Tensorflw快速入门——运用逻辑回归算法手写数字识别

ゞ浴缸里的玫瑰 2023-06-27 04:29 21阅读 0赞

# Tensorflw快速入门二 #

## 手写数字识别 ##

*  运用逻辑回归算法对手写数字进行识别

上篇博文我们用tensorflow实现了线性回归  
[Tensorflow快速入门——线性回归][Tensorflow]  
今天我们运用逻辑回归算法对手写数字进行识别  
本文具体数据集与源代码可从我的GitHub地址获取  
[https://github.com/liuzuoping/Deep\_Learning\_note][https_github.com_liuzuoping_Deep_Learning_note]

## MNIST 数据集简介 ##

> 手写数字识别也是比较常见的例子了，这个数据集包含有60000张用于训练的手写数字的图片，10000张用于测试的图片，所有图片的尺寸都已经被标准化了，并且，尺寸为28 \* 28，每个像素值0~1区间内的值，其中0代表白色，1代表黑色，区间内的值表示灰色。为了简化，每张图片已经被转换成一个1*728的一维数组，表示784个特征（28*28）。

![MNIST Dataset][]

数据集下载:[http://yann.lecun.com/exdb/mnist/][http_yann.lecun.com_exdb_mnist]

#### 加载mnist数据集 ####

import tensorflow as tf
    
    
    from tensorflow.examples.tutorials.mnist import input_data
    mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
    print(mnist)

### 设置参数 ###

learning_rate = 0.01
    training_epochs = 100
    batch_size = 100
    display_step = 1

#### tf Graph的输入 ####

x = tf.placeholder(tf.float32, [None, 784]) # mnist data image of shape 28*28=784
    y = tf.placeholder(tf.float32, [None, 10]) # 0-9 digits recognition => 10 classes

#### 设置权重和偏置 ####

W = tf.Variable(tf.zeros([784, 10]))
    b = tf.Variable(tf.zeros([10]))

#### 设定运行模型 ####

pred = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax

#### 设置cost function为cross entropy ####

cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), reduction_indices=1))

#### 梯度下降 ####

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

#### 初始化所有参数 ####

init = tf.global_variables_initializer()

### 开始训练 ###

with tf.Session() as sess:
        sess.run(init)
        
        for epoch in range(training_epochs):
            avg_cost = 0.
            total_batch = int(mnist.train.num_examples/batch_size)
            # 遍历每个batch
            for i in range(total_batch):
                batch_xs, batch_ys = mnist.train.next_batch(batch_size)
                # 把每个batch的数据放进去训练
                _, c = sess.run([optimizer, cost], feed_dict={ x: batch_xs,
                                                              y: batch_ys})
                # 计算平均损失
                avg_cost += c / total_batch
            # 展示每次迭代的日志
            if (epoch+1) % display_step == 0:
                print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))
    
        print("Optimization Finished!")
    
        # 测试模型
        correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
        # 计算3000个样本的准确率
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        print("Accuracy:", accuracy.eval({ x: mnist.test.images[:3000], y: mnist.test.labels[:3000]}))

[Tensorflow]: https://blog.csdn.net/liuzuoping/article/details/103819763
[https_github.com_liuzuoping_Deep_Learning_note]: https://github.com/liuzuoping/Deep_Learning_note
[MNIST Dataset]: https://imgconvert.csdnimg.cn/aHR0cDovL25ldXJhbG5ldHdvcmtzYW5kZGVlcGxlYXJuaW5nLmNvbS9pbWFnZXMvbW5pc3RfMTAwX2RpZ2l0cy5wbmc?x-oss-process=image/format,png
[http_yann.lecun.com_exdb_mnist]: http://yann.lecun.com/exdb/mnist/