逻辑回归softmax神经网络实现手写数字识别(cs)

逻辑回归softmax神经网络实现手写数字识别全过程

项目已上传至github：marsggbo/MLinAction

---

1 - 导入模块

import numpy as np
import matplotlib.pyplot as plt
from ld_mnist import load_digits

%matplotlib inline

2 - 导入数据及数据预处理

mnist = load_digits()

Extracting C:/Users/marsggbo/Documents/Code/ML/TF Tutorial/data/MNIST_data\train-images-idx3-ubyte.gz
Extracting C:/Users/marsggbo/Documents/Code/ML/TF Tutorial/data/MNIST_data\train-labels-idx1-ubyte.gz
Extracting C:/Users/marsggbo/Documents/Code/ML/TF Tutorial/data/MNIST_data\t10k-images-idx3-ubyte.gz
Extracting C:/Users/marsggbo/Documents/Code/ML/TF Tutorial/data/MNIST_data\t10k-labels-idx1-ubyte.gz

print("Train: "+ str(mnist.train.images.shape))
print("Train: "+ str(mnist.train.labels.shape))
print("Test: "+ str(mnist.test.images.shape))
print("Test: "+ str(mnist.test.labels.shape))

Train: (55000, 784)
Train: (55000, 10)
Test: (10000, 784)
Test: (10000, 10)

mnist数据采用的是TensorFlow的一个函数进行读取的，由上面的结果可以知道训练集数据X_train有55000个，每个X的数据长度是784（28*28）。

另外由于数据集的数量较多，所以TensorFlow提供了批量提取数据的方法，从而大大提高了运行速率，方法如下：

x_batch, y_batch = mnist.train.next_batch(100)
print(x_batch.shape)
print(y_batch.shape)

>>>
(100, 784)
(100, 10)

x_train, y_train, x_test, y_test = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels

因为训练集的数据太大，所以可以再划分成训练集，验证集，测试集，比例为6:2:2

x_train_batch, y_train_batch = mnist.train.next_batch(30000)
x_cv_batch, y_cv_batch = mnist.train.next_batch(15000)
x_test_batch, y_test_batch = mnist.train.next_batch(10000)
print(x_train_batch.shape)
print(y_cv_batch.shape)
print(y_test_batch.shape)

(30000, 784)
(15000, 10)
(10000, 10)

展示手写数字

nums = 6
for i in range(1,nums+1):
    plt.subplot(1,nums,i)
    plt.imshow(x_train[i].reshape(28,28), cmap="gray")

3 - 算法介绍

3.1 算法

对单个样本数据 $x^{(i)}$:

z(i)=wTx(i)+b(1)