从网上找到的一张图，很生动形象。

第一段代码：

import tensorflow as tfimport numpy as np# 使用 NumPy 生成假数据(phony data), 总共 100 个点.x_data = np.float32(np.random.rand(2, 100)) # 随机输入，float64->float32y_data = np.dot([0.100, 0.200], x_data) + 0.300#print(y_data)# 构造一个线性模型b = tf.Variable(tf.zeros([1]))W = tf.Variable(tf.random_uniform([1, 2], -1.0, 1.0))y = tf.matmul(W, x_data) + b# 最小化方差loss = tf.reduce_mean(tf.square(y - y_data))optimizer = tf.train.GradientDescentOptimizer(0.5)  #学习率train = optimizer.minimize(loss)# 初始化变量init = tf.initialize_all_variables()# 启动图 (graph)sess = tf.Session()sess.run(init)# 拟合平面for step in range(0, 201):    sess.run(train)    if step % 20 == 0:        print(step, sess.run(W), sess.run(b))# 得到最佳拟合结果 W: [[0.100  0.200]], b: [0.300]

　　一段图像识别算法：

原理图：

 

用数学语言描述：

argmax是指最大值所对应的下标

#coding:utf-8import tensorflow as tfimport numpy as npimport input_datamnist = input_data.read_data_sets('MNIST_data', one_hot=True)#tf.placeholder形参x = tf.placeholder(tf.float32, shape=[None, 784])y_ = tf.placeholder("float", shape=[None, 10])#参数设置W = tf.Variable(tf.zeros([784,10]))b = tf.Variable(tf.zeros([10]))#y是推出每个y[0,10]的概率，所以是一个数组y = tf.nn.softmax(tf.matmul(x,W) + b)cross_entropy = -tf.reduce_sum(y_*tf.log(y))train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)#梯度下降#建立网络sess = tf.InteractiveSession()sess.run(tf.initialize_all_variables())#训练网络for i in range(1000):  batch = mnist.train.next_batch(50)  train_step.run(feed_dict={x: batch[0], y_: batch[1]})#计算准确率correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))sess.close()

　　多层神经网络：加入卷积层与池化层

#coding:utf-8import tensorflow as tfimport numpy as npimport input_datamnist = input_data.read_data_sets('MNIST_data', one_hot=True)x = tf.placeholder(tf.float32, shape=[None, 784])y_ = tf.placeholder("float", shape=[None, 10])sess = tf.InteractiveSession()def weight_variable(shape):  initial = tf.truncated_normal(shape, stddev=0.1)#正态分布，有正有负  return tf.Variable(initial)def bias_variable(shape):#偏置项  initial = tf.constant(0.1, shape=shape)  return tf.Variable(initial)#卷积与池化？？def conv2d(x, W):  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')def max_pool_2x2(x):  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],                        strides=[1, 2, 2, 1], padding='SAME')W_conv1 = weight_variable([5, 5, 1, 32])b_conv1 = bias_variable([32])x_image = tf.reshape(x, [-1,28,28,1])h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1)W_conv2 = weight_variable([5, 5, 32, 64])b_conv2 = bias_variable([64])h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)h_pool2 = max_pool_2x2(h_conv2)W_fc1 = weight_variable([7 * 7 * 64, 1024])b_fc1 = bias_variable([1024])h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)keep_prob = tf.placeholder("float")h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)W_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10])y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))sess.run(tf.initialize_all_variables())for i in range(20000):  batch = mnist.train.next_batch(50)  if i%100 == 0:    train_accuracy = accuracy.eval(feed_dict={        x:batch[0], y_: batch[1], keep_prob: 1.0})    print("step %d, training accuracy %g"%(i, train_accuracy))  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})print("test accuracy %g"%accuracy.eval(feed_dict={    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))