:orphan:

:py:mod:`neural_compressor.compression.pruner.dsnot`
====================================================

.. py:module:: neural_compressor.compression.pruner.dsnot


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


Functions
~~~~~~~~~

.. autoapisummary::

   neural_compressor.compression.pruner.dsnot.return_reorder_indice
   neural_compressor.compression.pruner.dsnot.DSnoT



.. py:function:: return_reorder_indice(input_tensor)

   For instance:
   [[1., -2., 3.],
   [-2, 2., -4],
   [5., 6., -7],
   [-6, -7, -4]]
   return indices of
   [[-2.,  3.,  1.],
   [-2., -4.,  2.],
   [-7.,  6.,  5.],
   [-6., -7., -4.]]
   Description: The relative order in the positive number remains unchanged,
   and the relative order in the negative number is flipped.


.. py:function:: DSnoT(initial_metric, sparsity_ratio, wrapped_layer, prune_n=0, prune_m=0, pow_of_var_regrowing=1.0, max_cycle_time=100, without_same_sign=True, update_threshold=0.1)

   :param pow_of_var_regrowing: The power of variance, float type, default=1.
   :param max_cycle_time: Max cycle time.
   :param without_same_sign:
   :param without same sign:
   :param bool:
   :param default True.:
   :param update_threshold: update threshold, float, default 0.1.

   See the original paper: https://arxiv.org/pdf/2310.08915.pdf