Adam¶
- class Adam(params, lr, betas=(0.9, 0.999), eps=1e-08, weight_decay=0.0)[源代码]¶
实现 “Adam: A Method for Stochastic Optimization” 中提出的Adam算法。
- 参数
params (Union[Iterable[Parameter], dict]) – 可迭代对象，可以是一组待优化的参数，或定义几组参数的dict类型。
lr (float) – learning rate.
betas (Tuple[float, float]) – coefficients used for computing running averages of gradient and its square. Default: (0.9, 0.999).
eps (float) – term added to the denominator to improve numerical stability. Default: 1e-8.
weight_decay (float) – weight decay (L2 penalty). Default: 0.
- 返回
An instance of the Adam optimizer.