6.10第十四次作业

1.手写数字数据集

• 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：

digits = load_digits()

X_data = digits.data.astype(np.float32)
Y_data = digits.target.astype(np.float32).reshape(-1, 1)

scaler = MinMaxScaler()
# x：归一化MinMaxScaler()
X_data = scaler.fit_transform(X_data)
print("MinMaxScaler_trans_X_data：",X_data)

# y：独热编码OneHotEncoder()或to_categorical
Y = OneHotEncoder().fit_transform(Y_data).todense()
print("one-hot_Y：",Y)

# 转换为图片的格式
X = X_data.reshape(-1, 8, 8, 1)
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_train.shape)
print('X_test.shape：', X_test.shape)
print('y_train.shape：',y_train.shape)
print('y_test.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。

代码：

# 设计卷积神经网络结构
model = Sequential()
# 先制定卷积核的大小
ks = (3, 3)
input_shape = X_train.shape[1:]

# +一层卷积
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)))

# +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)))

# +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))

model.add(Dense(10, activation='softmax'))
model.summary()

4.模型训练

准确率：

损失率：

 

 代码：

# 训练模型
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)
score = model.evaluate(X_test,y_test)
score
# 定义训练参数可视化
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, '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