텐서플로우 v2

tensorflow : https://www.tensorflow.org/?hl=ko

tensorflow 홈페이지 스타트 코드

https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/quickstart/advanced.ipynb?hl=ko

 

 

데이터 처리

tf.data.Dataset.from_tensor_slices

train_ds = tf.data.Dataset.from_tensor_slices((x_train, y_train)).shuffle(10000).batch(32)
test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)

# dataset = tf.data.Dataset.from_tensor_slices((input_tensor_train, target_tensor_train)).shuffle(BUFFER_SIZE)
# dataset = dataset.batch(BATCH_SIZE, drop_remainder=True)

데이터셋을 배치로

example_input_batch, example_target_batch = next(iter(dataset))

 

모델 구현

class makemodel (model):

  def __init__(self):    #구조 만들기

     super(makemodel, self).__init__()

     self.쓰는 모델 레이어~~ 

  def call(self, x):     #만든 구조에 데이터 넣기

     x = 위에 레이어( x )

     ~~~

     return 마지막 출력

 

model = makemodel()

 

이 구조가 기본인듯

class MyModel(Model):
  def __init__(self):
    super(MyModel, self).__init__()
    self.conv1 = Conv2D(32, 3, activation='relu')
    self.flatten = Flatten()
    self.d1 = Dense(128, activation='relu')
    self.d2 = Dense(10)

  def call(self, x):
    x = self.conv1(x)
    x = self.flatten(x)
    x = self.d1(x)
    return self.d2(x)

# Create an instance of the model
model = MyModel()

loss랑 optimizer

(tf.keras.~~~에 보통 함수 들어있음)

loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)

optimizer = tf.keras.optimizers.Adam()

Accuracy

(또한 tf.keras.~~~)

train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')

test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')

학습

(배치가 있다면 배치 안에 테이프코드가 들어간다.)
with tf.GradientTape() as tape():

   prediction, loss등 모델에 맞도록 필요한 코드 구성

gradients = tape.gradient(loss, model.variables)

optimizer.apply_gradients( zip(gradients, model.variables) )

@tf.function
def train_step(images, labels):
  with tf.GradientTape() as tape:
    # training=True is only needed if there are layers with different
    # behavior during training versus inference (e.g. Dropout).
    predictions = model(images, training=True)
    loss = loss_object(labels, predictions)
  gradients = tape.gradient(loss, model.trainable_variables)
  optimizer.apply_gradients(zip(gradients, model.trainable_variables))

  train_loss(loss)
  train_accuracy(labels, predictions)

EPOCHS = 5

for epoch in range(EPOCHS):
  # Reset the metrics at the start of the next epoch
  train_loss.reset_states()
  train_accuracy.reset_states()
  test_loss.reset_states()
  test_accuracy.reset_states()

  for images, labels in train_ds:
    train_step(images, labels)

  for test_images, test_labels in test_ds:
    test_step(test_images, test_labels)

  print(
    f'Epoch {epoch + 1}, '
    f'Loss: {train_loss.result()}, '
    f'Accuracy: {train_accuracy.result() * 100}, '
    f'Test Loss: {test_loss.result()}, '
    f'Test Accuracy: {test_accuracy.result() * 100}'
  )