This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
Accumulative blockwise pruning #1170
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D18698077 |
Summary: Pull Request resolved: facebookresearch#1170 [sparsification] fix sparsity calculation error when use accumulate_mask option. Purpose: enable building up the mask accumulately by permanently removing s% from the unpruned weights in every X steps. Previously, the sparsity is calculated among ALL weights, which is wrong when we want to use accumulate_mask option. In this case, a param is masked to 0 permanently and future sparsification should perform only among the unmasked weights. ._masks: attribute stores the masks. In between the X steps, the ._masks are still applied to the weights but the masks are only updated in every X steps. When ._masks are updated, it prunes away s% of the weights that were previously "1" (kept) in ._masks. In addition, the mask is also applied to the gradient (so the param is effective removed from the architecture, not just set to zero) Reviewed By: arbabu123 Differential Revision: D18698077 fbshipit-source-id: 79ad67ddbd8eb55e3ef0eaec320d2b3cf4ed5239
psuzhanhy
force-pushed
the
export-D18698077
branch
from
e2fa0ab
to
cfd40dc
Compare
|
This pull request was exported from Phabricator. Differential Revision: D18698077 |
|
This pull request has been merged in 8f54218. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
[sparsification] fix sparsity calculation error when use accumulate_mask option. Purpose: enable building up the mask accumulately by permanently removing s% from the unpruned weights in every X steps.
Previously, the sparsity is calculated among ALL weights, which is wrong when we want to use accumulate_mask option. In this case, a param is masked to 0 permanently and future sparsification should perform only among the unmasked weights.
._masks: attribute stores the masks. In between the X steps, the ._masks are still applied to the weights but the masks are only updated in every X steps. When ._masks are updated, it prunes away s% of the weights that were previously "1" (kept) in ._masks. In addition, the mask is also applied to the gradient (so the param is effective removed from the architecture, not just set to zero)
Differential Revision: D18698077