ABOUT ME

-

Today
-
Yesterday
-
Total
-
  • Keras Cat Dog 분류 - 8. 딥러닝 시작하기 - 과대적합
    주제를 딱히 정하기 싫을때 2019. 6. 13. 23:20

    설치 부터 실제 분류까지 keras로

     Cat과 Dog 데이터 셋으로 끝까지 해보기 

     

    2019/06/13 - [주제를 딱히 정하기 싫을때] - Keras Cat Dog 분류 - 7. 딥러닝 시작하기 - 텐션보드 사용하기

     

    Keras Cat Dog 분류 - 7. 딥러닝 시작하기 - 텐션보드 사용하기

    " 설치 부터 실제 분류까지 keras로 Cat과 Dog 데이터 셋으로 끝까지 해보기 2019/06/13 - [주제를 딱히 정하기 싫을때] - Keras Cat Dog 분류 - 6. 딥러닝 시작하기 - 모델 구성 Keras Cat Dog 분류 - 6. 딥러닝..

    redapply.tistory.com

    11 과대적합 

    • 설명은 챕터 6을 참고

    • MaxPolling2D 

    • Dropout 적용

    def cnn_api2(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.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.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.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
    • 저장할 모델을 식별하기위해 프로젝트 name을 바꿔줍니다.

    project_name = 'dog_cat_CNN_api2_model'

     

    • 새롭게 적용될 모델도 바꿔줍니다

    newType_model = cnn_api2(input_shape)

     

     

    • 전체 코드는 다음과 같습니다.

    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_api2_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)
    
    #MaxPolling2d,Dropout 적용
    
    def cnn_api2(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.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.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.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)
    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_api2(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()

     

     

     

     

    • 이전 보다 정확도는 약간 올라갔지만 과대적합이 남아있습니다.

    • 다음은 레이어 층을 늘려 보겠습니다.

     

     

     

    변경된 부분

    • 모델 레이어 추가

    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

     

    • 저장할 모델을 식별하기위해 프로젝트 name을 바꿔줍니다.

    project_name = 'dog_cat_CNN_api3_model'

     

    • 새롭게 적용될 모델도 바꿔줍니다

    newType_model = cnn_api3(input_shape)

     

     

    변경된 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_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)
    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()

     

     

     

     

     

    음. 그렇게 특별히 나아 보이지를 않습니다.

    오히려 정확도가 더 떨어졌습니다.

    그리고 36에포크 만에 훈련이 중단 되었군요

     

    다음 절에서 데이터 증식을 통해 과대적합을 잡아 보겠습니다.

     

    Keras Cat Dog 분류 - 딥러닝 시작하기 .ipynb
    0.15MB

     

     

    댓글

Designed by Tistory.