Python深度学习笔记07--使用Keras建立卷积神经网络

from keras.datasets import mnist
from keras.utils import to_categorical

#1. 获取数据
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

#2. 处理数据
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32') / 255

test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32') / 255

train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

from keras import layers
from keras import models

#3. 建立网络模型
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))

model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))

# print(model.summary())

'''
#网络参数计算方式
1.conv2d有320个参数，计算方式：(3 * 3 * 1 + 1) * 32
2.conv2d_1有18496个参数，计算方式：(3 * 3 * 32 + 1) * 64
3.conv2d_2有36928个参数，计算方式：(3 * 3 * 64 + 1) * 64
4.dense有36928个参数，计算方式：(576 + 1) * 64
5.dense_1有650个参数，计算方式：(64 + 1) * 10
'''
#4. 设置编译参数
model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

#5. 设置训练条件并训练             
model.fit(train_images, train_labels, epochs=5, batch_size=64)

#6. 评估模型
test_loss, test_acc = model.evaluate(test_images, test_labels)
#313/313 [==============================] - 1s 3ms/step - loss: 0.0324 - accuracy: 0.9898

print(test_acc)
#0.989799976348877

5.1 卷积神经网络简介 

5.1.1 卷积运算

卷积神经网络有以下两个性质：

(1)卷积神经网络学到的模式具有平移不变性。

(2)卷积神经网络可以学到模式的空间层次结构i。

卷积的两个关键参数：

(1)从输入中提取的图块尺寸

(2)输出特征的深度

Keras的API为：Conv2D(output_depth, window_height, window_width)

注意：书上这部分对卷积过程的描述不是很容易理解，建议看吴恩达的视频来学习卷积网络相关的概念。

吴恩达卷积神经网络课程地址

5.1.2 最大池化运算

最大池化是从输入特征图中提取窗口，并输出每个通道的最大值。

最大池化通常使用2 * 2的窗口和步幅2，其目的是将特征图下采样2倍。

5.2 在小型数据集上从头开始训练一个卷积神经网络

卷积神经网络代码如下：

import os, shutil

# The path to the directory where the original
# dataset was uncompressed
# original_dataset_dir = '/Users/fchollet/Downloads/kaggle_original_data'
original_dataset_dir = 'E:\desktop\code\data\dogs-vs-cats\train'

# The directory where we will
# store our smaller dataset
# base_dir = '/Users/fchollet/Downloads/cats_and_dogs_small'
base_dir = 'E:\desktop\code\data\dogs-vs-cats\cats_and_dogs_small'
# os.mkdir(base_dir)

# Directories for our training,
# validation and test splits
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)

# Directory with our training cat pictures
train_cats_dir = os.path.join(train_dir, 'cats')
# os.mkdir(train_cats_dir)

# Directory with our training dog pictures
train_dogs_dir = os.path.join(train_dir, 'dogs')
# os.mkdir(train_dogs_dir)

# Directory with our validation cat pictures
validation_cats_dir = os.path.join(validation_dir, 'cats')
# os.mkdir(validation_cats_dir)

# Directory with our validation dog pictures
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
# os.mkdir(validation_dogs_dir)

# Directory with our validation cat pictures
test_cats_dir = os.path.join(test_dir, 'cats')
# os.mkdir(test_cats_dir)

# Directory with our validation dog pictures
test_dogs_dir = os.path.join(test_dir, 'dogs')
# os.mkdir(test_dogs_dir)


# #验证图片存放是否正确
# print('total training cat images:', len(os.listdir(train_cats_dir)))

# print('total training dog images:', len(os.listdir(train_dogs_dir)))

# print('total validation cat images:', len(os.listdir(validation_cats_dir)))

# print('total validation dog images:', len(os.listdir(validation_dogs_dir)))

# print('total test cat images:', len(os.listdir(test_cats_dir)))

# print('total test dog images:', len(os.listdir(test_dogs_dir)))


from keras import layers
from keras import models

model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu',
                        input_shape=(150, 150, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

from keras import optimizers

model.compile(loss='binary_crossentropy',
              optimizer=optimizers.RMSprop(lr=1e-4),
              metrics=['acc'])


from keras.preprocessing.image import ImageDataGenerator

# All images will be rescaled by 1./255
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        # This is the target directory
        train_dir,
        # All images will be resized to 150x150
        target_size=(150, 150),
        batch_size=20,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        validation_dir,
        target_size=(150, 150),
        batch_size=20,
        class_mode='binary')        

history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,
      epochs=30,
      validation_data=validation_generator,
      validation_steps=50)       

model.save('cats_and_dogs_small_1.h5')
# model.load_weights('cats_and_dogs_small_1.h5')



import matplotlib.pyplot as plt

# #dict_keys(['loss', 'accuracy', 'val_loss', 'val_accuracy'])
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(len(acc))

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()