14.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()

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

import numpy as np
from sklearn.preprocessing import MinMaxScaler
X_data = digits.data.astype(np.float32)
scaler = MinMaxScaler()
X_data = scaler.fit_transform(X_data)
print("归一化后",X_data)
X=X_data.reshape(-1,8,8,1)
from sklearn.preprocessing import OneHotEncoder
y = digits.target.astype(np.float32).reshape(-1,1)
Y = OneHotEncoder().fit_transform(y).todense()
print("独热编码：",Y)
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,Y,test_size=0.2,random_state=0,stratify=Y)
print("X_data.shape:",X_data.shape)
print("X.shape:",X.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。

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,Dropout,Conv2D,MaxPool2D,Flatten
model = Sequential()
ks = (3, 3) 
input_shape = X_train.shape[1:]
model.add(Conv2D(filters=16, kernel_size=ks, padding='same', input_shape=input_shape, activation='relu'))
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
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))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.25))
model.add(Dense(10, activation='softmax'))
print(model.summary())

4.模型训练

import matplotlib.pyplot as plt
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()
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)
show_train_history(train_history, 'accuracy', 'val_accuracy')
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 pandas as pd
import seaborn as sns
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]
pd.crosstab(y_true, y_pred, rownames=['true'], colnames=['predict'])
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="Blues", linewidths=0.2, linecolor='G')
plt.show()