MNIST 卷积神经网络。https://github.com/nlintz/TensorFlow-Tutorials/blob/master/05_convolutional_net.py 。 TensorFlow搭建卷积神经网络(CNN)模型，训练MNIST数据集。

构建模型。

定义输入数据，预处理数据。读取数据MNIST，得到训练集图片、标记矩阵，测试集图片标记矩阵。trX、trY、teX、teY 数据矩阵表现。trX、teX形状变为[-1,28,28,1]，-1 不考虑输入图片数量，28x28 图片长、宽像素数，1 通道(channel)数量。MNIST 黑白图片，通道1。RGB彩色图像，通道3。 初始化权重，定义网络结构。卷积神经网络，3个卷积层、3个池化层、1个全连接层、1个输出层。 定义dropout占位符keep_conv，神经元保留比例。生成网络模型，得到预测值。 定义损失函数，tf.nn.softmax_cross_entropy_with_logits 比较预测值、真实值差异，做均值处理。 定义训练操作(train_op)，RMSProp算法优化器tf.train.RMSPropOptimizer，学习率0.001,衰减值0.9，优化损失。 定义预测操作(predict_op)。 会话启动图，训练、评估。

#!/usr/bin/env python import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data batch_size = 128 # 训练批次大小 test_size = 256 # 评估批次大小 # 定义初始化权重函数 def init_weights(shape):     return tf.Variable(tf.random_normal(shape, stddev=0.01)) # 定义神经网络模型函数 # 入参：X 输入数据，w 每层权重，p_keep_conv、p_keep_hidden dropout保留神经元比例 def model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden):     # 第一组卷积层及池化层，dropout部分神经元     l1a = tf.nn.relu(tf.nn.conv2d(X, w,                       # l1a shape=(?, 28, 28, 32)                         strides=[1, 1, 1, 1], padding='SAME'))     l1 = tf.nn.max_pool(l1a, ksize=[1, 2, 2, 1],              # l1 shape=(?, 14, 14, 32)                         strides=[1, 2, 2, 1], padding='SAME')     l1 = tf.nn.dropout(l1, p_keep_conv)     # 第二组卷积层及池化层，dropout部分神经元     l2a = tf.nn.relu(tf.nn.conv2d(l1, w2,                     # l2a shape=(?, 14, 14, 64)                         strides=[1, 1, 1, 1], padding='SAME'))     l2 = tf.nn.max_pool(l2a, ksize=[1, 2, 2, 1],              # l2 shape=(?, 7, 7, 64)                         strides=[1, 2, 2, 1], padding='SAME')     l2 = tf.nn.dropout(l2, p_keep_conv)     # 第三组卷积层及池化层，dropout部分神经元     l3a = tf.nn.relu(tf.nn.conv2d(l2, w3,                     # l3a shape=(?, 7, 7, 128)                         strides=[1, 1, 1, 1], padding='SAME'))     l3 = tf.nn.max_pool(l3a, ksize=[1, 2, 2, 1],              # l3 shape=(?, 4, 4, 128)                         strides=[1, 2, 2, 1], padding='SAME')     l3 = tf.reshape(l3, [-1, w4.get_shape().as_list()[0]])    # reshape to (?, 2048)     l3 = tf.nn.dropout(l3, p_keep_conv)     # 全连接层，dropout部分神经元     l4 = tf.nn.relu(tf.matmul(l3, w4))     l4 = tf.nn.dropout(l4, p_keep_hidden)     # 输出层     pyx = tf.matmul(l4, w_o)     return pyx # 返回预测值 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels # 数据预处理 trX = trX.reshape(-1, 28, 28, 1)  # 28x28x1 input img teX = teX.reshape(-1, 28, 28, 1)  # 28x28x1 input img X = tf.placeholder("float", [None, 28, 28, 1]) Y = tf.placeholder("float", [None, 10]) # 卷积核大小 3x3 # patch大小3x3，输入维度1，输出维度32 w = init_weights([3, 3, 1, 32])       # 3x3x1 conv, 32 outputs # patch大小3x3，输入维度32，输出维度64 w2 = init_weights([3, 3, 32, 64])     # 3x3x32 conv, 64 outputs # patch大小3x3，输入维度64，输出维度128 w3 = init_weights([3, 3, 64, 128])    # 3x3x32 conv, 128 outputs # 全连接层，输入维度128*4*4 上层输数据三维转一维，输出维度625 w4 = init_weights([128 * 4 * 4, 625]) # FC 128 * 4 * 4 inputs, 625 outputs # 输出层，输入维度625，输出维度10 代表10类(labels) w_o = init_weights([625, 10])         # FC 625 inputs, 10 outputs (labels) # 定义dropout占位符 p_keep_conv = tf.placeholder("float") p_keep_hidden = tf.placeholder("float") py_x = model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden) # 得到预测值 # 定义损失函数 cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y)) # 定义训练操作 train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost) # 定义预测操作 predict_op = tf.argmax(py_x, 1) # Launch the graph in a session #会话启动图 with tf.Session() as sess:     # you need to initialize all variables     tf.global_variables_initializer().run()     for i in range(100):         # 训练模型         training_batch = zip(range(0, len(trX), batch_size),                              range(batch_size, len(trX)+1, batch_size))         for start, end in training_batch:             sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end],                                           p_keep_conv: 0.8, p_keep_hidden: 0.5})         # 评估模型         test_indices = np.arange(len(teX)) # Get A Test Batch         np.random.shuffle(test_indices)         test_indices = test_indices[0:test_size]         print(i, np.mean(np.argmax(teY[test_indices], axis=1) ==                          sess.run(predict_op, feed_dict={X: teX[test_indices],                                                          p_keep_conv: 1.0,                                                          p_keep_hidden: 1.0}))) 

