tf.train.AdamOptimizer 优化器

Posted 2022-04-22 smallredness

adaptive moment estimation(自适应矩估计)

tf.train.AdamOptimizer(
    learning_rate=0.001,
    beta1=0.9,
    beta2=0.999,
    epsilon=1e-08,
    use_locking=False,
    name='Adam'
)

参数：
learning_rate: （学习率）张量或者浮点数
beta1:? 浮点数或者常量张量 ，表示 The exponential decay rate for the 1st moment estimates.
beta2: ?浮点数或者常量张量 ，表示?The exponential decay rate for the 2nd moment estimates.
epsilon: A small constant for numerical stability. This epsilon is "epsilon hat" in the Kingma and Ba paper (in the formula just before Section 2.1), not the epsilon in         Algorithm 1 of the paper.
use_locking: 为True时锁定更新
name: ?梯度下降名称，默认为 "Adam"