lmflow.optim.adamp

Classes

AdamP

Implements AdamP algorithm.

Module Contents

class lmflow.optim.adamp.AdamP(params, lr: float = 0.001, betas=(0.9, 0.999), eps: float = 1e-08, weight_decay: float = 0, delta: float = 0.1, wd_ratio: float = 0.1, nesterov: bool = False)

Bases: torch.optim.optimizer.Optimizer

Implements AdamP algorithm.

It has been proposed in Slowing Down the Weight Norm Increase in Momentum-based Optimizers https://arxiv.org/abs/2006.08217

Note:

Reference code: clovaai/AdamP

static _channel_view(x)

static _layer_view(x)

static _cosine_similarity(x, y, eps, view_func)

_projection(p, grad, perturb, delta, wd_ratio, eps)

step(closure=None)

Performs a single optimization step.

Arguments:

closure: A closure that reevaluates the model and returns the loss.