深度学习框架Tensorflow学习与应用 第2课

2-1：非线性回归

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


#使用numpy生成200个随机点,[:,np.newaxis]增加一个维度
x_data = np.linspace(-0.5,0.5,200)[:,np.newaxis]
noise = np.random.normal(0,0.02,x_data.shape)
y_data = np.square(x_data) + noise

#定义两个placeholder
x = tf.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])

#定义神经网络中间层
Weights_L1 = tf.Variable(tf.random_normal([1,10]))
biases_L1 = tf.Variable(tf.zeros([1,10]))
Wx_plus_b_L1 = tf.matmul(x,Weights_L1) + biases_L1
L1 = tf.nn.tanh(Wx_plus_b_L1)

#定义神经网络输出层
Weights_L2 = tf.Variable(tf.random_normal([10,1]))
biases_L2 = tf.Variable(tf.zeros([1,1]))
Wx_plus_b_L2 = tf.matmul(L1,Weights_L2) + biases_L2
prediction = tf.nn.tanh(Wx_plus_b_L2)

#二次代价函数
loss = tf.reduce_mean(tf.square(y-prediction))
#使用梯度下降法训练
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

with tf.Session() as sess:
    #变量初始化
    sess.run(tf.global_variables_initializer())
    for _ in range(2000):
        sess.run(train_step,feed_dict={x:x_data,y:y_data})
        
    #获得预测值
    prediction_value = sess.run(prediction,feed_dict={x:x_data})
    #画图
    plt.figure()
    plt.scatter(x_data,y_data)
    plt.plot(x_data,prediction_value,'r-',lw=5)
    plt.show()
    

2-2：MNIST数据集分类简单版本

MNIST数据集介绍：

 60000行的训练数据集（mnist.train）

 10000行测试数据集（mnist.test）

 每张图片包含28*28个像素

 MNIST数据集的标签是介于0-9的数字

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf


#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)

#每个批次的大小
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples//batch_size

#定义两个placeholder
x = tf.placeholder(tf.float32,[None, 784])
y = tf.placeholder(tf.float32,[None,10])

#创建一个简单的神经网络
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
predicton = tf.nn.softmax(tf.matmul(x,W)+b)

#二次代价函数
loss = tf.reduce_mean(tf.square(y-predicton))
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

#初始化变量
init = tf.global_variables_initializer()

#结果存放在一个布尔型列表中
#tf.argmax(input, axis=None, name=None, dimension=None)此函数是对矩阵按行或列计算最大值
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(predicton,1))
#求准确率
#tf.cast(x, dtype, name=None) ,把x转化为dtype型
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))


with tf.Session() as sess:
    sess.run(init)
    for epoch in range(21):#训练21次
        for batch in range(n_batch):
            batch_xs,batch_ys = mnist.train.next_batch(batch_size)
            sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys})
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
        print("Iter "+str(epoch)+"Test Accuracy " + str(acc)) 

输出：