hongdroid.ai 's blog

Learn and use ML

11 Oct 2018

고수준의 Keras API는 deep learning model들을 생성하고 훈련하기 위한 블록 제작을 제공합니다. 처음 시작하는 분을 위한 예제를 시작하고, TensorFlow Keras guide를 읽으세요.

  1. Basic classification
  2. Text classification
  3. Regression
  4. Overfitting and underfitting
  5. Save and load
import tensorflow  as tf
mnist = tf.keras.datasets.mnist

#Download MNIST data, require internet
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

#Configuration Model
model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512, activation=tf.nn.relu),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Dense(10, activation=tf.nn.softmax)])

#Compile Configuration Model
model.compile(optimizer = ‘Adam’,
              loss = ‘sparse_categorical_crossentropy’,
              metrics= [‘accuracy’])

#Run training
model.fit(x_train, y_train, epochs = 5)
#Run test data
model.evaluate(x_test, y_test)

Related Posts