최적의 모델을 선택하기 위한 하이퍼파라미터 스윕 실행

fashion_mnist = tf.keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = 
fashion_mnist.load_data()
# Scale the pixel values of the images
train_images = train_images / 255.0
test_images = test_images / 255.0
# Select the hyperparameters you want to tune. This is specified like the 
following:
sweep_config = {
   'method': 'grid',
   'parameters': {
       'layers': {
           'values': [32, 64, 96, 128, 256]
       }
   }
}

sweep_id = wandb.sweep(sweep_config)

def train():
   # Initialize wandb with a sample project name
   wandb.init(project="hyperparameter-sweeps-partI")
   
   (X_train, y_train) = train_images, train_labels
   (X_test, y_test) = test_images, test_labels
   
   # Specify the hyperparameter to be tuned along with
   # an initial value
   configs = {
       'layers': 128
   }
   
   # Specify the other hyperparameters to the configuration
   config = wandb.config
   config.epochs = 5
   
   # Define the model
   model = tf.keras.Sequential([
       tf.keras.layers.Flatten(input_shape=(28, 28)),
       tf.keras.layers.Dense(wandb.config.layers, activation=tf.nn.relu),
       tf.keras.layers.Dense(10, activation=tf.nn.softmax)
   ])
   
   # Compile the model
   model.compile(optimizer='adam',
                 loss='sparse_categorical_crossentropy',
                 metrics=['accuracy'])
   
   # Train the model
   model.fit(X_train, y_train, epochs=config.epochs,
                 validation_data=(X_test, y_test),
            callbacks=[WandbCallback(data_type="image", labels=labels)])

wandb.agent(sweep_id, function=train)