15 手写数字识别-小数据集

　　未交作业（12.朴素贝叶斯-垃圾邮件分类）链接：https://www.cnblogs.com/chenjd/p/12910004.html

　　由于之前写好后未发布，而且有点忙，所以忘记交了，其它的作业我也是比较早完成提交的。

1.手写数字数据集

• from sklearn.datasets import load_digits
• digits = load_digits()

 代码：

from sklearn.datasets import load_digits
digits = load_digits()

2.图片数据预处理

• x：归一化MinMaxScaler()
• y：独热编码OneHotEncoder()或to_categorical
• 训练集测试集划分
• 张量结构

 代码：

import numpy as np
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import OneHotEncoder
from sklearn.model_selection import train_test_split
x_data = digits.data.astype(np.float32)
y_data = digits.target.astype(np.float32).reshape(-1, 1)
scaler = MinMaxScaler()
x_data = scaler.fit_transform(x_data)
print(x_data)
x = x_data.reshape(-1, 8, 8, 1)  # 张量结构，转换为图片格式
y = OneHotEncoder().fit_transform(y_data).todense()
# 划分训练集测试集
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=0, stratify=y)
print(x_train.shape)
print(x_test.shape)
print(y_train.shape)
print(y_test.shape)

3.设计卷积神经网络结构

• 绘制模型结构图，并说明设计依据。

代码：

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D

# 建立模型
model = Sequential()
ks = [3, 3]  # 卷积核大小
# 一层卷积
model.add(Conv2D(filters=16,
                 kernel_size=(5,5),
                 padding='same',
                 input_shape=x_train.shape[1:],
                 activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# 二层卷积
model.add(Conv2D(filters=32,
                 kernel_size=(3,3),
                 padding='same',
                 activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# 三层卷积
model.add(Conv2D(filters=64,
                 kernel_size=ks,
                 padding='same',
                 activation='relu'))
# 四层卷积
model.add(Conv2D(filters=128,
                 kernel_size=ks,
                 padding='same',
                 activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# 平坦层
model.add(Flatten())
# 全连接层
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.25))
# 激活函数
model.add(Dense(10, activation='softmax'))
model.summary()

 

4.模型训练

• model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
• train_history = model.fit(x=X_train,y=y_train,validation_split=0.2, batch_size=300,epochs=10,verbose=2)

代码：

model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])
train_history = model.fit(x=x_train,
                          y=y_train,
                          validation_split=0.2,
                          batch_size=300,
                          epochs=20,
                          verbose=2)

import matplotlib.pyplot as plt

def show_train_history(train_history, train, validation):
    plt.plot(train_history.history[train])
    plt.plot(train_history.history[validation])
    plt.title('Train History')
    plt.ylabel('train')
    plt.xlabel('epoch')
    plt.legend(['train', 'validation'], loc='upper left')
    plt.show()

# 准确率
show_train_history(train_history, 'accuracy', 'val_accuracy')
# 损失率
show_train_history(train_history, 'loss', 'val_loss')

5.模型评价

• model.evaluate()
• 交叉表与交叉矩阵
• pandas.crosstab
• seaborn.heatmap

代码：

import pandas as pd
import seaborn as sns

score = model.evaluate(x_test, y_test)[1]
print('模型准确率=', score)
# 预测值
y_pre = model.predict_classes(x_test)
print('预测的y值=', y_pre[:10])
# 交叉表和交叉矩阵
y_test1 = np.argmax(y_test, axis=1).reshape(-1)
y_true = np.array(y_test1)[0]
y_true.shape
# 交叉表查看预测数据与原数据对比
pd.crosstab(y_true, y_pre, rownames=['true'], colnames=['predict'])
# 交叉矩阵
y_test1 = y_test1.tolist()[0]
a = pd.crosstab(np.array(y_test1), y_pre, rownames=['Lables'], colnames=['predict'])
df = pd.DataFrame(a)
print(df)
sns.heatmap(df, annot=True, cmap="Reds", linewidths=0.2, linecolor='G')
plt.show()