机器学习之手写数字识别-小数据集

zhaorui0

2020-06-09

1.手写数字数据集

# 导入手写数据集
from sklearn.datasets import load_digits
data = load_digits()
print(data)

机器学习之手写数字识别-小数据集

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

"""
    @author Rakers
"""
import numpy as np
# 导入手写数据集
from sklearn.datasets import load_digits
# 图片数据预处理 --归一化
from sklearn.preprocessing import MinMaxScaler
# OneHotEncoder独热编码
from sklearn.preprocessing import OneHotEncoder
# 切分数据集
from sklearn.model_selection import train_test_split

data = load_digits()

# x：归一化MinMaxScaler()
X_data = data[‘data‘].astype(np.float32)
scaler = MinMaxScaler()
X_data = scaler.fit_transform(X_data)
print("归一化后数据:\n",X_data)
# 转化为图片的格式
X=X_data.reshape(-1, 8, 8, 1)
print("转化为图片后数据:", X.shape)

# y：独热编码OneHotEncoder()
y = data[‘target‘].astype(np.float32).reshape(-1, 1)  # 将Y_data变为一列
Y = OneHotEncoder().fit_transform(y).todense() # 张量结构todense
print("Y独热编码：\n", Y)
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,X_test,y_train,y_test)
print("X_data.shape:",X_data.shape)
print("X.shape:",X.shape)

机器学习之手写数字识别-小数据集

3.设计卷积神经网络结构

绘制模型结构图，设计依据。

机器学习之手写数字识别-小数据集

"""
    @author Rakers
"""
import numpy as np
# 导入手写数据集
from sklearn.datasets import load_digits
# 图片数据预处理 --归一化
from sklearn.preprocessing import MinMaxScaler
# OneHotEncoder独热编码
from sklearn.preprocessing import OneHotEncoder
# 切分数据集
from sklearn.model_selection import train_test_split

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

def buildModel(isPrintSummary=True, X_train=None):
    """
    # 建立模型
    :param isPrintSummary: 是否打印Summary信息
    :return: 返回构建的模型
    """
    model = Sequential()
    ks = (3, 3)  # 卷积核的大小
    input_shape = X_train.shape[1:]
    # 一层卷积，padding=‘same‘,tensorflow会对输入自动补0
    model.add(Conv2D(filters=16, kernel_size=ks, padding=‘same‘, input_shape=input_shape, activation=‘relu‘))
    # 池化层1
    model.add(MaxPool2D(pool_size=(2, 2)))
    # 防止过拟合，随机丢掉连接
    model.add(Dropout(0.25))
    # 二层卷积
    model.add(Conv2D(filters=32, kernel_size=ks, padding=‘same‘, activation=‘relu‘))
    # 池化层2
    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3
    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softmax
    model.add(Dense(10, activation=‘softmax‘))
    if isPrintSummary:
        print(model.summary())
    return model


if __name__ == "__main__":
    data = load_digits()

    # x：归一化MinMaxScaler()
    X_data = data[‘data‘].astype(np.float32)
    scaler = MinMaxScaler()
    X_data = scaler.fit_transform(X_data)
    # print("归一化后数据:\n", X_data)
    # 转化为图片的格式
    X = X_data.reshape(-1, 8, 8, 1)
    # print("转化为图片后数据:", X.shape)

    # y：独热编码OneHotEncoder()
    y = data[‘target‘].astype(np.float32).reshape(-1, 1)  # 将Y_data变为一列
    Y = OneHotEncoder().fit_transform(y).todense()  # 张量结构todense
    # print("Y独热编码：\n", Y)
    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, X_test, y_train, y_test)
    # print("X_data.shape:", X_data.shape)
    # print("X.shape:", X.shape)
    model = buildModel(X_train=X_train)

机器学习之手写数字识别-小数据集

4.模型训练

"""
    @author Rakers
"""
import numpy as np
import matplotlib.pyplot as plt
# 导入手写数据集
from sklearn.datasets import load_digits
# 图片数据预处理 --归一化
from sklearn.preprocessing import MinMaxScaler
# OneHotEncoder独热编码
from sklearn.preprocessing import OneHotEncoder
# 切分数据集
from sklearn.model_selection import train_test_split

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

def buildModel(isPrintSummary=True, X_train=None):
    """
    # 建立模型
    :param isPrintSummary: 是否打印Summary信息
    :return: 返回构建的模型
    """
    model = Sequential()
    ks = (3, 3)  # 卷积核的大小
    input_shape = X_train.shape[1:]
    # 一层卷积，padding=‘same‘,tensorflow会对输入自动补0
    model.add(Conv2D(filters=16, kernel_size=ks, padding=‘same‘, input_shape=input_shape, activation=‘relu‘))
    # 池化层1
    model.add(MaxPool2D(pool_size=(2, 2)))
    # 防止过拟合，随机丢掉连接
    model.add(Dropout(0.25))
    # 二层卷积
    model.add(Conv2D(filters=32, kernel_size=ks, padding=‘same‘, activation=‘relu‘))
    # 池化层2
    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3
    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softmax
    model.add(Dense(10, activation=‘softmax‘))
    if isPrintSummary:
        print(model.summary())
    return model


# 画Train History图
def show_train_history(train_history, train, validation):
    """
    @author Rakers
    :param train_history: 
    :param train: 
    :param validation: 
    :return: 
    """
    if train in train_history.history:
        plt.plot(train_history.history[train])
    if validation in train_history.history:
        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()


if __name__ == "__main__":
    data = load_digits()

