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. iOS分辨率的那些事儿(转)

    1 iOS设备的分辨率 iOS设备,目前最主要的有3种(Apple TV等不在此讨论),按分辨率分为两类 iPhone/iPod Touch 普屏分辨率    320像素 x 480像素 Retina ...

  2. 【Postgres】dump数据库备份与还原

    备份 pg_dump.exe -h localhost -p 5432 -U postgres -F plain -v -f C:\Backup.sql db1 2> C:\Backup.log ...

  3. NetBpm 测试篇（3）

    http://www.netbpm.org/movie/holiday/holiday.html

  4. Python中的类（上）

    在Python中,可以通过class关键字定义自己的类,然后通过自定义的类对象类创建实例对象. 例如,下面创建了一个Student的类,并且实现了这个类的初始化函数"__init__&quo ...

  5. 如何构建日均千万PV Web站点 (三) Sharding

    其实国内许多大型网站为了应对日益复杂的业务场景,通过使用分而治之的手段将整个网站业务分成不同的产品线,比如说国内那些大型购物交易网站它们都将自己的网站首页.商铺.订单.买家.卖家等拆分不同的产品线,分 ...

  6. linux实现开机自启动脚本

    Linux下(以RedHat为范本)添加开机自启动脚本有两种方法,先来简单的; 一.在/etc/rc.local中添加如果不想将脚本粘来粘去,或创建链接什么的,则:step1. 先修改好脚本,使其所有 ...

  7. Android Studio 出现 Gradle's dependency cache may be corrupt 解决方案

    将 .\项目地址\gradle\wrapper\gradle-wrapper.properties 文件中的 gradle版本 与 正常的版本 修改一致即可.

  8. 【大数据系列】Hive安装及web模式管理

    一.什么是Hive Hive是建立在Hadoop基础常的数据仓库基础架构,,它提供了一系列的工具,可以用了进行数据提取转化加载(ETL),这是一种可以存储.查询和分析存储在Hadoop中的按规模数据的 ...

  9. swagger环境搭建

    下面所用工具下载   http://editor.swagger.io/#/  demo   一.安装 swagger editor   说明:安装swagger前需要安装node工具   工具安装 ...

  10. webstorm启动报错

    环境: 在重装完系统的电脑上第一次安装webstorm, 问题: 解决”failed to load jvm dll“的报错问题: 解决方案: 安装Microsoft Visual C++ 2010 ...