[Feature] Add group_fisher pruning algorithm to prune a detection model #410
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
pppppM
reviewed
Jan 9, 2023
There was a problem hiding this comment.
@wilxy @LKJacky During the development of GroupFisher, some MMRazor's problems were exposed.
Problems
L1MutableChannelUnitinherits fromSequentialMutableChannelUnit, butL1MutableChannelUnitis not sequential.- Are
MutatorandChannelUnitnecessary ? I can doGroupFisherjust withGroupFisherAlgorithmandL1MutableChannelUnit. https://github.com/pppppM/mmrazor/tree/group_fisher - For pruning algorithms, the boundaries between the
Algorithm,ChannelMutator, andChannelUnitare not clear enough. Even though I am the developer of MMRazor, I can't find a reasonable way to divideGroupFisherintoAlgorithm,ChannelMutator, andChannelUnit
Suggestions
I think the above problems are difficult to solve completely without refactoring, especially 2 and 3. There are some suggestions about refactoring.
- For the boundaries between
MutatorandChannelUnit, I suggest that we can refer to NNI and concentrate the logic of pruning inMutatorinstead ofMutator&ChannelUnit.ChannelUnitonly serves as the most basic data structure.
In this way, when developers develop new pruning algorithms, they will know more clearly that they need to develop a newXXChannelMutatorbased onChannelUnit. - For the boundaries between
MutatorandAlgorithm,Mutatorshould contain all the basic APIs of a pruning algorithm, andAlgorithmcan implement the complete pruning algorithm through these APIs.
The logic of the algorithm should be implemented inMutatoras much as possible, andAlgorithmis just some logic for adapting to OpenMMLab so that MMRazor can be quickly used in other codebases.
Temporary Solution
Considering the reality, MMRazor needs to have some robust pruning algorithms as soon as possible, and the above suggestions cannot be realized in the short term. I suggest that the GroupFisher can be released in the form of a project(https://github.com/open-mmlab/mmocr/tree/1.x/projects). After the above problems are completely solved, it will be merged into MMRazor
|
@pppppM I provide three answers for the proposed problems above.
Now, we refactor group fisher by dividing it to four parts in the folder.
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Motivation
Add the pruning algorithm Group Fisher Pruning for Practical Network Compression as a demo to prune the detection model (like RetinaNet in this PR).
Modification