keras 分层学习率

使用tensorflow-addons，第一层学习率设置为1e-4，后面3层为1e-2
import tensorflow_addons as tfa

    >>> model = tf.keras.Sequential([
    ...     tf.keras.Input(shape=(4,)),
    ...     tf.keras.layers.Dense(8),
    ...     tf.keras.layers.Dense(16),
    ...     tf.keras.layers.Dense(32),
    ... ])
    >>> optimizers = [
    ...     tf.keras.optimizers.Adam(learning_rate=1e-4),
    ...     tf.keras.optimizers.Adam(learning_rate=1e-2)
    ... ]
    >>> optimizers_and_layers = [(optimizers[0], model.layers[0]), (optimizers[1], model.layers[1:])]
    >>> optimizer = tfa.optimizers.MultiOptimizer(optimizers_and_layers)
    >>> model.compile(optimizer=optimizer, loss="mse")

详细信息可以去看tensorflow-addons文档或者源码