이미지 데이터 처리를 위한 CNN 완벽 가이드 - CNN 모델을 이용한 Cats & Dogs 분류 분석

import tensorflow as tf
from tensorflow import keras

import os
import matplotlib.pyplot as plt

url = 'https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip'
path_to_zip = keras.utils.get_file(fname='cats_and_dogs_filtered.zip',
									origin=url, extract=True,
									cache_dir='/content')
                                    
train_dir = '/content/datasets/cats_and_dogs_filtered/train'
validation_dir = '/content/datasets/cats_and_dogs_filtered/validation'

from tensorflow.keras.preprocessing.image import ImageDataGenerator

# 모든 이미지를 1/255로 스케일을 조정합니다
train_datagen = ImageDataGenerator(rescale=1./255)
validation_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
	directory=train_dir,
    target_size=(150, 150),
    batch_size=20,
    shuffle=True,
    class_mode='binary'
)

validation_generator = validation_datagen.flow_from_directory(
	directory=validation_dir,
    target_size=(150, 150),
    batch_size=20,
    class_mode='binary'
)

# CNN 모델 디자인 및 학습 정보 설정
from tensorflow.keras import models, layers

model = models.Sequential()
model.add(layers.Conv2D(filters=32, kernel_size=(3, 3),
						activation='relu',
                        input_shape=(150, 150, 3)))
model.add(layers.MaxPool2D(pool_size=(2, 2)))
model.add(layers.Conv2D(filters=64, kernel_size=(3, 3),
						activation='relu'))
model.add(layers.MaxPool2D(pool_size=(2, 2)))
model.add(layers.Conv2D(filters=128, kernel_size=(3, 3),
						activation='relu'))
model.add(layers.MaxPool2D(pool_size=(2, 2)))
model.add(layers.Conv2D(filters=128, kernel_size=(3, 3),
						activation='relu'))
model.add(layers.MaxPool2D(pool_size=(2, 2)))

model.add(layers.Flatten())

model.add(layers.Dense(units=512, activation='relu'))
model.add(layers.Dropout(0.3))
model.add(layers.Dense(units=1, activation='sigmoid'))

model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])

# 모델에 데이터 generator 연결 후 학습
history = model.fit(train_generator,
					steps_per_epoch=len(train_generator),
					epochs=20,
                    validation_data=validation_generator,
                    validation_steps=len(validation_generator))

# 모델의 학습과정 시각화
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
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.show()

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()

# 테스트 데이터셋을 통한 모델의 성능 평가
val_loss, val_accuracy = model.evaluate(validation_generator)