[케라스] 컨볼루션 신경망(CNN) 모델 학습을 위한 데이터 부풀리기

import numpy as np

# 랜덤시드 고정시키기
np.random.seed(3)

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D

# 데이터셋 불러오기
train_datagen = ImageDataGenerator(rescale= 1./255)
train_generator = train_datagen.flow_from_directory(
    'CNN-tutorial/train',
    target_size = (24, 24),
    batch_size = 3,
    class_mode = 'categorical'
)

test_datagen = ImageDataGenerator(rescale = 1./255)
test_generator = test_datagen.flow_from_directory(
    'CNN-tutorial/additional test',
    target_size = (24, 24),
    batch_size = 3,
    class_mode = 'categorical'
)

# 모델 구성하기
model = Sequential()
model.add(Conv2D(32, kernel_size = (3, 3), 
                 padding = 'valid', 
                 activation = 'relu',
                 input_shape = (24, 24, 3)))
model.add(Conv2D(64, kernel_size = (3, 3),
                 padding = 'valid',
                 activation = 'relu'))
model.add(MaxPooling2D(pool_size = (2, 2)))
model.add(Flatten())
model.add(Dense(128, activation = 'relu'))
model.add(Dense(3, activation = 'softmax'))

# 모델 학습과정 설정하기
model.compile(loss = 'categorical_crossentropy',
              optimizer = 'adam',
              metrics = ['accuracy'])

# 모델 학습하기
model.fit_generator(train_generator, 
                    steps_per_epoch = 15,
                    epochs = 200,
                    validation_data = test_generator,
                    validation_steps = 5)

# 모델 평가하기
print('--Evaluate--')

scores = model.evaluate_generator(test_generator,
                                  steps = 5)

print('%s : %.2f%%' %(model.metrics_names[1], scores[1]*100))

# 모델 예측하기
print('--Predict--')

output = model.predict_generator(test_generator,
                                 steps = 5)

np.set_printoptions(formatter = {'float' : lambda x : "{0:0.3f}".format(x)})

print(output)

keras.preprocessing.image.ImageDataGenerator(
    featurewise_center=False, 
    samplewise_center=False, 
    featurewise_std_normalization=False, 
    samplewise_std_normalization=False, 
    zca_whitening=False, 
    zca_epsilon=1e-06, 
    rotation_range=0, 
    width_shift_range=0.0, 
    height_shift_range=0.0, 
    brightness_range=None, 
    shear_range=0.0, 
    zoom_range=0.0, 
    channel_shift_range=0.0, 
    fill_mode='nearest', 
    cval=0.0, 
    horizontal_flip=False, 
    vertical_flip=False, 
    rescale=None, 
    preprocessing_function=None, 
    data_format='channels_last', 
    validation_split=0.0, 
    interpolation_order=1, 
    dtype='float32')

import numpy as np

# 랜덤시드 고정시키기
np.random.seed(5)

from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img

# 데이터셋 불러오기
data_aug_gen = ImageDataGenerator(rescale=1./255, 
                                  rotation_range=15,
                                  width_shift_range=0.1,
                                  height_shift_range=0.1,
                                  shear_range=0.5,
                                  zoom_range=[0.8, 2.0],
                                  horizontal_flip=True,
                                  vertical_flip=True,
                                  fill_mode='nearest')

img = load_img('CNN-tutorial/train/triangle/triangle001.png')
x = img_to_array(img)
x = x.reshape((1, ) + x.shape)

i = 0
# 이 구문은 무한 반복되기 때문에 원하는 반복횟수를 지정하여, 지정된 반복횟수가 되면 빠져나오도록 세팅해주어야 합니다.
for batch in data_aug_gen.flow(x, batch_size = 1, save_to_dir = 'CNN-tutorial/dummy', save_prefix = 'triange', save_format = 'png'):
    i += 1
    if i >= 100:
        break

import numpy as np

# 랜덤시드 고정시키기
np.random.seed(3)

from keras.preprocessing.image import ImageDataGenerator

# 데이터셋 불러오기 : 이 부분이 수정되었습니다.
train_datagen = ImageDataGenerator(rescale=1./255, 
                                   rotation_range=10,
                                   width_shift_range=0.2,
                                   height_shift_range=0.2,
                                   shear_range=0.7,
                                   zoom_range=[0.9, 2.2],
                                   horizontal_flip=True,
                                   vertical_flip=True,
                                   fill_mode='nearest')

train_generator = train_datagen.flow_from_directory(
        'CNN-tutorial/train',
        target_size=(24, 24),
        batch_size=3,
        class_mode='categorical')

test_datagen = ImageDataGenerator(rescale=1./255)

test_generator = test_datagen.flow_from_directory(
        'CNN-tutorial/test',
        target_size=(24, 24),    
        batch_size=3,
        class_mode='categorical')

from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D

from keras.layers import Dropout

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=(24,24,3)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(3, activation='softmax'))

# 모델 엮기
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

# 모델 학습시키기
model.fit_generator(
        train_generator,
        steps_per_epoch=15 * 50,
        epochs=200,
        validation_data=test_generator,
        validation_steps=5)

# 모델 평가하기
print("-- Evaluate --")

scores = model.evaluate_generator(
            test_generator, 
            steps = 5)

print("%s: %.2f%%" %(model.metrics_names[1], scores[1]*100))

# 모델 예측하기
print("-- Predict --")

output = model.predict_generator(
            test_generator, 
            steps = 5)

np.set_printoptions(formatter={'float': lambda x: "{0:0.3f}".format(x)})

print(output)