猫狗识别尝试

一.实验准备
1.软件
自行下载Anaconda3
二.实验过程
在 Jupyter Notebook中实验

1.数据集
（1）下载 百度网盘下载

kaggle网站的数据集下载地址： https://www.kaggle.com/lizhensheng/-2000

（2）分类
2.代码

import tensorflow as tf
import keras
import os, shutil 
# 原始目录所在的路径
original_dataset_dir = 'G:\\Cat_And_Dog\\kaggle\\train\\'

# 数据集分类后的目录
base_dir = 'G:\\Cat_And_Dog\\kaggle\\cats_and_dogs_small'
os.mkdir(base_dir)

# # 训练、验证、测试数据集的目录
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)

# 猫训练图片所在目录
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)

# 狗训练图片所在目录
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)

# 猫验证图片所在目录
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)

# 狗验证数据集所在目录
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)

# 猫测试数据集所在目录
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)

# 狗测试数据集所在目录
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_dir)

# 将前1000张猫图像复制到train_cats_dir
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)

# 将下500张猫图像复制到validation_cats_dir
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)
    
# 将下500张猫图像复制到test_cats_dir
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)
    
# 将前1000张狗图像复制到train_dogs_dir
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)
    
# 将下500张狗图像复制到validation_dogs_dir
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)
    
# 将下500张狗图像复制到test_dogs_dir
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)

对应目录下图片数量

#输出数据集对应目录下图片数量
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)))

2.实验
（1）搭建模型

#网络模型构建
from keras import layers
from keras import models
#keras的序贯模型
model = models.Sequential()
#卷积层，卷积核是3*3，激活函数relu
model.add(layers.Conv2D(32, (3, 3), activation='relu',
                        input_shape=(150, 150, 3)))
#最大池化层
model.add(layers.MaxPooling2D((2, 2)))
#卷积层，卷积核2*2，激活函数relu
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
#最大池化层
model.add(layers.MaxPooling2D((2, 2)))
#卷积层，卷积核是3*3，激活函数relu
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
#最大池化层
model.add(layers.MaxPooling2D((2, 2)))
#卷积层，卷积核是3*3，激活函数relu
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
#最大池化层
model.add(layers.MaxPooling2D((2, 2)))
#flatten层，用于将多维的输入一维化，用于卷积层和全连接层的过渡
model.add(layers.Flatten())
#全连接，激活函数relu
model.add(layers.Dense(512, activation='relu'))
#全连接，激活函数sigmoid
model.add(layers.Dense(1, activation='sigmoid'))

（2）查看模型情况

#输出模型各层的参数状况
model.summary()

（3）配置

model.compile(optimizer = 优化器，
              loss = 损失函数，
              metrics = ["准确率”])

优化器和损失函数可以是字符串形式的名字，也可以是函数形式

from keras import optimizers

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

（4）转换格式 调整为150*150

from keras.preprocessing.image import ImageDataGenerator

# 所有图像将按1/255重新缩放
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        # 这是目标目录
        train_dir,
        # 所有图像将调整为150x150
        target_size=(150, 150),
        batch_size=20,
        # 因为我们使用二元交叉熵损失，我们需要二元标签
        class_mode='binary')

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

查看结果

#查看上面对于图片预处理的处理结果
for data_batch, labels_batch in train_generator:
    print('data batch shape:', data_batch.shape)
    print('labels batch shape:', labels_batch.shape)
    break

（5）生成保存模型

#模型训练过程
history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,
      epochs=30,
      validation_data=validation_generator,
      validation_steps=50)
#保存训练得到的的模型
model.save('G:\\Cat_And_Dog\\kaggle\\cats_and_dogs_small_1.h5')

（6）可视化结果

#对于模型进行评估，查看预测的准确性
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(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()