Tensorflow for beginner

Classic/VPC 환경에서 이용 가능합니다.

더 많은 예제와 자세한 안내는 TensorFlow 튜토리얼 을 참조해 주십시오.

먼저 프로그램에 텐서플로 라이브러리를 임포트해 주십시오.

import tensorflow as tf

MNIST 데이터셋을 로드하여 준비해 주십시오. 샘플 값을 정수에서 부동소수로 변환합니다.

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

층을 차례대로 쌓아 tf.keras.Sequential 모델을 만들어 주십시오. 훈련에 사용할 옵티마이저(optimizer)와 손실 함수를 선택해 주십시오.

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10, activation='softmax')
])

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

모델을 훈련하고 평가합니다.

model.fit(x_train, y_train, epochs=5)

model.evaluate(x_test,  y_test, verbose=2)

'''
Train on 60000 samples
Epoch 1/5
WARNING:tensorflow:Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x7f2d11707048> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Num'
WARNING: Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x7f2d11707048> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Num'
60000/60000 [==============================] - 4s 68us/sample - loss: 0.2941 - accuracy: 0.9140
Epoch 2/5
60000/60000 [==============================] - 4s 62us/sample - loss: 0.1396 - accuracy: 0.9587
Epoch 3/5
60000/60000 [==============================] - 4s 62us/sample - loss: 0.1046 - accuracy: 0.9680
Epoch 4/5
60000/60000 [==============================] - 4s 62us/sample - loss: 0.0859 - accuracy: 0.9742
Epoch 5/5
60000/60000 [==============================] - 4s 62us/sample - loss: 0.0724 - accuracy: 0.9771
10000/1 - 0s - loss: 0.0345 - accuracy: 0.9788
[0.06729823819857557, 0.9788]
'''

훈련된 이미지 분류기는 이 데이터셋에서 약 98%의 정확도를 달성합니다. 더 자세한 내용은 TensorFlow 튜토리얼을 참조해 주십시오.