0


基于kaggle数据集的猫狗识别(超详细版本)

目录

下载kaggle数据集

kaggle猫狗识别数据集共包含25000张JPEG数据集照片,其中猫和狗的照片各占12500张。数据集大小经过压缩打包后占543MB。
数据集可以从kaggle官方网站下载,链接如下:

https://www.kaggle.com/c/dogs-vs-cats/data

如果嫌官网下载麻烦,也可以从博主之前分享的百度网盘链接中直接获取:

网盘分享—博客链接,点击>>>

在下载的kaggle数据集基础上,创建一个新的小数据集,其中包含三个子集。

猫和狗的数据集:各 1000 个样本的训练集、各 500 个样本的验证集、各 500 个样本的测试集。

创建新的小数据集

下面的网络所使用的数据集不是从kaggle网站中直接下载下来的完整数据集,而是基于kaggle完整数据集的部分小数据集。

import os, shutil
# 下载的kaggle数据集路径
original_dataset_dir = '/Users/Downloads/kaggle_original_data' 
# 新的小数据集放置路径
base_dir = '/Users/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)

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)

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)

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)

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)

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)

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)

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)))

以上程序会生成各个文件夹路径,并将对应的训练集、验证集、测试集复制进去生成新的小数据集。

以上程序输出结果如下:

total training cat images: 1000
total training dog images: 1000
total validation cat images: 500
total validation dog images: 500
total test cat images: 500
total test dog images: 500

构建猫狗分类的小型卷积神经网络

猫狗分类的网络架构

# 网络架构
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'))
print(model.summary())

输出的特征图的维度随层变化的情况如下:

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 148, 148, 32)      896       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 74, 74, 32)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 72, 72, 64)        18496     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 36, 36, 64)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 34, 34, 128)       73856     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 17, 17, 128)       0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 15, 15, 128)       147584    
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 7, 7, 128)         0         
_________________________________________________________________
flatten (Flatten)            (None, 6272)              0         
_________________________________________________________________
dense (Dense)                (None, 512)               3211776   
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 513       
=================================================================
Total params: 3,453,121
Trainable params: 3,453,121
Non-trainable params: 0
_________________________________________________________________

模型的配置

from tensorflow.keras import optimizers
model.compile(loss=‘binary_crossentropy’,
optimizer=optimizers.RMSprop(lr=1e-4),
metrics=[‘acc’])

图像的预处理

# 图像预处理
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)

# 此处改成自己的路径
train_dir='D:\\0 keras shujuji\\kaggle\\modle_date\\train'
validation_dir='D:\\0 keras shujuji\\kaggle\\modle_date\\validation'

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)

##保存模型

model.save('cats_and_dogs_small_1.h5')

绘制精度和损失

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, 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()

结果显示

在这里插入图片描述

把本节(构建猫狗分类的小型卷积神经网络)各个子程序结合在一起就可以显示结果了,需要修改 模型的预处理 一节中的数据集放置路径

随机增强后的训练图像显示

from keras.preprocessing import image
import os
import matplotlib.pyplot as plt
from keras.preprocessing.image import ImageDataGenerator

datagen = ImageDataGenerator(
 rotation_range=40,
 width_shift_range=0.2,
 height_shift_range=0.2,
 shear_range=0.2,
 zoom_range=0.2,
 horizontal_flip=True,
 fill_mode='nearest')

# 自己的train_cats_dir数据集路径
train_cats_dir='D:\\modle_date\\train\\cats'

fnames = [os.path.join(train_cats_dir, fname) for fname in os.listdir(train_cats_dir)]
img_path = fnames[3]
img = image.load_img(img_path, target_size=(150, 150))
x = image.img_to_array(img)
x = x.reshape((1,) + x.shape)
i = 0
for batch in datagen.flow(x, batch_size=1):
    plt.figure(i)
    imgplot = plt.imshow(image.array_to_img(batch[0]))
    i += 1
    if i % 4 == 0:
        break
plt.show()

结果显示

在这里插入图片描述

这一节(随机增强后的训练图像显示)的代码也可以单独出结果

使用数据增强的卷积神经网络

网络架构

# 网络架构
from keras import layers
from keras import models
from tensorflow.keras import optimizers
from keras.preprocessing.image import ImageDataGenerator

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.Dropout(0.5))
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

模型的编译

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

利用数据增强生成器重新训练网络

# 自己的数据集路径
train_dir='D:\\kaggle\\modle_date\\train'
validation_dir='D:\\kaggle\\modle_date\\validation'

train_datagen = ImageDataGenerator(rescale=1./255,
                                   rotation_range=40,
                                   width_shift_range=0.2,
                                   height_shift_range=0.2,
                                   shear_range=0.2,
                                   zoom_range=0.2,
                                   horizontal_flip=True,)
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(train_dir,
                                                    target_size=(150, 150),
                                                    batch_size=32,
                                                    class_mode='binary')
validation_generator = test_datagen.flow_from_directory(validation_dir,
                                                        target_size=(150, 150),
                                                        batch_size=32,
                                                        class_mode='binary')

修改后的拟合函数

拟合函数这里改动了下,原来的steps_per_epoch=100,运行时会出错,原因是数据集量变小,结合运行错误提示,上限可以到63,因此这里改为steps_per_epoch=63;同理, validation_steps也应该随着改变,改为 validation_steps=32,以下代码已做更正。

history = model.fit_generator(train_generator,
                              # steps_per_epoch=100,
                              steps_per_epoch=63,  #  取上限63
                              epochs=100,
                              validation_data=validation_generator,
                              validation_steps=32) # 改为32

模型的保存

model.save('cats_and_dogs_small_2.h5')

结果输出

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, 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()

结果展示

经过一百个轮次,模型训练完毕
在这里插入图片描述
模型的精度和损失图像:
在这里插入图片描述

将本节(使用数据增强的卷积神经网络)子代码汇总后就可以编译出以上结果。

代码参考:deep learning with python


本文转载自: https://blog.csdn.net/ximu__l/article/details/125885974
版权归原作者 Dream_Bri 所有, 如有侵权,请联系我们删除。

“基于kaggle数据集的猫狗识别(超详细版本)”的评论:

还没有评论