关于python:交作业手写数字识别Minst数据集SoftMax回归

本人跑的时候正确率 0.89

库

• numpy
• PIL(如果须要对理论图片进行预测)

后果

• minst 的四个文件解压之后和这四个 py 文件放在同级文件夹
• 运行完结后的权重 W 和偏移 b 也在同级文件夹下，csv 文件只用来看，用的是 bin 文件

softmax.py

和训练、测试无关的所有函数

#!/usr/bin/python

import numpy as np

np.random.seed(0)

# 定义 softmax 函数
def SoftMax(z):
    if np.ndim(z) == 2:
        axisn = 1
    else:
        axisn = 0
    s = np.exp(z) / np.sum(np.exp(z), axis=axisn, keepdims=True)
    return s

# b = np.array([1,2,4, 5,5,6]).reshape(2,3)
# print(SoftMax(b))

# 编码标签
def OneCode(y):
    r = len(y)
    c = len(np.unique(y))
    one_hot = np.zeros((r,c))
    one_hot[np.arange(len(y)), y.astype(int).T] = 1
    return one_hot
# 定义 y_ 的计算函数
def CalcY_(x, w, b):
    # w * X.T + b 前面 +b 是一个播送运算，y_ = np.dot(w, x.T) + b
    return y_.T

# 定义损失函数 - 穿插熵
def cross_entropy(y, y_):
    loss = -(1/len(y))*np.sum(y * np.log(y_))
    return loss

# 定义训练函数
def train(tr_x, tr_y, N):
    ''''''
    # 模型
    # y = w1 * x1 + w2 * x2 + b
    W = np.random.rand(10,784)
    b = np.random.rand(10,1)
    losss = []
    losi = 0
    y = OneCode(tr_y) # 把 1 2 3 4 转换成向量 0001 0010 0100 1000
    for i in range(N):
        
        # 计算 loss
        x = tr_x
        y_ = SoftMax(CalcY_(x, W, b))
        loss = cross_entropy(y, y_)
        losss.append(loss)

        # 计算梯度
        grad_w = (1/len(x)) * np.dot((y_ - y).T, x)
        grad_b = (1/len(x)) * np.sum((y_ - y))

        # 更新参数
                # 学习率 × 梯度
        W = W - 0.5 * grad_w
        b = b - 0.5 * grad_b
        delta = abs(losi - loss)
        print(i ,  loss ,delta)
        # 损失值低于 0.01 或者 其变动值低于 0.0001
        if(loss < 0.01 or delta < 0.0001):
            break
        losi = loss

    return W,b

# 定义测试函数
def check(te_x, te_y, W, b):
    # te_x,te_y = Iread('te')
    # te_x = te_x / 255
    # te_y = te_y

    # print(W)
    # print(b)
    y_ = SoftMax(CalcY_(te_x, W, b))
    l = np.argmax(y_, axis=1).reshape(10000,1)

    right = np.sum(l == te_y.astype())/10000
    print('right rate:', right)
    return right

Idata.py

文件读取函数

#!/usr/bin/python

import numpy as np

filename_train_data ='./train-images-idx3-ubyte'
filename_train_label='./train-labels-idx1-ubyte'
filename_test_data  ='./t10k-images-idx3-ubyte'
filename_test_label ='./t10k-labels-idx1-ubyte'

def Iread_train_data():
    fp = open(filename_train_data, 'rb')
    fl = open(filename_train_label, 'rb')
    fp.read(4*4)
    fl.read(2*4)

    nstrs=np.zeros((60000, 28*28))
    l    =np.zeros((60000, 1))
    for i in range(60000):
        fstr = fp.read(28*28)
        lstr = fl.read(1)
        l[i] = int.from_bytes(lstr,byteorder='big',signed=False)
        nstrs[i,:] = np.frombuffer(fstr, dtype=np.uint8)
    return nstrs,l
def Iread_test_data():
    fp = open(filename_test_data, 'rb')
    fl = open(filename_test_label, 'rb')
    fp.read(4*4)
    fl.read(2*4)

    nstrs=np.zeros((10000, 28*28))
    l    =np.zeros((10000, 1))
    for i in range(10000):
        fstr = fp.read(28*28)
        lstr = fl.read(1)
        l[i] = int.from_bytes(lstr,byteorder='big',signed=False)
        nstrs[i,:] = np.frombuffer(fstr, dtype=np.uint8)
    return nstrs,l

def Iread(option):
    if(option == 'tr'):
        d,l = Iread_train_data()
        return d,l
    else if(option == 'te'):
        d,l = Iread_test_data()
        return d,l
    else:
        print('op err')

minst.py

实现训练和测试的脚本

#!/usr/bin/python

import numpy as np
from Idata import Iread
from softmax import train,check

# 读数据
tr_x,tr_y = Iread('tr')
te_x,te_y = Iread('te')
# 训练集和测试集正规到 0-1 区间
tr_x = tr_x / 255
te_x = te_x / 255

# print(tr_x.shape, tr_y.shape)
# print(te_x.shape, te_y.shape)

# 训练
W,b = train(tr_x, tr_y, 1000)
# 而后保留参数
W.tofile('W.bin')
b.tofile('b.bin')

np.savetxt('w.csv', W, fmt='%f', delimiter=',')
np.savetxt('b.csv', b, fmt='%f', delimiter=',')

# 读取参数
W = np.fromfile('W.bin').reshape(10, 784)
b = np.fromfile('b.bin').reshape(10, 1)
# 测试
r = check(te_x, te_y, W, b)

predict.py

用来对一个理论的手写数字图像识别的脚本

#!/usr/bin/python

import numpy as np

from softmax import SoftMax,CalcY_,cross_entropy,OneCode
from PIL import Image

# 图像文件必须是 28 × 28 的 0～255 灰度图像
fname = '4.bmp'

img = np.array(Image.open(fname))
te_x = img.reshape(1, 28*28)
te_x = te_x / 255
print(te_x)

W = np.fromfile('W.bin').reshape(10, 784)
b = np.fromfile('b.bin').reshape(10, 1)

y_ = SoftMax(CalcY_(te_x, W, b))
y_ = np.argmax(y_, axis=1)

print('pred:', y_)