간단한 MNIST 예제

simple_mnist.py

import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Flatten, Dense, Activation

def softmax(x):
  return np.exp(x) / np.sum(np.exp(x), axis=0)

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')

gray_scale = 255
x_train /= gray_scale
x_test /= gray_scale

model = Sequential([
  Flatten(input_shape=(28, 28)),
  Dense(256, activation='sigmoid'),
  Dense(128, activation='sigmoid'),
  Dense(10, activation='softmax')
])

model.compile(
  optimizer='adam',
  loss='sparse_categorical_crossentropy',
  metrics=['accuracy']
)

model.fit(
  x_train, y_train,
  epochs=15,
  batch_size=2000,
  validation_split=0.2
)

results = model.evaluate(
  x_test, y_test, verbose=0
)

print('Test loss: %.2f%%' % (results[0] * 100))
print('Test accuray: %.2f%%' % (results[1] * 100))