    # x：归一化MinMaxScaler()
    X_data = data[‘data‘].astype(np.float32)
    scaler = MinMaxScaler()
    X_data = scaler.fit_transform(X_data)
    # print("归一化后数据:\n", X_data)
    # 转化为图片的格式
    X = X_data.reshape(-1, 8, 8, 1)
    # print("转化为图片后数据:", X.shape)

    # y：独热编码OneHotEncoder()
    y = data[‘target‘].astype(np.float32).reshape(-1, 1)  # 将Y_data变为一列
    Y = OneHotEncoder().fit_transform(y).todense()  # 张量结构todense
    # print("Y独热编码：\n", Y)
    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, X_test, y_train, y_test)
    # print("X_data.shape:", X_data.shape)
    # print("X.shape:", X.shape)
    model = buildModel(X_train=X_train)

    # 模型训练
    model.compile(loss=‘categorical_crossentropy‘, optimizer=‘adam‘, metrics=[‘acc‘])
    train_history = model.fit(x=X_train, y=y_train, validation_split=0.2, batch_size=300, epochs=10, verbose=2)
    # 准确率
    show_train_history(train_history, ‘acc‘, ‘val_acc‘)
    # 损失率
    show_train_history(train_history, ‘loss‘, ‘val_loss‘)

机器学习之手写数字识别-小数据集

5.模型评价

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

"""
    @author Rakers
"""
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
# 导入手写数据集
from sklearn.datasets import load_digits
# 图片数据预处理 --归一化
from sklearn.preprocessing import MinMaxScaler
# OneHotEncoder独热编码
from sklearn.preprocessing import OneHotEncoder
# 切分数据集
from sklearn.model_selection import train_test_split

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

def buildModel(isPrintSummary=True, X_train=None):
    """
    # 建立模型
    :param isPrintSummary: 是否打印Summary信息
    :return: 返回构建的模型
    """
    model = Sequential()
    ks = (3, 3)  # 卷积核的大小
    input_shape = X_train.shape[1:]
    # 一层卷积，padding=‘same‘,tensorflow会对输入自动补0
    model.add(Conv2D(filters=16, kernel_size=ks, padding=‘same‘, input_shape=input_shape, activation=‘relu‘))
    # 池化层1
    model.add(MaxPool2D(pool_size=(2, 2)))
    # 防止过拟合，随机丢掉连接
    model.add(Dropout(0.25))
    # 二层卷积
    model.add(Conv2D(filters=32, kernel_size=ks, padding=‘same‘, activation=‘relu‘))
    # 池化层2
    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3
    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softmax
    model.add(Dense(10, activation=‘softmax‘))
    if isPrintSummary:
        print(model.summary())
    return model


# 画Train History图
def show_train_history(train_history, train, validation):
    """
    @author Rakers
    :param train_history:
    :param train:
    :param validation:
    :return:
    """
    if train in train_history.history:
        plt.plot(train_history.history[train])
    if validation in train_history.history:
        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()


if __name__ == "__main__":
    data = load_digits()

    # x：归一化MinMaxScaler()
    X_data = data[‘data‘].astype(np.float32)
    scaler = MinMaxScaler()
    X_data = scaler.fit_transform(X_data)
    # print("归一化后数据:\n", X_data)
    # 转化为图片的格式
    X = X_data.reshape(-1, 8, 8, 1)
    # print("转化为图片后数据:", X.shape)

    # y：独热编码OneHotEncoder()
    y = data[‘target‘].astype(np.float32).reshape(-1, 1)  # 将Y_data变为一列
    Y = OneHotEncoder().fit_transform(y).todense()  # 张量结构todense
    # print("Y独热编码：\n", Y)
    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, X_test, y_train, y_test)
    # print("X_data.shape:", X_data.shape)
    # print("X.shape:", X.shape)
    model = buildModel(X_train=X_train)

    # 模型训练
    model.compile(loss=‘categorical_crossentropy‘, optimizer=‘adam‘, metrics=[‘acc‘])
    train_history = model.fit(x=X_train, y=y_train, validation_split=0.2, batch_size=300, epochs=10, verbose=2)
    # 准确率
    show_train_history(train_history, ‘acc‘, ‘val_acc‘)
    # 损失率
    show_train_history(train_history, ‘loss‘, ‘val_loss‘)

    # 模型评价
    score = model.evaluate(X_test, y_test)
    print(‘score：‘, score)
    # 预测值
    y_pred = model.predict_classes(X_test)
    print(‘y_pred：‘, y_pred[:10])
    # 交叉表与交叉矩阵
    y_test1 = np.argmax(y_test, axis=1).reshape(-1)
    y_true = np.array(y_test1)[0]
    # 交叉表查看预测数据与原数据对比
    # pandas.crosstab
    pd.crosstab(y_true, y_pred, rownames=[‘true‘], colnames=[‘predict‘])
    # 交叉矩阵
    # seaborn.heatmap
    y_test1 = y_test1.tolist()[0]
    a = pd.crosstab(np.array(y_test1), y_pred, rownames=[‘Lables‘], colnames=[‘Predict‘])
    # 转换成属dataframe
    df = pd.DataFrame(a)
    sns.heatmap(df, annot=True, cmap="Reds", linewidths=0.2, linecolor=‘G‘)
    plt.show()