MNIST 循环神经网络。 https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py 。

RNN 自然语言处理领域成功应用，机器翻译、语音识别、图像描述生成(图像特征生成描述)、语言模型与文本生成(生成模型预测下一单词概率)。Alex Graves《Supervised Sequence Labelling with Recurrent Neural Networks》 http://www.cs.toronto.edu/~graves/preprint.pdf 。

构建模型。设置训练超参数，设置学习率、训练次数、每轮训练数据大小。 RNN分类图片，每张图片行，像素序列(sequence)。MNIST图片大小28x28，28个元素序列 X 28行，每步输入序列长度28，输入步数28步。 定义输入数据、权重。 定义RNN模型。 定义损失函数、优化器(AdamOptimizer)。 定义模型预测结果、准确率计算方法。 会话启动图，开始训练，每20次输出1次准确率大小。

from __future__ import print_function import tensorflow as tf from tensorflow.contrib import rnn # Import MNIST data from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("/tmp/data/", one_hot=True) # Training Parameters # 设置训练超参数 learning_rate = 0.001 training_steps = 10000 batch_size = 128 display_step = 200 # Network Parameters # 神经网络参数 num_input = 28 # MNIST data input (img shape: 28*28) 输入层 timesteps = 28 # timesteps 28 长度 num_hidden = 128 # hidden layer num of features 隐藏层神经元数 num_classes = 10 # MNIST total classes (0-9 digits) 输出数量，分类类别 0~9 # tf Graph input # 输入数据占位符 X = tf.placeholder("float", [None, timesteps, num_input]) Y = tf.placeholder("float", [None, num_classes]) # Define weights # 定义权重 weights = {     'out': tf.Variable(tf.random_normal([num_hidden, num_classes])) } biases = {     'out': tf.Variable(tf.random_normal([num_classes])) } # 定义RNN模型 def RNN(x, weights, biases):     # Unstack to get a list of 'timesteps' tensors of shape (batch_size, n_input)     # 输入x转换成(128 batch * 28 steps, 28 inputs)     x = tf.unstack(x, timesteps, 1)     # Define a lstm cell with tensorflow     # 基本LSTM循环网络单元 BasicLSTMCell     lstm_cell = rnn.BasicLSTMCell(num_hidden, forget_bias=1.0)     # Get lstm cell output     outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32)     # Linear activation, using rnn inner loop last output     return tf.matmul(outputs[-1], weights['out']) + biases['out'] logits = RNN(X, weights, biases) prediction = tf.nn.softmax(logits) # Define loss and optimizer # 定义损失函数 loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(     logits=logits, labels=Y)) # 定义优化器 optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate) train_op = optimizer.minimize(loss_op) # Evaluate model (with test logits, for