Question

我正在尝试在polynomial decay框架中为learning rate decay复制Keras，在Tensorflow框架中实现如下。

def poly_decay(step, initial_value, decay_period_images_seen):
    """
    Decays a variable using a polynomial law.
    :param step: number of images seen by the network since the beginning of the training.
    :param initial_value: The initial value of the variable to decay..
    :param decay_period_images_seen: the decay period in terms of images seen by the network
    (1 epoch of 10 batches of 6 images each means that 1 epoch = 60 images seen).
    Thus this value must be a multiple of the number of batches
    :return: The decayed variable.
    """

    factor = 1.0 - (tf.cast(step, tf.float32) / float(decay_period_images_seen))
    lrate = initial_value * np.power(factor, 0.9)

    return lrate

Keras是否为global step提供了任何隐藏的参数（也许我不知道），还是Keras中有等效的global step？还是有其他方法可以在polynomial learning rate decay框架中实现Keras？

Answer 1

基本上，参数本身是optimisers的参数。

看看optimizers。

sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mean_squared_error', optimizer=sgd)

因此，在这里，您只需传递poly_decay()作为参数即可。

通常，我们使用time-based decay代替polynomial decay：

learning_rate = 0.1
decay_rate = learning_rate / epochs
momentum = 0.8
sgd = SGD(lr=learning_rate, momentum=momentum, decay=decay_rate, nesterov=False)

选中此blog以获得更多参考！

有没有办法在Keras框架中使用global_step？

1 个答案: