tensorFlow（三）逻辑回归

tensorFlow 基础见前博客

逻辑回归广泛应用在各类分类，回归任务中。本实验介绍逻辑回归在 TensorFlow 上的实现

理论知识回顾

逻辑回归的主要公式罗列如下：

激活函数（activation function）：

损失函数（cost function）：

其中

损失函数求偏导（derivative cost function）：

训练模型

• 数据准备
  首先我们需要先下载MNIST的数据集。使用以下的命令进行下载：

  wget https://devlab-1251520893.cos.ap-guangzhou.myqcloud.com/t10k-images-idx3-ubyte.gz
  wget https://devlab-1251520893.cos.ap-guangzhou.myqcloud.com/t10k-labels-idx1-ubyte.gz
  wget https://devlab-1251520893.cos.ap-guangzhou.myqcloud.com/train-images-idx3-ubyte.gz
  wget https://devlab-1251520893.cos.ap-guangzhou.myqcloud.com/train-labels-idx1-ubyte.gz

创建代码

#-*- coding:utf-8 -*-
import time
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

MNIST = input_data.read_data_sets("./", one_hot=True)

learning_rate = 0.01
batch_size = 128
n_epochs = 25

X = tf.placeholder(tf.float32, [batch_size, 784])
Y = tf.placeholder(tf.float32, [batch_size, 10])

w = tf.Variable(tf.random_normal(shape=[784,10], stddev=0.01), name="weights")
b = tf.Variable(tf.zeros([1, 10]), name="bias")

logits = tf.matmul(X, w) + b

entropy = tf.nn.softmax_cross_entropy_with_logits(labels=Y, logits=logits)
loss = tf.reduce_mean(entropy) 

optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(loss)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    n_batches = int(MNIST.train.num_examples/batch_size)
    for i in range(n_epochs): 
        for j in range(n_batches):
            X_batch, Y_batch = MNIST.train.next_batch(batch_size)
            _, loss_ = sess.run([optimizer, loss], feed_dict={ X: X_batch, Y: Y_batch})
            print "Loss of epochs[{0}] batch[{1}]: {2}".format(i, j, loss_)

执行结果

Loss of epochs[0] batch[0]: 2.28968191147
Loss of epochs[0] batch[1]: 2.30224704742
Loss of epochs[0] batch[2]: 2.26435565948
Loss of epochs[0] batch[3]: 2.26956915855
Loss of epochs[0] batch[4]: 2.25983452797
Loss of epochs[0] batch[5]: 2.2572259903
......
Loss of epochs[24] batch[420]: 0.393310219049
Loss of epochs[24] batch[421]: 0.309725940228
Loss of epochs[24] batch[422]: 0.378903746605
Loss of epochs[24] batch[423]: 0.472946226597
Loss of epochs[24] batch[424]: 0.259472459555
Loss of epochs[24] batch[425]: 0.290799200535
Loss of epochs[24] batch[426]: 0.256865829229
Loss of epochs[24] batch[427]: 0.250789999962
Loss of epochs[24] batch[428]: 0.328135550022

测试模型

#-*- coding:utf-8 -*-
import time
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

MNIST = input_data.read_data_sets("./", one_hot=True)

learning_rate = 0.01
batch_size = 128
n_epochs = 25

X = tf.placeholder(tf.float32, [batch_size, 784])
Y = tf.placeholder(tf.float32, [batch_size, 10])

w = tf.Variable(tf.random_normal(shape=[784,10], stddev=0.01), name="weights")
b = tf.Variable(tf.zeros([1, 10]), name="bias")

logits = tf.matmul(X, w) + b

entropy = tf.nn.softmax_cross_entropy_with_logits(labels=Y, logits=logits)
loss = tf.reduce_mean(entropy) 

optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(loss)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    n_batches = int(MNIST.train.num_examples/batch_size)
    for i in range(n_epochs): 
        for j in range(n_batches):
            X_batch, Y_batch = MNIST.train.next_batch(batch_size)
            _, loss_ = sess.run([optimizer, loss], feed_dict={ X: X_batch, Y: Y_batch})
            print "Loss of epochs[{0}] batch[{1}]: {2}".format(i, j, loss_)

    n_batches = int(MNIST.test.num_examples/batch_size)
    total_correct_preds = 0
    for i in range(n_batches):
        X_batch, Y_batch = MNIST.test.next_batch(batch_size)
        preds = tf.nn.softmax(tf.matmul(X_batch, w) + b)
        correct_preds = tf.equal(tf.argmax(preds, 1), tf.argmax(Y_batch, 1))
        accuracy = tf.reduce_sum(tf.cast(correct_preds, tf.float32)) 

        total_correct_preds += sess.run(accuracy)

    print "Accuracy {0}".format(total_correct_preds/MNIST.test.num_examples)

执行结果

Accuracy 0.9108