Home [Tensorflow] DNN 모델
Post
Cancel

[Tensorflow] DNN 모델

1
2
3
4
5
6
7
8
9
10
11
model = tf.keras.Sequential([
    input_layers,
    layers.Dense(1024, activation='relu'),
    layers.BatchNormalization(),
    layers.Dense(512, activation='relu'),
    layers.BatchNormalization(),
    layers.Dropout(.2),
    layers.Dense(1, activation='sigmoid')
])
model.compile(optimizer, loss, metrics) 
model.fit(train_ds, val_ds, epochs, callbacks)
1
2
3
4
5
6
for units in hidden_units:
    inputs = layers.Dense(units)(inputs)
    inputs = layers.BatchNormalization()(inputs)
    inputs = layers.ReLU()(inputs)
    inputs = layers.Dropout(dropout)(inputs)
model = layers.Dense(1, activation='sigmoid')(inputs)
This post is licensed under CC BY 4.0 by the author.

[Pyspark] groupby, collect_set 그룹별로 컬럼의 값을 리스트로 변경

[Tensorflow] Wide&Deep, Deep&Cross 모델 생성