自编码Autoencoder
神经网络的非监督学习
神经网络接收图像→→给图像打马赛克→→再还原
原有的图像被压缩，再用所储存的特征信息，经过解压获得原图。
如果神经元直接从获取的高清图像中取学习信息，会是一件很吃力的事情，所以通过特征提取，提取出能够重构出原图的主要信息，把缩减后的信息放入神经网络中进行学习，就可以更加轻松的学习。
输入：白色的X
输出：黑色的X
求取两者的误差，经过误差反向传递，逐步提升自编码准确性，中间的隐层就是能够提取出原数据最主要特征的神经元。
为什么说其是非监督学习：因为该过程只是用了X，而不用其标签，所以使非监督学习。
一般使用的时候只是用前半部分
因为前面已经学习了数据的精髓，我们只需要创建一个神经网络来学习这些精髓就好啦，可以达到和普通神经网络一样的效果，并且很高效。
编码器：前半部分
解码器：后半部分
自编码和PCA类似，可以提取出特征，可以给特征降维，自编码超越了PCA。
代码一：
#!/usr/bin/env python2 # -*- coding: utf-8 -*- """ Created on Thu Apr 11 00:02:38 2019 @author: xiexj """ import tensorflow as tf import numpy as np import matplotlib.pyplot as plt from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("/tmp/data/", one_hot=False) # 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 # 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: init = tf.global_variables_initializer() sess.run(init) total_batch = int(mnist.train.num_examples/batch_size) for epoch in range(training_epochs): for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) _, c = sess.run([optimizer, cost], feed_dict={X:batch_xs}) if epoch % display_step == 0: print("Epoch:", \'%04d\' % (epoch+1),"cost=", "{:.9f}".format(c)) print("Epoch:", \'%04d\' % (epoch+1),"cost=", "{:.9f}".format(c)) print("Optimization Finished!") encode_decode = sess.run(y_pred, feed_dict={X:mnist.test.images[:examples_to_show]}) 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()
training_epochs = 5 # 训练批数
training_epochs = 10 # 训练批数
代码二：
#!/usr/bin/env python2 # -*- coding: utf-8 -*- """ Created on Wed Apr 10 21:43:11 2019 @author: xiexj """ import tensorflow as tf import matplotlib.pyplot as plt from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=False) learning_rate = 0.01 trainning_epochs = 10 #20 batch_size = 256 display_step = 1 n_input = 784 X = tf.placeholder(tf.float32, [None, n_input]) n_hidden_1 = 128 n_hidden_2 = 64 n_hidden_3 = 10 n_hidden_4 = 2 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 dont use af 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 encoder_op = encoder(X) decoder_op = decoder(encoder_op) y_pred = decoder_op y_true = X cost = tf.reduce_mean(tf.pow(y_true - y_pred, 2)) optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost) init = tf.global_variables_initializer() with tf.Session() as sess: sess.run(init) total_batch = int(mnist.train.num_examples/batch_size) for epoch in range(trainning_epochs): for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) _, c = sess.run([optimizer, cost], feed_dict={X:batch_xs}) if epoch % display_step == 0: print("Epoch:%04d" % (epoch+1),"cost={:.9f}".format(c)) print("Optimization Finished!") 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.show()