dropout to be disabled) correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) # Initialize the variables (i.e. assign their default value) init = tf.global_variables_initializer() # Start training with tf.Session() as sess:     # Run the initializer     sess.run(init)     for step in range(1, training_steps+1):         batch_x, batch_y = mnist.train.next_batch(batch_size)         # Reshape data to get 28 seq of 28 elements         batch_x = batch_x.reshape((batch_size, timesteps, num_input))         # Run optimization op (backprop)         sess.run(train_op, feed_dict={X: batch_x, Y: batch_y})         if step % display_step == 0 or step == 1:             # Calculate batch loss and accuracy             loss, acc = sess.run([loss_op, accuracy], feed_dict={X: batch_x,                                                                  Y: batch_y})             print("Step " + str(step) + ", Minibatch Loss= " + \                   "{:.4f}".format(loss) + ", Training Accuracy= " + \                   "{:.3f}".format(acc))     print("Optimization Finished!")     # Calculate accuracy for 128 mnist test images     test_len = 128     test_data = mnist.test.images[:test_len].reshape((-1, timesteps, num_input))     test_label = mnist.test.labels[:test_len]     print("Testing Accuracy:", \         sess.run(accuracy, feed_dict={X: test_data, Y: test_label})) 

MNIST 无监督学习。自编码器(autoencoder)。

自编码网络。UFLDL http://ufldl.stanford.edu/wiki/index.php/Autoencoders_and_Sparsity 。 监督学习数据有标记。 自编码网络，输入样本压缩到隐藏层，解压，输出端重建样本。最终输出层神经元数量等于输入层神经元数据量。压缩，输入数据(图像、文本、声音)存在不同程度冗余信息，自动编码网络学习去掉冗余信息，有用特征输入到隐藏层。找到可以代表源数据的主要成分。激活函数不使用sigmoid等非线性函数，用线性函数，就是PCA模型。 主成分分析(principal components analysis, PCA)，分析、简化数据集技术。减少数据集维数，保持数据集方差贡献最大特征。保留低阶主成分，忽略高阶主成分。最常用线性降维方法。 压缩过程，限制隐藏神经元数量，学习有意义特征。希望神经元大部分时间被抑制。神经元输出接近1为被激活，接近0为被抑制。部分神经元处于被抑制状态，稀疏性限制。 多个隐藏层，输入数据图像，第一层学习识别边，第二层学习组合边，构成轮廓、角，更高层学习组合更有意义特征。

TensorFlow自编码网络实现。 https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/autoencoder.py 。

构建模型。设置超参数，学习率、训练轮数(epoch)、每次训练数据多少、每隔多少轮显示一次训练结果。 定义输入数据，无监督学习只需要图片数据，不需要标记数据。 初始化权重，定义网络结构。2个隐藏层，第一个隐藏层神经元256个，第二个隐藏层神经元128个。包括压缩、解压过程。 构建损失函数、优化器。损失函数“最小二乘法”，原始数据集和输出数据集平方差取均值运算。优化器用RMSPropOptimizer。 训练数据、评估模型。对测试集应用训练好的自动编码网络。比较测试集原始图片和自动编码网络重建结果。

