Autoencoder降维可视化

Posted

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了Autoencoder降维可视化相关的知识,希望对你有一定的参考价值。

参考技术A     关于高维度数据降维,以前都是使用PCA线性降维或者直接使用pandas的corr函数来找到相关性,但是这种方式的降维都是线性的。Autoencoder可以完成线性的、非线性的降维,提取有效的数据表征。下面是笔者收集展示的三个案例。

案例1:3D dataset数据集

 1、创建3D数据集

2、创建模型并训练,2个神经元的编码器隐藏层,3个神经元的解码器隐藏层

3、encoder编码器预测实例完成降维

案例2:mnist手写数字

1、定义函数load_mnist导入本地mnist数据集

2、Autoencoder降低到二维

3、AutoEncoder编码器预测新实例得到二维数据,并绘制图形

    以上绘制的图形有重叠部分,不便于区分。笔者再次修改模型使用Autoencoder来降低为对应的10维。

        使用TNSE再次完成数据降低到二维,这也就可以展开数据集便于可视化。

案例3:fashion_mnist图像

    此案例基于 Autoencoder神经网络完成异常检测(样本重构) ,前期的操作就不再展示了。下面是在编码器预测数据之后再次使用t-SNE,能够将高维空间中的数据映射到低维空间中,并保留数据集的局部特性。

2.3AutoEncoder

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:

 

以上是关于Autoencoder降维可视化的主要内容,如果未能解决你的问题,请参考以下文章

AutoEncoder

CNN autoencoder 先降维再使用kmeans进行图像聚类 是不是也可以降维以后进行iforest处理?

2.3AutoEncoder

Autoencoder 有啥用?

降噪自动编码器(Denoising AutoEncoder)+BERT

技术+案例详解无监督学习Autoencoder