手写数字识别-小数据集

1.手写数字数据集

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

#导入手写数字数据集
from sklearn.datasets import load_digits
import numpy as np
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

# 归一化MinMaxScaler()
from sklearn.preprocessing import MinMaxScaler
X_data = digits.data.astype(np.float32)
scaler = MinMaxScaler()
X_data = scaler.fit_transform(X_data)
print("归一化后",X_data)
# 转化为图片的格式
X=X_data.reshape(-1,8,8,1)

独热编码：

# 独热编码
from sklearn.preprocessing import OneHotEncoder
# y = digits.target.reshape(-1,1)
#将Y_data变为一列
y = digits.target.astype(np.float32).reshape(-1,1)  
Y = OneHotEncoder().fit_transform(y).todense() #张量结构todense
print("独热编码：",Y)
# 切分数据集
from sklearn.model_selection import train_test_split
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)

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。

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,Dropout,Conv2D,MaxPool2D,Flatten
#3、建立模型
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'))
print(model.summary())

4.模型训练

import matplotlib.pyplot as plt
# 画图
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()

# 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)
# 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

import pandas as pd
import seaborn as sns
# model.evaluate()
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()