MNIST数字识别训练

1、下载mnist数据

自行寻找资源

并安装依赖库

joblib
numpy
Pillow
scikit-learn
opencv-python

2、 加载数据集并生成模型

import numpy as np
from sklearn.linear_model import LogisticRegression
import os
import joblib
# pre-data
trainData = np.loadtxt(open(
    './mnist/mnist_csv/mnist_train.csv', 'r'), delimiter=",", skiprows=1)  # load-data
MTrain, NTrain = np.shape(trainData)  # col/row nums
print("train set：", MTrain, NTrain)
xTrain = trainData[:, 1:NTrain]
xTrain_col_avg = np.mean(xTrain, axis=0)  # get avg
xTrain = (xTrain - xTrain_col_avg)/255  # to zero
yTrain = trainData[:, 0]
'''================================='''
# train model
model = LogisticRegression(
    solver='lbfgs', multi_class='multinomial', max_iter=500)
model.fit(xTrain, yTrain)
print("train success")
'''================================='''
# test model
testData = np.loadtxt(open('./mnist/mnist_csv/mnist_test.csv', 'r'),
                      delimiter=",", skiprows=1)
MTest, NTest = np.shape(testData)
print("test dataset：", MTest, NTest)
xTest = testData[:, 1:NTest]
xTest = (xTest-xTrain_col_avg) / 255 
yTest = testData[:, 0]
yPredict = model.predict(xTest)
errors = np.count_nonzero(yTest - yPredict)  # get not zero
print("predict end. error nums：", errors, ".")
print("data currect:", (MTest - errors) / MTest)
'''================================='''
# saveModel
dirs = './models'
if not os.path.exists(dirs):
  os.makedirs(dirs)
joblib.dump(model, dirs+'/model.pkl')

3、生成训练图片

import numpy as np
import struct
 
from PIL import Image
import os
 
data_file = r'./mnist/mnist_base/train-images-idx3-ubyte'
# It's 47040016B, but we should set to 47040000B
data_file_size = 47040016
data_file_size = str(data_file_size - 16) + 'B'
data_buf = open(data_file, 'rb').read()
magic, numImages, numRows, numColumns = struct.unpack_from(
    '>IIII', data_buf, 0)
datas = struct.unpack_from(
    '>' + data_file_size, data_buf, struct.calcsize('>IIII'))
datas = np.array(datas).astype(np.uint8).reshape(
    numImages, 1, numRows, numColumns)
label_file = r'./mnist/mnist_base/train-labels-idx1-ubyte'
# It's 60008B, but we should set to 60000B
label_file_size = 45184
label_file_size = str(label_file_size - 8) + 'B'
 
label_buf = open(label_file, 'rb').read()
 
magic, numLabels = struct.unpack_from('>II', label_buf, 0)
labels = struct.unpack_from(
    '>' + label_file_size, label_buf, struct.calcsize('>II'))
labels = np.array(labels).astype(np.int64)
 
datas_root = './mnist_train'
if not os.path.exists(datas_root):
    os.mkdir(datas_root)
 
for i in range(10):
    file_name = datas_root + os.sep + str(i)
    if not os.path.exists(file_name):
        os.mkdir(file_name)
 
for ii in range(numLabels):
    img = Image.fromarray(datas[ii, 0, 0:28, 0:28])
    label = labels[ii]
    file_name = datas_root + os.sep + str(label) + os.sep + \
                'mnist_train_' + str(ii) + '.png'
    img.save(file_name)

4、生成测试图片

import numpy as np
import struct
 
from PIL import Image
import os
 
data_file = r'./mnist/mnist_base/t10k-images-idx3-ubyte'
# It's 7840016B, but we should set to 7840000B
data_file_size = 7018384
data_file_size = str(data_file_size - 16) + 'B'
data_buf = open(data_file, 'rb').read()
magic, numImages, numRows, numColumns = struct.unpack_from(
    '>IIII', data_buf, 0)
datas = struct.unpack_from(
    '>' + data_file_size, data_buf, struct.calcsize('>IIII'))
datas = np.array(datas).astype(np.uint8).reshape(
    numImages, 1, numRows, numColumns)
label_file = r'./mnist/mnist_base/t10k-labels-idx1-ubyte'
# It's 10008B, but we should set to 10000B
label_file_size = 8960
label_file_size = str(label_file_size - 8) + 'B'
 
label_buf = open(label_file, 'rb').read()
 
magic, numLabels = struct.unpack_from('>II', label_buf, 0)
labels = struct.unpack_from(
    '>' + label_file_size, label_buf, struct.calcsize('>II'))
labels = np.array(labels).astype(np.int64)
 
datas_root = './mnist_test'
if not os.path.exists(datas_root):
    os.mkdir(datas_root)
 
for i in range(10):
    file_name = datas_root + os.sep + str(i)
    if not os.path.exists(file_name):
        os.mkdir(file_name)
 
for ii in range(numLabels):
    img = Image.fromarray(datas[ii, 0, 0:28, 0:28])
    label = labels[ii]
    file_name = datas_root + os.sep + str(label) + os.sep + \
                'mnist_test_' + str(ii) + '.png'
    img.save(file_name)

5、加载模型推理预测

import  cv2
import numpy as np
import joblib
map=cv2.imread(r"./mnist_test/3/mnist_test_15.png")
GrayImage = cv2.cvtColor(map, cv2.COLOR_BGR2GRAY)
ret,thresh2=cv2.threshold(GrayImage,127,255,cv2.THRESH_BINARY_INV)
Image=cv2.resize(thresh2,(28,28))
img_array = np.asarray(Image)
z=img_array.reshape(1,-1)
'''================================================'''
model = joblib.load('model'+'/model.pkl')
yPredict = model.predict(z)
print(yPredict)
y=str(yPredict)
cv2.putText(map,y, (10,20), cv2.FONT_HERSHEY_SIMPLEX,0.7,(0,0,255), 2, cv2.LINE_AA)
cv2.imshow("map",map)
cv2.waitKey(0)

参考博文：

        MNIST数据集下载+idx3-ubyte解析【超详细+上手简单】_不拘于时.的博客-CSDN博客

        python实现手写数字识别（小白入门）「建议收藏」-腾讯云开发者社区-腾讯云