"""Kaggle发布的猫狗数据集
4000张猫狗图片,2000张猫,2000张狗。将2000张图片用于训练,1000张用于验证,1000张用于测试
下载数据集之后,创建一个新的数据集,包含三个子集:每个类别各1000各样本的训练集,500各样本的验证集,500各样本的测试机"""
import os, shutil
original_dataset_dir = '/python 深度学习/datasets/kaggle/train'
base_dir = '/python 深度学习/datasets/cats_and_dogs_small'
os.mkdir(base_dir)
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)
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_dir)
"""在创建好的文件里面填充数据,将数据复制到里面"""
fnames = ['cat.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
scr = os.path.join(original_dataset_dir, fname)
dst = os.path.join(train_cats_dir, fname)
shutil.copyfile(scr, dst)
fnames = ['cat.{}.jpg'.format(i) for i in range(1000, 1500)]
for fname in fnames:
scr = os.path.join(original_dataset_dir, fname)
dst = os.path.join(validation_cats_dir, fname)
shutil.copyfile(scr, dst)
fnames = ['cat.{}.jpg'.format(i) for i in range(1500, 2000)]
for fname in fnames:
scr = os.path.join(original_dataset_dir, fname)
dst = os.path.join(test_cats_dir, fname)
shutil.copyfile(scr, dst)
fnames = ['dog.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
scr = os.path.join(original_dataset_dir, fname)
dst = os.path.join(train_dogs_dir, fname)
shutil.copyfile(scr, dst)
fnames = ['dog.{}.jpg'.format(i) for i in range(1000, 1500)]
for fname in fnames:
scr = os.path.join(original_dataset_dir, fname)
dst = os.path.join(validation_dogs_dir, fname)
shutil.copyfile(scr, dst)
fnames = ['dog.{}.jpg'.format(i) for i in range(1500, 2000)]
for fname in fnames:
scr = os.path.join(original_dataset_dir, fname)
dst = os.path.join(test_dogs_dir, fname)
shutil.copyfile(scr, dst)
print(len(os.listdir(train_cats_dir)))
print(len(os.listdir(train_dogs_dir)))
print(len(os.listdir(validation_cats_dir)))
print(len(os.listdir(validation_dogs_dir)))
print(len(os.listdir(test_cats_dir)))
print(len(os.listdir(test_dogs_dir)))
"""网络构建"""
from tensorflow.keras import layers
from tensorflow.keras import models
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))
model.add(layers.MaxPool2D(2, 2))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPool2D(2, 2))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPool2D(2, 2))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPool2D(2, 2))
model.add(layers.Flatten())
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
model.summary()

"""配置模型用于训练"""
from tensorflow.keras import optimizers
model.compile(optimizer=optimizers.RMSprop(lr=1e-4),
loss='binary_crossentropy',
metrics=['acc'])
"""数据预处理
数据输入神经网络前,应该将数据格式化为经过预处理的浮点张量,目前的数据格式jpeg
(1)读取图像文件
(2)将JPEG文件解码为RGB
(3)像素转化为浮点张量
(4)normalization化,标准化数据,缩放到【0, 1】之间(神经网络喜欢处理较小的输入值)
keras自带图像转化工具,快速创建python生成器,将硬盘上的图像文件自动转化为预处理好的张量,批量"""
from tensorflow.keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(train_dir,
target_size=(150, 150),
batch_size=20,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(validation_dir,
target_size=(150, 150),
batch_size=20,
class_mode='binary')
"""利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)
model.save('cats_and_dogs_small_1.h5')


"""绘制训练过程的损失与精度曲线"""
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, 30 + 1)
plt.plot(epochs, acc, 'bo', label='Training accuracy')
plt.plot(epochs, val_acc, 'b', label='Validation accuracy')
plt.xlabel('epochs')
plt.ylabel('accuracy')
plt.title('Training and Validation accuracy')
plt.legend()
plt.show()
plt.plot(epochs, loss, 'ro', label='Training loss')
plt.plot(epochs, val_loss, 'r', label='Validation loss')
plt.xlabel('epochs')
plt.ylabel('loss')
plt.title('Training and Validation loss')
plt.legend()
plt.show()
