keras dog_vs_cat数据集学习

keras dog_vs_cat数据集学习

1.指定GPU，设置显存自动增长（非必须）

#指定gpu
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "1"

#设置显存自动增长
import tensorflow as tf
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)

2.将图像复制到训练、验证和测试的目录

数据集链接:https://pan.baidu.com/s/1qQKBdzejJlW544BbrWk4pg 提取码:6fdq

我们将2000张训练图像放入训练集中，将1000张验证图像放入验证集中，将1000张测试图像放入测试集中

import os,shutil

original_test_dir='/home/disk2/summer_internship_2020/team04/test/test'
original_train_dir='/home/disk2/summer_internship_2020/team04/train/train'

base_dir='/home/disk2/summer_internship_2020/team04/dog-vs-cats_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)

fnames = ['cat.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
    src = os.path.join(original_train_dir,fname)
    dst = os.path.join(train_cats_dir,fname)
    shutil.copyfile(src,dst)

fnames = ['cat.{}.jpg'.format(i) for i in range(1000,1500)]
for fname in fnames:
    src = os.path.join(original_train_dir,fname)
    dst = os.path.join(validation_cats_dir,fname)
    shutil.copyfile(src,dst)

fnames = ['cat.{}.jpg'.format(i) for i in range(1500,2000)]
for fname in fnames:
    src = os.path.join(original_train_dir,fname)
    dst = os.path.join(test_cats_dir,fname)
    shutil.copyfile(src,dst)

fnames = ['dog.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
    src = os.path.join(original_train_dir,fname)
    dst = os.path.join(train_dogs_dir,fname)
    shutil.copyfile(src,dst)

fnames = ['dog.{}.jpg'.format(i) for i in range(1000,1500)]
for fname in fnames:
    src = os.path.join(original_train_dir,fname)
    dst = os.path.join(validation_dogs_dir,fname)
    shutil.copyfile(src,dst)

fnames = ['dog.{}.jpg'.format(i) for i in range(1500,2000)]
for fname in fnames:
    src = os.path.join(original_train_dir,fname)
    dst = os.path.join(test_dogs_dir,fname)
    shutil.copyfile(src,dst)

3.构建网络

特征图的深度逐渐增大，特征图的尺寸逐渐缩小

from tensorflow.python.keras import models
from tensorflow.python.keras import layers

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'))

4.从目录中读取图像

除以255是为了将像素值缩放到[0,1]区间内

from tensorflow.python.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 = train_datagen.flow_from_directory(
    validation_dir,
    target_size=(150,150),
    batch_size=20,
    class_mode='binary')

5.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)

训练集图像数量=steps_per_epoch*batch_size

测试集图像数量=validation_steps*batch_size

6.保存模型

model.save('cat_and_dogs_small_1.h5')

7.绘制训练损失和验证损失

import matplotlib as mpl
mpl.use('Agg')
import matplotlib.pyplot as plt


history_dict = history.history
loss_values = history_dict['loss']
val_loss_values = history_dict['val_loss']

epochs = range(1, len(loss_values) + 1)

plt.plot(epochs, loss_values, 'bo', label='Training loss')        #‘bo'表示蓝色圆点
plt.plot(epochs, val_loss_values, 'b', label='Validation loss')   #’b‘ 表示蓝色实线
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()

plt.show()
plt.savefig('loss' + '_labeled.jpg')

#绘制训练精度和验证精度
plt.clf()
acc = history_dict['acc']
val_acc = history_dict['val_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.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()

plt.show()
plt.savefig('acc' + '_labeled.jpg')