TensorFlow 2.x버전으로 MNIST 실습하기

import tensorflow as tf
import numpy as np
from tensorflow.keras.datasets import mnist

(x_train, t_train), (x_test, t_test) = mnist.load_data()

print('\n train shape =', x_train.shape, ', train label shape = ', t_train.shape)
print(' test shape =', x_test.shape, ', test label shape=', t_test.shape)

print('\n train label = ', t_train) # 학습 데이터 
print(' test label =', t_test)      # 테스트 데이터

print(x_train[0])

import matplotlib.pyplot as plt

# 25개 이미지 출력
plt.figure(figsize=(6,6))

for index in range(25): # 25개 이미지 출력
    plt.subplot( 5, 5, index + 1)   # 5행 5열
    plt.imshow(x_train[index], cmap='gray')
    plt.axis('off')
    # plt.title(str(t_train[index]))

plt.show()

# 학습 데이터 / 테스트 데이터 정규화
x_train = (x_train - 0.0) / (255.0 - 0.0)
x_test = (x_test - 0.0) / (255.0 - 0.0)

# 정답 데이터 원핫 인코딩
t_train = tf.keras.utils.to_categorical(t_train, num_classes=10)
t_test = tf.keras.utils.to_categorical(t_test, num_classes=10)

print(x_train[0])

model = tf.keras.Sequential()
model.add(tf.keras.layers.Flatten(input_shape=(28,28)))
model.add(tf.keras.layers.Dense(100, activation='relu'))
model.add(tf.keras.layers.Dense(10, activation='softmax'))

model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-3), loss='categorical_crossentropy', metrics=['accuracy'])

model.summary()

 

hist = model.fit(x_train, t_train, epochs=30, validation_split=0.3)

model.evaluate(x_test, t_test)

plt.title('Loss')
plt.xlabel('epochs')
plt.ylabel('loss')
plt.grid()

plt.plot(hist.history['loss'], label='train loss')
plt.plot(hist.history['val_loss'], label='validation loss')

plt.legend(loc='best')

plt.show()

 

plt.title('Accuracy')
plt.xlabel('epochs')
plt.ylabel('accuracy')
plt.grid()

plt.plot(hist.history['accuracy'], label='train accuracy')
plt.plot(hist.history['val_accuracy'], label='validation accuracy')

plt.legend(loc='best')

plt.show()