텐서플로 - Tensorflow 2버전 : 딥러닝(with Keras)

필요 모듈 설정

import tensorflow as tf
import keras
import numpy as np
from matplotlib import pyplot as plt
from keras.datasets import mnist
from keras import models, layers
from keras.utils import to_categorical

mnist 데이터 불러오기

(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

mnist 데이터 확인하기

print(train_images.shape)
print(train_labels)
print(test_images.shape)
print(test_labels)

예측 확인용 체크 이미지 저장 하기

check_image = test_images[24]

Keras 모델 만들기

model = models.Sequential()
model.add(layers.Dense(512, activation='relu', input_shape=(28*28, )))
model.add(layers.Dense(256, activation='relu'))
model.add(layers.Dense(128, activation='relu'))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))

만든 모델 구조 확인하기

from keras.utils import plot_model
plot_model(model, show_shapes=True)

모델 컴파일 하기

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

이미지 모양 바꿔주기

train_images = train_images.reshape((60000, 28*28))
train_images = train_images.astype('float32')/255
test_images = test_images.reshape((10000, 28*28))
test_images = test_images.astype('float32')/255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

모델 학습하기

model.fit(train_images, train_labels, epochs=5, batch_size=128)

모델 Cost 및 loss 값 확인하기

test_loss, test_acc = model.evaluate(test_images, test_labels)
print(test_loss, test_acc)

예측 확인용 체크 이미지 확인하기

plt.imshow(check_image, cmap = plt.cm.binary)

예측 확인용 체크 이미지 모델에 넣고 예측하기

checking_img = check_image.reshape((1, 28*28))
output = model.predict(checking_img)
print(np.argmax(output))