机器学习---14

1.手写数字数据集

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

import numpy as np
from sklearn.datasets import load_digits
digits = load_digits()

x_data = digits.data.astype(np.float32)
x_target = digits.target.astype(np.float32).reshape(-1, 1)
print("data-----")
print(x_data)
print("-"*10)
print("target"+"-"*10)
print(x_target)

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

 

 

 

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler, OneHotEncoder
#归一化
scaler = MinMaxScaler()
X_data = scaler.fit_transform(x_data)
print("data归一化"+"-"*100)
print(X_data)
print("-"*100)
# one-hot编码
X_target = OneHotEncoder().fit_transform(x_target).todense()
print("tagert独热编码"+"-"*100)
print(X_target)
print("-"*100)
# 转换为图片的格式
X_data_1 = X_data.reshape(-1, 8, 8, 1)
#训练集测试集划分
X_train, X_test, y_train, y_test = train_test_split(X_data_1, X_target, test_size=0.2, random_state=0, stratify=X_target)
print('X_train.shape, X_test.shape, y_train.shape, y_test.shape：',X_train.shape, X_test.shape, y_train.shape, 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。

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

model = Sequential()
ks = [3, 3]  # 卷积核

model.add(Conv2D(filters=16, kernel_size=ks, padding='same', input_shape=X_train.shape[1:], activation='relu'))# 一层卷积

model.add(MaxPool2D(pool_size=(2, 2)))# 池化层
model.add(Dropout(0.25))

model.add(Conv2D(filters=32, kernel_size=ks, padding='same', activation='relu'))# 二层卷积

model.add(MaxPool2D(pool_size=(2, 2)))# 池化层
model.add(Dropout(0.25))

model.add(Conv2D(filters=64, kernel_size=ks, padding='same', activation='relu'))# 三层卷积

model.add(Conv2D(filters=128, kernel_size=ks, padding='same', activation='relu'))# 四层卷积

model.add(MaxPool2D(pool_size=(2, 2)))# 池化层
model.add(Dropout(0.25))

model.add(Flatten())# 平坦层

model.add(Dense(128, activation='relu'))# 全连接层
model.add(Dropout(0.25))

model.add(Dense(10, activation='softmax'))# 激活函数
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)

import matplotlib.pyplot as plt

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)

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

import matplotlib.pyplot as plt

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)

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')