15.手写数字识别-小数据集

Posted 2020-12-10 av10492

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)
y_data = digits.target.astype(np.float32).reshape(-1, 1) #手写数字数据集

 

 

 

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

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler, OneHotEncoder

scaler = MinMaxScaler() #归一化
X_data = scaler.fit_transform(x_data)
print(X_data)

Y = OneHotEncoder().fit_transform(y_data).todense() # oe-hot编码
print(Y)

X = X_data.reshape(-1, 8, 8, 1) # 转换为图片的格式 batch、height、width和channels


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：‘,
      X_train.shape, X_test.shape, y_train.shape, y_test.shape)#训练集测试集划分

 

 归一化后：

 

 

 oe-hot：

 

 

 划分后：

 

 

 

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, 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
#载入新的包

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‘)

 

定义训练参数可视化：

 

准确率图：

 

 

 

损失率图：

 

 

 

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
#加载两个新包

score = model.evaluate(X_test, y_test)
print(‘score：‘, score)
y_pred = model.predict_classes(X_test)
print(‘y_pred：‘, y_pred[:10])

y_test1 = np.argmax(y_test, axis=1).reshape(-1)
y_true = np.array(y_test1)[0] # 数据对比
pd.crosstab(y_true, y_pred, rownames=[‘true‘], colnames=[‘predict‘])# 交叉表与交叉矩阵

y_test1 = y_test1.tolist()[0]
a = pd.crosstab(np.array(y_test1), y_pred, rownames=[‘Lables‘], colnames=[‘Predict‘])

df = pd.DataFrame(a) # 转换DataFrame

sns.heatmap(df, annot=True, cmap="GnBu_r", linewidths=0.2, linecolor=‘G‘)# seaborn.heatmap ，选择蓝色来画图

plt.show()

模型score，y_pred的预测值：

 

最终画出来的图：