【深度学习实战—5】：基于AlexNet的CIFAR10数据集分类（附Keras实现）

✨博客主页：米开朗琪罗~
✨博主爱好：羽毛球
✨年轻人要：Living for the moment（活在当下）！
推荐专栏：【图像处理】【千锤百炼Python】【深度学习】【排序算法】

之前我们用AlexNet进行了手写数字的识别，今天带来对cifar10数据集的分类！文末附完整程序！

一、数据集获取

"""
数据集获取
"""
def get_cifar10_data():

    # x_train_original和y_train_original代表训练集的图像与标签, x_test_original与y_test_original代表测试集的图像与标签
    (x_train_original, y_train_original), (x_test_original, y_test_original) = cifar10.load_data()

    # 验证集分配（从测试集中抽取，因为训练集数据量不够）
    x_val = x_test_original[:5000]
    y_val = y_test_original[:5000]
    x_test = x_test_original[5000:]
    y_test = y_test_original[5000:]
    x_train = x_train_original
    y_train = y_train_original

    # 这里把数据从unint类型转化为float32类型, 提高训练精度。
    x_train = x_train.astype('float32')
    x_val = x_val.astype('float32')
    x_test = x_test.astype('float32')

    # 原始图像的像素灰度值为0-255，为了提高模型的训练精度，通常将数值归一化映射到0-1。
    x_train = x_train / 255
    x_val = x_val / 255
    x_test = x_test / 255

    # 图像标签一共有10个类别即0-9，这里将其转化为独热编码（One-hot）向量
    y_train = np_utils.to_categorical(y_train)
    y_val = np_utils.to_categorical(y_val)
    y_test = np_utils.to_categorical(y_test)

    return x_train, y_train, x_val, y_val, x_test, y_test

二、定义AlexNet

"""
定义alexnet网络模型
"""
def alexnet():
    model = Sequential()

    model.add(Conv2D(96, (11, 11), strides=(4, 4), input_shape=(32, 32, 3), padding='same', activation='relu',
                     kernel_initializer='uniform'))
    model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
    model.add(BatchNormalization())

    model.add(Conv2D(256, (5, 5), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
    model.add(BatchNormalization())

    model.add(Conv2D(384, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))

    model.add(Conv2D(384, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))

    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))

    model.add(Flatten())
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(10, activation='softmax'))
    print(model.summary())

    return model

三、编译并训练

"""
编译网络并训练
"""
x_train, y_train, x_val, y_val, x_test, y_test = get_cifar10_data()
model = alexnet()

# 编译网络（定义损失函数、优化器、评估指标）
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

# 开始网络训练（定义训练数据与验证数据、定义训练代数，定义训练批大小）
train_history = model.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=20, batch_size=16, verbose=2)

# 模型保存
model.save('alexnet_cifar10.h5')

# 定义训练过程可视化函数（训练集损失、验证集损失、训练集精度、验证集精度）
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='best')
    plt.show()

show_train_history(train_history, 'accuracy', 'val_accuracy')
show_train_history(train_history, 'loss', 'val_loss')

训练过程如下：

四、测试模型

# 输出网络在测试集上的损失与精度
score = model.evaluate(x_test, y_test)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

# 输出网络在测试集上的损失与精度
score = model.evaluate(x_test, y_test)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

# 测试集结果预测
predictions = model.predict(x_test)
predictions = np.argmax(predictions, axis=1)
print('前20张图片预测结果：', predictions[:20])

测试结果：

Test loss: 2.0042192935943604
Test accuracy: 0.5730000138282776
前20张图片预测结果： [7 6 8 4 4 5 4 3 4 4 7 5 3 3 7 2 5 7 8 1]

因为博主电脑显存不足，所以用的CPU运行的，且batch_size略低，训练批次也不足，所以结果没有很理想！

五、预测结果可视化

# 预测结果图像可视化
(x_train_original, y_train_original), (x_test_original, y_test_original) = cifar10.load_data()
def cifar10_visualize_multiple_predict(start, end, length, width):

    for i in range(start, end):
        plt.subplot(length, width, 1 + i)
        plt.imshow(x_test_original[i], cmap=plt.get_cmap('gray'))
        title_true = 'true=' + str(y_test_original[i])                  # 图像真实标签
        title_prediction = ',' + 'prediction' + str(predictions[i])     # 预测结果
        title = title_true + title_prediction
        plt.title(title)
        plt.xticks([])
        plt.yticks([])
    plt.show()

cifar10_visualize_multiple_predict(start=0, end=9, length=3, width=3)

