lmflow.optim.adamp
==================

.. py:module:: lmflow.optim.adamp


Classes
-------

.. autoapisummary::

   lmflow.optim.adamp.AdamP


Module Contents
---------------

.. py:class:: 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: :py:obj:`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: https://github.com/clovaai/AdamP















   ..
       !! processed by numpydoc !!

   .. py:method:: _channel_view(x)
      :staticmethod:



   .. py:method:: _layer_view(x)
      :staticmethod:



   .. py:method:: _cosine_similarity(x, y, eps, view_func)
      :staticmethod:



   .. py:method:: _projection(p, grad, perturb, delta, wd_ratio, eps)


   .. py:method:: step(closure=None)

      
      Performs a single optimization step.

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















      ..
          !! processed by numpydoc !!