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("/tmp/data/", one_hot=True) # Training Parameters # 设置训练超参数 learning_rate = 0.01 # 学习率 num_steps = 30000 # 训练轮数 batch_size = 256 # 每次训练数据多少 display_step = 1000 # 每隔多少轮显示训练结果 examples_to_show = 10 # 测试集选10张图片验证自动编码器结果 # Network Parameters # 网络参数 # 第一个隐藏层神经元个数，特征值个数 num_hidden_1 = 256 # 1st layer num features # 第二个隐藏层神经元个数，特征值个数 num_hidden_2 = 128 # 2nd layer num features (the latent dim) # 输入数据特征值个数 28x28=784 num_input = 784 # MNIST data input (img shape: 28*28) # tf Graph input (only pictures) # 定义输入数据，只需要图片，不要需要标记 X = tf.placeholder("float", [None, num_input]) # 初始化每层权重和偏置 weights = {     'encoder_h1': tf.Variable(tf.random_normal([num_input, num_hidden_1])),     'encoder_h2': tf.Variable(tf.random_normal([num_hidden_1, num_hidden_2])),     'decoder_h1': tf.Variable(tf.random_normal([num_hidden_2, num_hidden_1])),     'decoder_h2': tf.Variable(tf.random_normal([num_hidden_1, num_input])), } biases = {     'encoder_b1': tf.Variable(tf.random_normal([num_hidden_1])),     'encoder_b2': tf.Variable(tf.random_normal([num_hidden_2])),     'decoder_b1': tf.Variable(tf.random_normal([num_hidden_1])),     'decoder_b2': tf.Variable(tf.random_normal([num_input])), } # Building the encoder # 定义压缩函数 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']))     # Encoder 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 # 定义解压函数 def decoder(x):     # Decoder 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 # 构建模型 encoder_op = encoder(X) decoder_op = decoder(encoder_op) # Prediction # 得出预测值 y_pred = decoder_op # Targets (Labels) are the input data. # 得出真实值，即输入值 y_true = X # Define loss and optimizer, minimize the squared error # 定义损失函数、优化器 loss = tf.reduce_mean(tf.pow(y_true - y_pred, 2)) optimizer = tf.train.RMSPropOptimizer(learning_rate).minimize(loss) # Initialize the variables (i.e. assign their default value) init = tf.global_variables_initializer() # Start Training # Start a new TF session with tf.Session() as sess:     # Run the initializer     sess.run(init)     # Training     # 开始训练     for i in range(1, num_steps+1):         # Prepare Data         # Get the next batch of MNIST data (only images are needed, not labels)         batch_x, _ = mnist.train.next_batch(batch_size)         # Run optimization op (backprop) and cost op (to get loss value)         _, l = sess.run([optimizer, loss], feed_dict={X: batch_x})         # Display logs per step         # 每一轮，打印出一次损失值         if i % display_step == 0 or i == 1:             print('Step %i: Minibatch Loss: %f' % (i, l))     # Testing     # Encode and decode images from test set and visualize their reconstruction.     n = 4     canvas_orig = np.empty((28 * n, 28 * n))     canvas_recon = np.empty((28 * n, 28 * n))     for i in range(n):         # MNIST test set         batch_x, _ = mnist.test.next_batch(n)         # Encode and decode the digit image         g = sess.run(decoder_op, feed_dict={X: batch_x})         # Display original images         for j in range(n):             # Draw the original digits             canvas_orig[i * 28:(i + 1) * 28, j * 28:(j + 1) * 28] = \                 batch_x[j].reshape([28, 28])         # Display reconstructed images         for j in range(n):             # Draw the reconstructed digits             canvas_recon[i * 28:(i + 1) * 28, j * 28:(j + 1) * 28] = \                 g[j].reshape([28, 28])     print("Original Images")     plt.figure(figsize=(n, n))     plt.imshow(canvas_orig, origin="upper", cmap="gray")     plt.show()     print("Reconstructed Images")     plt.figure(figsize=(n, n))     plt.imshow(canvas_recon, origin="upper", cmap="gray")     plt.show() 

参考资料： 《TensorFlow技术解析与实战》

欢迎推荐上海机器学习工作机会，我的微信：qingxingfengzi