code test

수정 목록

import tensorflow as tf

from tensorflow.keras import layers, models

from tensorflow.keras.datasets import mnist

import matplotlib.pyplot as plt



# MNIST 데이터셋 로드

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



# 데이터 전처리

train_images = train_images.reshape((60000, 28 * 28)).astype('float32') / 255

test_images = test_images.reshape((10000, 28 * 28)).astype('float32') / 255



# 모델 생성

model = models.Sequential([

    layers.Dense(128, activation='relu', input_shape=(28 * 28,)),

    layers.Dropout(0.2),

    layers.Dense(10, activation='softmax')

])



model.compile(optimizer='adam',

              loss='sparse_categorical_crossentropy',

              metrics=['accuracy'])



# 모델 훈련

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



# 모델 평가

test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)

print(f'\nTest Accuracy: {test_acc * 100:.2f} %')



# 예측 수행

predictions = model.predict(test_images)

predicted_labels = [tf.argmax(p).numpy() for p in predictions]



# 이미지 표시

plt.figure(figsize=(9, 9))

for i in range(25):

    plt.subplot(5, 5, i + 1)

    plt.xticks([])

    plt.yticks([])

    plt.grid(False)

    plt.imshow(test_images[i].reshape(28, 28), cmap=plt.cm.binary)  # 이미지를 2D로 변환

    plt.xlabel(f"Real: {test_labels[i]} - Pred: {predicted_labels[i]}")



plt.show()