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()

digits = load_digits()
X_data = digits.data.astype(np.float32)
Y_data = digits.target.astype(np.float32).reshape(-1, 1)# 将Y_data变为一列

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

# 将属性缩放到一个指定的最大和最小值（通常是1-0之间）
scaler = MinMaxScaler()
X_data = scaler.fit_transform(X_data)
print("MinMaxScaler_trans_X_data：")
print(X_data)

Y = OneHotEncoder().fit_transform(Y_data).todense()# 进行oe-hot编码
print("one-hot_Y：")
print(Y)

# 转换为图片的格式（batch, height, width, channels）
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_test.shape, y_train.shape, y_test.shape：', X_train.shape, X_test.shape, y_train.shape, y_test.shape)

x：归一化MinMaxScaler()

y：独热编码OneHotEncoder()或to_categorical

训练集测试集划分

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。

model = Sequential()
ks = (3, 3)  # 卷积核的大小
input_shape = X_train.shape[1:]
model.add(Conv2D(filters=16, kernel_size=ks, padding='same', input_shape=input_shape, activation='relu'))# 一层卷积，padding='same',tensorflow会对输入自动补0
model.add(MaxPool2D(pool_size=(2, 2)))# 池化层1
model.add(Dropout(0.25))# 防止过拟合，随机丢掉连接
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2
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3
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softmax
model.summary()

4.模型训练

# 训练模型
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

第一次运行损失率loss:1.2753，准确率accuracy：0.6750

第二次运行

训练参数可视化

# 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')

准确率

损失率

5.模型评价

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

# 模型评价
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
pd.crosstab(y_true, y_pred, rownames=['true'], colnames=['predict'])

# 交叉矩阵
y_test1 = y_test1.tolist()[0]
a = pd.crosstab(np.array(y_test1), y_pred)
df = pd.DataFrame(a)
sns.heatmap(df, annot=True, cmap="YlGnBu", linewidths=0.2, linecolor='G')
plt.show()

模型评价score，预测值y_pred

交叉表查看预测数据与原数据对比

代码如下：

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.datasets import load_digits#小数据集8*8
from sklearn.model_selection import train_test_split# 训练集测试集划分
from sklearn.preprocessing import OneHotEncoder#独热编码
from sklearn.preprocessing import MinMaxScaler#归一化
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D
from sklearn.metrics import accuracy_score
import seaborn as sns

digits = load_digits()
X_data = digits.data.astype(np.float32)
Y_data = digits.target.astype(np.float32).reshape(-1, 1)# 将Y_data变为一列


# 将属性缩放到一个指定的最大和最小值（通常是1-0之间）
scaler = MinMaxScaler()
X_data = scaler.fit_transform(X_data)
print("MinMaxScaler_trans_X_data：")
print(X_data)

Y = OneHotEncoder().fit_transform(Y_data).todense()# 进行oe-hot编码
print("one-hot_Y：")
print(Y)

# 转换为图片的格式（batch, height, width, channels）
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_test.shape, y_train.shape, y_test.shape：', X_train.shape, X_test.shape, y_train.shape, y_test.shape)


model = Sequential()
ks = (3, 3)  # 卷积核的大小
input_shape = X_train.shape[1:]
model.add(Conv2D(filters=16, kernel_size=ks, padding='same', input_shape=input_shape, activation='relu'))# 一层卷积，padding='same',tensorflow会对输入自动补0
model.add(MaxPool2D(pool_size=(2, 2)))# 池化层1
model.add(Dropout(0.25))# 防止过拟合，随机丢掉连接
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2
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3
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softmax
model.summary()


# 训练模型
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')


# 模型评价
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
pd.crosstab(y_true, y_pred, rownames=['true'], colnames=['predict'])

# 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)
sns.heatmap(df, annot=True, cmap="YlGnBu", linewidths=0.2, linecolor='G')
plt.show()