可视化结果：

附录：完整程序

from keras.datasets import cifar10
import matplotlib.pyplot as plt
import pickle
from keras.utils import np_utils
import numpy as np
import pandas as pd
import seaborn as sns
from sklearn.metrics import confusion_matrix
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization
from keras.models import Sequential
from keras.utils import np_utils
import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
"""
数据集获取
"""
def get_cifar10_data():

    # x_train_original和y_train_original代表训练集的图像与标签, x_test_original与y_test_original代表测试集的图像与标签
    (x_train_original, y_train_original), (x_test_original, y_test_original) = cifar10.load_data()

    # 验证集分配（从测试集中抽取，因为训练集数据量不够）
    x_val = x_test_original[:5000]
    y_val = y_test_original[:5000]
    x_test = x_test_original[5000:]
    y_test = y_test_original[5000:]
    x_train = x_train_original
    y_train = y_train_original

    # 这里把数据从unint类型转化为float32类型, 提高训练精度。
    x_train = x_train.astype('float32')
    x_val = x_val.astype('float32')
    x_test = x_test.astype('float32')

    # 原始图像的像素灰度值为0-255，为了提高模型的训练精度，通常将数值归一化映射到0-1。
    x_train = x_train / 255
    x_val = x_val / 255
    x_test = x_test / 255

    # 图像标签一共有10个类别即0-9，这里将其转化为独热编码（One-hot）向量
    y_train = np_utils.to_categorical(y_train)
    y_val = np_utils.to_categorical(y_val)
    y_test = np_utils.to_categorical(y_test)

    return x_train, y_train, x_val, y_val, x_test, y_test

"""
定义alexnet网络模型
"""
def alexnet():
    model = Sequential()

    model.add(Conv2D(96, (11, 11), strides=(4, 4), input_shape=(32, 32, 3), padding='same', activation='relu',
                     kernel_initializer='uniform'))
    model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
    model.add(BatchNormalization())

    model.add(Conv2D(256, (5, 5), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
    model.add(BatchNormalization())

    model.add(Conv2D(384, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))

    model.add(Conv2D(384, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))

    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))

    model.add(Flatten())
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(10, activation='softmax'))
    print(model.summary())

    return model

"""
编译网络并训练
"""
x_train, y_train, x_val, y_val, x_test, y_test = get_cifar10_data()
model = alexnet()

# 编译网络（定义损失函数、优化器、评估指标）
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

# 开始网络训练（定义训练数据与验证数据、定义训练代数，定义训练批大小）
train_history = model.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=20, batch_size=64, verbose=2)

# 模型保存
model.save('alexnet_cifar10.h5')

# 定义训练过程可视化函数（训练集损失、验证集损失、训练集精度、验证集精度）
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='best')
    plt.show()

show_train_history(train_history, 'accuracy', 'val_accuracy')
show_train_history(train_history, 'loss', 'val_loss')

# 输出网络在测试集上的损失与精度
score = model.evaluate(x_test, y_test)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

# 输出网络在测试集上的损失与精度
score = model.evaluate(x_test, y_test)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

# 测试集结果预测
predictions = model.predict(x_test)
predictions = np.argmax(predictions, axis=1)
print('前20张图片预测结果：', predictions[:20])

# 预测结果图像可视化
(x_train_original, y_train_original), (x_test_original, y_test_original) = cifar10.load_data()
def cifar10_visualize_multiple_predict(start, end, length, width):

    for i in range(start, end):
        plt.subplot(length, width, 1 + i)
        plt.imshow(x_test_original[i], cmap=plt.get_cmap('gray'))
        title_true = 'true=' + str(y_test_original[i])                  # 图像真实标签
        title_prediction = ',' + 'prediction' + str(predictions[i])     # 预测结果
        title = title_true + title_prediction
        plt.title(title)
        plt.xticks([])
        plt.yticks([])
    plt.show()

cifar10_visualize_multiple_predict(start=0, end=9, length=3, width=3)