作业14 15 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()

#1、手写数字数据集
from sklearn.datasets import load_digits
import numpy as np
digits = load_digits()
X = digits.data.astype(np.float32)
Y = digits.target.astype(np.float32).reshape(-1, 1)  # 将y变为一列

结果如图：

  

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

#2、图片数据预处理
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import OneHotEncoder
from sklearn.model_selection import  train_test_split

scaler = MinMaxScaler()
x_data = scaler.fit_transform(X)
x = x_data.reshape(-1, 8, 8, 1)  # 转换为图片格式
y = OneHotEncoder().fit_transform(Y).todense() # y : 独热编码
# 训练集测试集划分
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, x_test.shape, y_train.shape, y_test.shape)

结果如图：

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。

#3.设计卷积神经网络结构
import tensorflow 
tensorflow.__version__
#导入相关包
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
#第一卷积层输入数据的shape要指定，其他层的数据shape框架会制动推导
model.add(Conv2D(filters=16,kernel_size=ks,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=ks,padding='same',activation='relu'))
model.add(MaxPool2D(pool_size=(2,2)))
model.add(Dropout(0.25))

model.add(Conv2D(filters=64,kernel_size=ks,padding='same',activation='relu'))
model.add(Conv2D(filters=128,kernel_size=ks,padding='same',activation='relu'))
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
model.add(Dense(10,activation='softmax'))
model.summary()

结果如图：

 

4.模型训练

# 4、模型训练
import matplotlib.pyplot as plt
# 损失函数:categorical_crossentropy,优化器:adam ,用准确率accuracy衡量模型
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# 划分20%作为验证数据,每次训练300个数据,训练迭代300轮
train_history = model.fit(x=x_train, y=y_train, validation_split=0.2, batch_size=300, epochs=10, verbose=2)

# 定义可视化
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, 'acc', 'val_acc')
# 损失率
show_train_history(train_history, 'loss', 'val_loss')

结果如图：

 

5.模型评价

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

#5、模型评估
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)
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="pink_r", linewidths=0.2, linecolor='G')

结果如图：