Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Mkaglins/pruning masks applying #985

Closed
wants to merge 12 commits into from
Closed

Mkaglins/pruning masks applying #985

wants to merge 12 commits into from

Commits on Sep 28, 2021

  1. POC of new mask applying algo

    @mkaglins
    mkaglins committed Sep 28, 2021
    Configuration menu
    Copy the full SHA
    230ba7c View commit details
    Browse the repository at this point in the history

Commits on Oct 17, 2021

  1. Fix tests and change weights updating mechanism

    @mkaglins
    mkaglins committed Oct 17, 2021
    Configuration menu
    Copy the full SHA
    1e7c220 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'develop' into mkaglins/pruning_masks_applying

    @mkaglins
    mkaglins committed Oct 17, 2021
    Configuration menu
    Copy the full SHA
    ae887b4 View commit details
    Browse the repository at this point in the history

  3. Fix mask type in apply_mask

    @mkaglins
    mkaglins committed Oct 17, 2021
    Configuration menu
    Copy the full SHA
    d235816 View commit details
    Browse the repository at this point in the history

  4. Small refactoring

    @mkaglins
    mkaglins committed Oct 17, 2021
    Configuration menu
    Copy the full SHA
    6e386d1 View commit details
    Browse the repository at this point in the history

  5. Fix pylint

    @mkaglins
    mkaglins committed Oct 17, 2021
    Configuration menu
    Copy the full SHA
    4effb86 View commit details
    Browse the repository at this point in the history

Commits on Oct 18, 2021

  1. UpdateWeightAndBias was refactored to use UpdateParameterList

    @mkaglins
    mkaglins committed Oct 18, 2021
    Configuration menu
    Copy the full SHA
    64b35e0 View commit details
    Browse the repository at this point in the history

  2. GroupNorm added

    @mkaglins
    mkaglins committed Oct 18, 2021
    Configuration menu
    Copy the full SHA
    30da9d8 View commit details
    Browse the repository at this point in the history

Commits on Oct 19, 2021

  1. Removed zero_grad param and functionality, restoring weights in LeGR … 

    …also deleted as not needed anymore
    @mkaglins
    mkaglins committed Oct 19, 2021
    Configuration menu
    Copy the full SHA
    dfd8b53 View commit details
    Browse the repository at this point in the history

  2. Update nncf/torch/module_operations.py with docs 

    Co-authored-by: Daniil Lyakhov <daniil.lyakhov@intel.com>
    @mkaglins @daniil-lyakhov
    mkaglins and daniil-lyakhov committed Oct 19, 2021
    Configuration menu
    Copy the full SHA
    351ccb8 View commit details
    Browse the repository at this point in the history

  3. Update nncf/torch/module_operations.py 

    Co-authored-by: Daniil Lyakhov <daniil.lyakhov@intel.com>
    @mkaglins @daniil-lyakhov
    mkaglins and daniil-lyakhov committed Oct 19, 2021
    Configuration menu
    Copy the full SHA
    0a4cab4 View commit details
    Browse the repository at this point in the history

Commits on Oct 21, 2021

  1. Fixed a lot of reerence graphs without BN + refactor

    @mkaglins
    mkaglins committed Oct 21, 2021
    Configuration menu
    Copy the full SHA
    e508faf View commit details
    Browse the repository at this point in the history