Keras Cat Dog 분류 - 9. 딥러닝 시작하기 - 과대적합2

설치 부터 실제 분류까지 keras로

 Cat과 Dog 데이터 셋으로 끝까지 해보기 

 

2019/06/13 - [주제를 딱히 정하기 싫을때] - Keras Cat Dog 분류 - 8. 딥러닝 시작하기 - 과대적합

Keras Cat Dog 분류 - 8. 딥러닝 시작하기 - 과대적합

 

 

12 - ImageDataGenerator

• 훈련 데이터를 증식을 시도 한다

• 검증데이터, 테스트 데이터는 절대 증식 금지!!

 

• 변경 데이터

#프로젝트 이름

project_name = 'dog_cat_CNN_api3_datagen_model'

 

#훈련데이터 데이터 증식

train_datagen = ImageDataGenerator(

    rescale = 1./255,

    rotation_range=40,

    width_shift_range=0.2,

    height_shift_range=0.2,

    shear_range=0.2,

    horizontal_flip=True,

    fill_mode='nearest')

 

 

• 전체 코드

from datetime import datetime

import os

import keras



save_dir = './my_log'



if not os.path.isdir(save_dir):

    os.makedirs(save_dir)



    

project_name = 'dog_cat_CNN_api3_datagen_model'



def save_file():

    time = datetime.today()

    yy = time.year

    mon = time.month

    dd = time.day

    hh = time.hour

    mm = time.minute

    sec = time.second

    time_name = str(yy) +  str(mon) + str(dd) + str(hh) + str(mm) +  str(sec) +'_my_' + project_name + '_model.h5'

    file_name = os.path.join(save_dir,time_name)

    return file_name



callbacks = [

    

    keras.callbacks.TensorBoard(

    log_dir = save_dir,

    write_graph=True,

    write_images=True

    ),

    

    keras.callbacks.EarlyStopping(

    monitor = 'val_acc',

        patience=10,

    ),

    keras.callbacks.ModelCheckpoint(

    filepath= save_file(),

    monitor = 'val_loss',

    save_best_only = True,

    )

]





from keras import Input

from keras import layers ,models, losses ,optimizers



batch_size = 256

no_classes = 1

epochs = 50

image_height, image_width = 150,150

input_shape = (image_height,image_width,3)



def cnn_api3(input_shape):

    

    input_tensor =Input(input_shape, name = "input")

    

    x = layers.Conv2D(filters= 32 ,kernel_size= (3,3) , padding= "same", activation='relu')(input_tensor)

    x = layers.Conv2D(filters= 32 ,kernel_size= (3,3) , padding= "same", activation='relu')(x)

    x = layers.MaxPooling2D(pool_size=(2,2))(x)

    x = layers.Dropout(rate=0.25)(x)

    

    x = layers.Conv2D(filters= 64 ,kernel_size= (3,3) , padding= "same", activation='relu')(x)

    x = layers.Conv2D(filters= 64 ,kernel_size= (3,3) , padding= "same", activation='relu')(x)

    x = layers.MaxPooling2D(pool_size=(2,2))(x)

    x = layers.Dropout(rate=0.25)(x)

    

    x = layers.Conv2D(filters= 128 ,kernel_size= (3,3) , padding= "same", activation='relu')(x)

    x = layers.Conv2D(filters= 128 ,kernel_size= (3,3) , padding= "same", activation='relu')(x)

    x = layers.MaxPooling2D(pool_size= (2,2))(x)

    x = layers.Dropout(rate= 0.25)(x)

    

    x = layers.Flatten()(x)

    x = layers.Dense(units= 1024 , activation='relu')(x)

    x = layers.Dropout(rate= 0.25)(x)

    

    output_tensor = layers.Dense(units= no_classes, activation= 'sigmoid', name= "output")(x)

    

    model = models.Model([input_tensor],[output_tensor])

    

    model.compile(loss = losses.binary_crossentropy, optimizer= optimizers.RMSprop(lr=0.0001), metrics=['acc'])

    return model





from keras.preprocessing.image import ImageDataGenerator

from PIL import Image



train_datagen = ImageDataGenerator(

    rescale = 1./255,

    rotation_range=40,

    width_shift_range=0.2,

    height_shift_range=0.2,

    shear_range=0.2,

    horizontal_flip=True,

    fill_mode='nearest')





val_datagen = ImageDataGenerator(rescale = 1./255) # 검증데이터 스케일 조정만 합니다.



train_generator = train_datagen.flow_from_directory(

    os.path.join(copy_train_path,"train"),

    target_size = (image_height, image_height),

    batch_size = batch_size,

    class_mode = "binary"

    )

validation_generator = val_datagen.flow_from_directory(

    os.path.join(copy_train_path,"validation"),

    target_size = (image_height, image_height),

    batch_size = batch_size,

    class_mode = "binary"

    )





newType_model = cnn_api3(input_shape)

hist = newType_model.fit_generator(train_generator, steps_per_epoch = 20000//batch_size, epochs= epochs,

                                  validation_data = validation_generator, validation_steps = 5000//batch_size,

                                  callbacks = callbacks)





import matplotlib.pyplot as plt

train_acc = hist.history['acc']

val_acc = hist.history['val_acc']



train_loss = hist.history['loss']

val_loss = hist.history['val_loss']

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



plt.plot(epochs,train_acc,'bo',label='Training acc')

plt.plot(epochs,val_acc,'r',label='Val acc')

plt.title('Training and Val accuracy')

plt.legend()



plt.figure()

plt.plot(epochs,train_loss,'bo',label='Training loss')

plt.plot(epochs,val_loss,'r',label='Val loss')

plt.title('Training and Val loss')

plt.legend()



plt.show()

 

 

 

 

데이터 증식 덕분에 과대 적합은 많이 줄여지만

정확성은 아직 부족합니다.

