow(np.reshape(encode_decode[i], (28, 28)))

#     plt.show()

    encoder_result = sess.run(encoder_op, feed_dict={X: mnist.test.images})

    plt.scatter(encoder_result[:, 0], encoder_result[:, 1], c=mnist.test.labels)

    plt.colorbar()

    plt.show()

显示如下：

2.3AutoEncoder的更多相关文章

随机推荐

  1. 阿里云被挖矿使用，导致cpu长期处于100%，ddgs进程，xWx3T进程,关于redis密码

    1.使用top命令,查看到一个叫xWx3T的进程cpu占用99.8%,由于我的阿里云是单核的,所以最高只能100%. 把它用kill命令杀死后,过一会儿又启动了,又占用100%. 使用ps -ef可以 ...

  2. [scala] scala 集合(⑧)

    1.List 基础操作 2.Set 基础操作 3. TreeSet 排序Set 4. 拉链操作 5. 流 import scala.collection.immutable.TreeSet impor ...

  3. 马尔科夫链蒙特卡洛(Markov chain Monte Carlo)

    (学习这部分内容大约需要1.3小时) 摘要 马尔科夫链蒙特卡洛(Markov chain Monte Carlo, MCMC) 是一类近似采样算法. 它通过一条拥有稳态分布 \(p\) 的马尔科夫链对 ...

  4. Linux+Redis实战教程_day01_常用命令【重点】

    3.常用命令[重点] Linux命令中参数,一般都是无序的.特殊情况下除外 3.1.磁盘管理命令 ls命令:列出目录内容 参数: -a 查询所有文件和文件夹.包含隐藏的 -l 查询详细列表    ls ...

  5. Dubbo -- 系统学习 笔记 -- 示例 -- 服务分组

    Dubbo -- 系统学习 笔记 -- 目录 示例 想完整的运行起来,请参见:快速启动,这里只列出各种场景的配置方式 服务分组 当一个接口有多种实现时,可以用group区分. <dubbo:se ...

  6. 删除腾讯游戏助手自动生成的文件aow_drv.log

    解决办法: 管理员身份运行cmd,依次执行如下指令: net stop aow_drvdel C:\aow_drv.logmkdir C:\aow_drv.logattrib +s +h C:\aow ...

  7. 【权限维持】window服务端常见后门技术

    0x00 前言 未知攻焉知防,攻击者在获取服务器权限后,通常会用一些后门技术来维持服务器权限,服务器一旦被植入后门,攻击者如入无人之境.这里整理一些window服务端常见的后门技术,了解攻击者的常见后 ...

  8. Git 学习笔记--3.EGit使用手册

    zz http://blog.csdn.net/pandakong/article/details/7234974 EGit是Eclipse上的Git插件,官方内容参看http://wiki.ecli ...

  9. 判断资源贴图是否有alpha

    /* modfly selected textures`s maxSize and ImportFormat bool hasAlpha = true; if(hasAlpha)then(textur ...

  10. codeforces水题100道 第七题 Codeforces Round #270 A. Design Tutorial: Learn from Math (math)

    题目链接:http://www.codeforces.com/problemset/problem/472/A题意:给你一个数n,将n表示为两个合数(即非素数)的和.C++代码: #include & ...