文章目录
一、实验准备
1.1 实验环境：
anaconda3 + python3.8 + Jupyter notebook
1.2 理解卷积神经网络CNN
这部分网上资源很多
1.3 下载安装TensorFlow 和Keras
1)命令行安装
pip install tensorflow
pip install keras
2)anaconda软件中安装
keras同理
二、开始实验
2.1 制作数据集
从kaggle网站下载数据集
1）图片分类：
import os, shutil
# The path to the directory where the original
# dataset was uncompressed
original_dataset_dir = 'D:\\Anaconda-Project\\CatAndDog\\kaggle_Dog&Cat\\kaggle_Dog&Cat\\train'
# The directory where we will
# store our smaller dataset
base_dir = 'D:\\Anaconda-Project\\CatAndDog\\kaggle_Dog&Cat\\kaggle_Dog&Cat\\find_cats_and_dogs'
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)
# Copy first 1000 cat images to 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)
# Copy next 500 cat images to 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)
# Copy next 500 cat images to 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)
# Copy first 1000 dog images to 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)
# Copy next 500 dog images to 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)
# Copy next 500 dog images to 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)
2）统计图片数量：
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)))
2.2 卷积神经网络CNN
2.2.1 网络模型搭建
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'))
model.summary()
2.2.2 图形生成器读取文件中数据
from keras import optimizers
model.compile(loss='binary_crossentropy',
optimizer=optimizers.RMSprop(lr=1e-4),
metrics=['acc'])
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')
2.2.3 开始训练
for data_batch, labels_batch in train_generator:
print('data batch shape:', data_batch.shape)
print('labels batch shape:', labels_batch.shape)
break
history = model.fit_generator(
train_generator,
steps_per_epoch=63,
epochs=30,
validation_data=validation_generator,
validation_steps=32)
2.4 保存训练模型
model.save('D:\\Anaconda-Project\\CatAndDog\\kaggle_Dog&Cat\\cats_and_dogs_small_1.h5')
2.2.5 在培训和验证数据上绘制模型的损失和准确性
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()
2.2.6 根据基准模型进行调整
1）使用数据扩充
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')
# 这是带有图像预处理实用程序的模块
from keras.preprocessing import image
fnames = [os.path.join(train_cats_dir, fname) for fname in os.listdir(train_cats_dir)]
# 我们选择一个图像来“增强”
img_path = fnames[3]
# 读取图像并调整其大小
img = image.load_img(img_path, target_size=(150, 150))
# 将其转换为具有形状的Numpy数组（150、150、3）
x = image.img_to_array(img)
# 把它改成（1150150，3）
x = x.reshape((1,) + x.shape)
# 下面的.flow（）命令生成一批随机转换的图像。
# 它将无限循环，所以我们需要在某个时刻“打破”循环！
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()
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'))
model.compile(loss='binary_crossentropy',
optimizer=optimizers.RMSprop(lr=1e-4),
metrics=['acc'])
2） 使用数据扩充和退出来训练（这一步运行时间非常久，建议关闭不必要的软件）
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,)
# 请注意，不应增加验证数据！
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=32,
# 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=32,
class_mode='binary')
history = model.fit_generator(
train_generator,
steps_per_epoch=63,
epochs=100,
validation_data=validation_generator,
validation_steps=50)
model.save('D:\\Study\\人工智能与机器学习\\project\\cats_and_dogs_small_2.h5')
3）在培训和验证数据上绘制模型的损失和准确性（可视化界面）
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()
三、使用VGG19实现猫狗分类
3.1 初始实列
from keras.applications.vgg19 import VGG19
conv_base = VGG19(weights = 'imagenet',include_top = False,input_shape=(150, 150, 3))
conv_base.summary()
3.2 将数据集传递给神经网络
import os
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
# 数据集分类后的目录
base_dir = 'D:\\Anaconda-Project\\CatAndDog\\kaggle_Dog&Cat\\kaggle_Dog&Cat\\find_cats_and_dogs'
train_dir = os.path.join(base_dir, 'train')
validation_dir = os.path.join(base_dir, 'validation')
test_dir = os.path.join(base_dir, 'test')
datagen = ImageDataGenerator(rescale = 1. / 255)
batch_size = 20
def extract_features(directory, sample_count):
features = np.zeros(shape = (sample_count, 4, 4, 512))
labels = np.zeros(shape = (sample_count))
generator = datagen.flow_from_directory(directory, target_size = (150, 150),
batch_size = batch_size,
class_mode = 'binary')
i = 0
for inputs_batch, labels_batch in generator:
#把图片输入VGG19卷积层，让它把图片信息抽取出来
features_batch = conv_base.predict(inputs_batch)
#feature_batch 是 4*4*512结构
features[i * batch_size : (i + 1)*batch_size] = features_batch
labels[i * batch_size : (i+1)*batch_size] = labels_batch
i += 1
if i * batch_size >= sample_count :
#for in 在generator上的循环是无止境的，因此我们必须主动break掉
break
return features , labels
#extract_features 返回数据格式为(samples, 4, 4, 512)
train_features, train_labels = extract_features(train_dir, 2000)
validation_features, validation_labels = extract_features(validation_dir, 1000)
test_features, test_labels = extract_features(test_dir, 1000)
3.3 将抽取的特征输入到自己的神经层中进行分类训练
train_features = np.reshape(train_features, (2000, 4 * 4 * 512))
validation_features = np.reshape(validation_features, (1000, 4 * 4 * 512))
test_features = np.reshape(test_features, (1000, 4 * 4* 512))
from keras import models
from keras import layers
from keras import optimizers
#构造我们自己的网络层对输出数据进行分类
model = models.Sequential()
model.add(layers.Dense(256, activation='relu', input_dim = 4 * 4 * 512))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(1, activation = 'sigmoid'))
model.compile(optimizer=optimizers.RMSprop(lr = 2e-5), loss = 'binary_crossentropy', metrics = ['acc'])
history = model.fit(train_features, train_labels, epochs = 30, batch_size = 20,
validation_data = (validation_features, validation_labels))
3.4 结果可视化
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 = 'Train_acc')
plt.plot(epochs, val_acc, 'b', label = 'Validation acc')
plt.title('Trainning 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()
四、资料引用
windows10（64位）Anaconda3+Python3.6搭建Tensorflow（cpu版本）及keras+用Jupyter notebook运行Kaggle狗猫数据集+提高模分类模型精度
【TensorFlow&Keras】入门猫狗数据集实验–理解卷积神经网络CNN
【TensorFlow&Keras】基于卷积神经网络CNN的猫狗分类
7万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