더 나은 모델을 사용해 보겠습니다.

 

 

1. 이미 구성된 모델 가져오기

•  xception 모델

• 이미 가중치가 적용된 모델을 사용합니다.

• include_top = False() 마지막  Dense레이어를 포함 여부를 물어봅니다.

• 여기에선 출력이 한개가 필요하므로 Dense부분만 모델에 추가합니다.

 

• 변경된 모델(Xception)

 

from keras.applications import Xception

def xception_Model(input_shape):

    xceptionmodel = Xception(input_shape=input_shape, weights='imagenet', include_top=False)



    model = models.Sequential()

    model.add(xceptionmodel)

    model.add(layers.Flatten())

    model.add(layers.Dense(units=256, activation="relu"))

    model.add(layers.Dense(units=no_classes, activation="sigmoid"))



    model.compile(loss=losses.binary_crossentropy, optimizer=optimizers.RMSprop(), metrics=['acc'])
    return model

    

 

• 변경된 내용

project_name = 'dog_cat_xception_datagen_model'

newType_model = xception_Model(input_shape)

 

 

• 전체코드

from datetime import datetime

import os

import keras



save_dir = './my_log'



if not os.path.isdir(save_dir):

    os.makedirs(save_dir)



    

project_name = 'dog_cat_xception_datagen_model'



def save_file():

    time = datetime.today()

    yy = time.year

    mon = time.month

    dd = time.day

    hh = time.hour

    mm = time.minute

    sec = time.second

    time_name = str(yy) +  str(mon) + str(dd) + str(hh) + str(mm) +  str(sec) +'_my_' + project_name + '_model.h5'

    file_name = os.path.join(save_dir,time_name)

    return file_name



callbacks = [

    

    keras.callbacks.TensorBoard(

    log_dir = save_dir,

    write_graph=True,

    write_images=True

    ),

    

    keras.callbacks.EarlyStopping(

    monitor = 'val_acc',

        patience=3,

    ),

    keras.callbacks.ModelCheckpoint(

    filepath= save_file(),

    monitor = 'val_loss',

    save_best_only = True,

    )

]





from keras import Input

from keras import layers ,models, losses ,optimizers



batch_size = 32

no_classes = 1

epochs = 10

image_height, image_width = 150,150

input_shape = (image_height,image_width,3)



from keras.applications import Xception

def xception_Model(input_shape):

    xceptionmodel = Xception(input_shape=input_shape, weights='imagenet', include_top=False)



    model = models.Sequential()

    model.add(xceptionmodel)

    model.add(layers.Flatten())

    model.add(layers.Dense(units=256, activation="relu"))

    model.add(layers.Dense(units=no_classes, activation="sigmoid"))



    model.compile(loss=losses.binary_crossentropy, optimizer=optimizers.RMSprop(), metrics=['acc'])

    return model





from keras.preprocessing.image import ImageDataGenerator

from PIL import Image



train_datagen = ImageDataGenerator(

    rescale = 1./255,

    rotation_range=40,

    width_shift_range=0.2,

    height_shift_range=0.2,

    shear_range=0.2,

    horizontal_flip=True,

    fill_mode='nearest')





val_datagen = ImageDataGenerator(rescale = 1./255) # 검증데이터 스케일 조정만 합니다.



train_generator = train_datagen.flow_from_directory(

    os.path.join(copy_train_path,"train"),

    target_size = (image_height, image_height),

    batch_size = batch_size,

    class_mode = "binary"

    )

validation_generator = val_datagen.flow_from_directory(

    os.path.join(copy_train_path,"validation"),

    target_size = (image_height, image_height),

    batch_size = batch_size,

    class_mode = "binary"

    )







newType_model = xception_Model(input_shape)

hist = newType_model.fit_generator(train_generator, steps_per_epoch = 20000//batch_size, epochs= epochs,

                                  validation_data = validation_generator, validation_steps = 5000//batch_size,

                                  callbacks = callbacks)





import matplotlib.pyplot as plt

train_acc = hist.history['acc']

val_acc = hist.history['val_acc']



train_loss = hist.history['loss']

val_loss = hist.history['val_loss']

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



plt.plot(epochs,train_acc,'bo',label='Training acc')

plt.plot(epochs,val_acc,'r',label='Val acc')

plt.title('Training and Val accuracy')

plt.legend()



plt.figure()

plt.plot(epochs,train_loss,'bo',label='Training loss')

plt.plot(epochs,val_loss,'r',label='Val loss')

plt.title('Training and Val loss')

plt.legend()



plt.show()

 

 

 

 

 

 

 

와우 !! 

정확도가 95%에 달하는 군요

이전 모델 보다 훨씬 안정적이고 정확성이 높습니다.

이 모델을 사용하겠습니다.