卷积神经网络之猫狗分类

# 卷积神经网络初体验
import os, shutil
from datetime import datetime

from keras import models
from keras import layers
from keras import optimizers
from keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt


def data_initial():
    # 原始数据集解压目录
    original_dataset_dir = r'D:\pycharm\DownloadData\cats_vs_dogs\train\train'
    # 小数据集保存目录
    base_dir = r'D:\pycharm\DownloadData\cats_vs_dogs\mini'
    # os.mkdir(base_dir)

    # 创建训练集，验证集，测试集目录
    train_dir = os.path.join(base_dir, 'train')
    # os.mkdir(train_dir)
    validation_dir = os.path.join(base_dir, 'validation')
    # os.mkdir(validation_dir)
    test_dir = os.path.join(base_dir, 'test')
    # os.mkdir(test_dir)

    # 猫的训练目录
    train_cats_dir = os.path.join(train_dir, 'cats')
    # os.mkdir(train_cats_dir)
    # 狗的训练目录
    train_dogs_dir = os.path.join(train_dir, 'dogs')
    # os.mkdir(train_dogs_dir)

    # 猫的验证目录
    validation_cats_dir = os.path.join(validation_dir, 'cats')
    # os.mkdir(validation_cats_dir)
    # 狗的验证目录
    validation_dogs_dir = os.path.join(validation_dir, 'dogs')
    # os.mkdir(validation_dogs_dir)

    # 猫的测试目录
    test_cats_dir = os.path.join(test_dir, 'cats')
    # os.mkdir(test_cats_dir)
    # 狗的测试目录
    test_dogs_dir = os.path.join(test_dir, 'dogs')
    # os.mkdir(test_dogs_dir)

    # 1000张猫的训练集
    fnames = ['cat.{}.jpg'.format(i) for i in range(1000)]
    for fname in fnames:
        src = os.path.join(original_dataset_dir, fname)
        dst = os.path.join(train_cats_dir, fname)
        shutil.copyfile(src, dst)

    # 500张猫的验证集
    fnames = ['cat.{}.jpg'.format(i) for i in range(1000, 1500)]
    for fname in fnames:
        src = os.path.join(original_dataset_dir, fname)
        dst = os.path.join(validation_cats_dir, fname)
        shutil.copyfile(src, dst)

    # 500张猫的测试集
    fnames = ['cat.{}.jpg'.format(i) for i in range(1500, 2000)]
    for fname in fnames:
        src = os.path.join(original_dataset_dir, fname)
        dst = os.path.join(test_cats_dir, fname)
        shutil.copyfile(src, dst)

    # 1000张狗的训练集
    fnames = ['dog.{}.jpg'.format(i) for i in range(1000)]
    for fname in fnames:
        src = os.path.join(original_dataset_dir, fname)
        dst = os.path.join(train_dogs_dir, fname)
        shutil.copyfile(src, dst)

    # 1000张狗的验证集
    fnames = ['dog.{}.jpg'.format(i) for i in range(1000, 1500)]
    for fname in fnames:
        src = os.path.join(original_dataset_dir, fname)
        dst = os.path.join(validation_dogs_dir, fname)
        shutil.copyfile(src, dst)

    # 1000张狗的测试集
    fnames = ['dog.{}.jpg'.format(i) for i in range(1500, 2000)]
    for fname in fnames:
        src = os.path.join(original_dataset_dir, fname)
        dst = os.path.join(test_dogs_dir, fname)
        shutil.copyfile(src, dst)

    # 检查
    print('total train_cat: ', len(os.listdir(train_cats_dir)))
    print('total validation_cat: ', len(os.listdir(validation_cats_dir)))
    print('total test_cat: ', len(os.listdir(test_cats_dir)))

    print('total train_dog: ', len(os.listdir(train_dogs_dir)))
    print('total validation_dog: ', len(os.listdir(validation_dogs_dir)))
    print('total test_dog: ', len(os.listdir(test_dogs_dir)))
    # 定义缩放比例
    train_datagen = ImageDataGenerator(rescale=1. / 255)
    test_datagen = ImageDataGenerator(rescale=1. / 255)

    train_generator = train_datagen.flow_from_directory(
        directory=train_dir,
        target_size=(150, 150),
        batch_size=20,
        class_mode='binary'
    )
    validation_generator = test_datagen.flow_from_directory(
        directory=validation_dir,
        target_size=(150, 150),
        batch_size=20,
        class_mode='binary'
    )
    return train_generator, validation_generator


# 创建模型
def create_convnet_model():
    model = models.Sequential()
    # 2D卷积层，32个过滤器，（3*3）卷积核，relu激活函数，输入形状为（150高*150宽*3通道）
    model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))
    # 2D最大池化
    model.add(layers.MaxPooling2D((2, 2)))
    # 64过滤器卷积层
    model.add(layers.Conv2D(64, (3, 3), activation='relu'))
    # 最大池化
    model.add(layers.MaxPooling2D((2, 2)))
    # 128过滤器卷积层
    model.add(layers.Conv2D(128, (3, 3), activation='relu'))
    # 最大池化
    model.add(layers.MaxPooling2D((2, 2)))
    # 128过滤器卷积层
    model.add(layers.Conv2D(128, (3, 3), activation='relu'))
    # 最大池化
    model.add(layers.MaxPooling2D((2, 2)))
    # 展平
    model.add(layers.Flatten())
    # 全连接层
    model.add(layers.Dense(512, activation='relu'))
    # 二分类层
    model.add(layers.Dense(1, activation='sigmoid'))
    # 输出模型
    model.summary()
    return model


if __name__ == '__main__':
    # 数据预处理,返回批量生成器
    train_generator, validation_generator = data_initial()
    model = create_convnet_model()
    # 编译模型
    model.compile(loss='binary_crossentropy', optimizer=optimizers.RMSprop(lr=1e-4), metrics=['acc'])

    # 开始拟合，计时
    start_time = datetime.now()
    # 使用批量生成器拟合模型
    history = model.fit_generator(
        train_generator,
        steps_per_epoch=100,
        epochs=30,
        validation_data=validation_generator,
        validation_steps=50
    )
    finish_time = datetime.now()
    print('运行时间: ', (finish_time - start_time).seconds)
    # 保存模型
    model.save('cats_vs_dogs_small.h5')
    print(history.history)
    # 绘制损失曲线和精度曲线
    acc = history.history['acc']
    val_acc = history.history['val_acc']
    loss = history.history['loss']
    val_loss = history.history['loss']
    epochs = range(1, len(acc) + 1)

    plt.plot(epochs, acc, 'bo', label='Training acc')
    plt.plot(epochs, val_acc, 'b', label='Validation acc')
    plt.title('Training and validation accuracy')
    plt.legend()
    plt.figure()

    plt.plot(epochs, loss, 'bo', label='Training loss')
    plt.plot(epochs, val_loss, 'b', label='Validation loss')
    plt.title('Training and validation loss')
    plt.legend()
    plt.show()

跑了接近四十分钟，明天敲优化。