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.

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

[BUG]Fix bugs in pruner #126

Merged
merged 8 commits into from
Apr 1, 2022

Conversation

HIT-cwh
Copy link
Collaborator

@HIT-cwh HIT-cwh commented Mar 27, 2022

Motivation

Fix bugs in StructurePruner.

  1. Fix the bug of grouping errors caused by shared modules
  2. Support trace Dilated Conv2d
  3. Fix the bug that the modules whose requires_grad is False can not be traced
  4. Modify the forward method in a correct way.

@codecov
Copy link

codecov bot commented Mar 27, 2022

Codecov Report

Merging #126 (55d33b0) into dev_v0.3.0 (f5ee768) will increase coverage by 0.50%.
The diff coverage is 94.28%.

@@              Coverage Diff               @@
##           dev_v0.3.0     #126      +/-   ##
==============================================
+ Coverage       65.28%   65.78%   +0.50%     
==============================================
  Files              91       91              
  Lines            3272     3300      +28     
  Branches          600      606       +6     
==============================================
+ Hits             2136     2171      +35     
+ Misses           1036     1030       -6     
+ Partials          100       99       -1     
Flag Coverage Δ
unittests 65.75% <94.28%> (+0.50%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
mmrazor/models/pruners/structure_pruning.py 89.35% <94.28%> (+0.96%) ⬆️
mmrazor/core/distributed_wrapper.py 42.10% <0.00%> (+4.96%) ⬆️
mmrazor/models/architectures/base.py 100.00% <0.00%> (+13.33%) ⬆️
mmrazor/models/architectures/mmdet.py 100.00% <0.00%> (+36.36%) ⬆️

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update f5ee768...55d33b0. Read the comment docs.

@HIT-cwh HIT-cwh changed the title [BUG]Fix bugs in pruner when pruning models with shared modules [BUG]Fix bugs in pruner when pruning models with shared modules or dilation conv2d Mar 27, 2022
@HIT-cwh HIT-cwh mentioned this pull request Mar 27, 2022
@HIT-cwh HIT-cwh changed the title [BUG]Fix bugs in pruner when pruning models with shared modules or dilation conv2d [BUG]Fix bugs in pruner Mar 31, 2022
@pppppM pppppM linked an issue Apr 1, 2022 that may be closed by this pull request
mmrazor/models/pruners/structure_pruning.py Show resolved Hide resolved
mmrazor/models/pruners/structure_pruning.py Outdated Show resolved Hide resolved
mmrazor/models/pruners/structure_pruning.py Show resolved Hide resolved
mmrazor/models/pruners/structure_pruning.py Outdated Show resolved Hide resolved
mmrazor/models/pruners/structure_pruning.py Outdated Show resolved Hide resolved
mmrazor/models/pruners/structure_pruning.py Show resolved Hide resolved
mmrazor/models/pruners/structure_pruning.py Show resolved Hide resolved
mmrazor/models/pruners/structure_pruning.py Show resolved Hide resolved
mmrazor/models/pruners/structure_pruning.py Show resolved Hide resolved
mmrazor/models/pruners/structure_pruning.py Show resolved Hide resolved
@pppppM pppppM merged commit 0ab5efe into open-mmlab:dev_v0.3.0 Apr 1, 2022
@HIT-cwh HIT-cwh deleted the fix_pruner_shared_module branch April 2, 2022 06:15
pppppM added a commit that referenced this pull request Apr 2, 2022
* [Feature] Add function to meet mmdeploy support (#102)

* add init_model function for mmdeploy

* fix lint

* add unittest for init_xxx_model

* fix lint

* mv test_inference.py to test_apis directory

* [Feature] Add function to meet mmdeploy support (#102)

* add init_model function for mmdeploy

* fix lint

* add unittest for init_xxx_model

* fix lint

* mv test_inference.py to test_apis directory

* [Refactor] Delete redundant `set_random_seed` function (#104)

* refactor set_random_seed

* add unittests

* fix unittests error

* fix lint

* avoid bc breaking

* [Feature] Add diff seeds to diff ranks and set torch seed in worker_init_fn (#113)

* add init_random_seed

* Set diff seed to diff workers

* [Feature] Add multi machine dist_train (#114)

* support multi nodes

* update training doc

* fix lints

* remove fixed seed

* fix ddp wrapper registry (#128)

* [Docs] Add brief installation steps in README(_zh-CN).md (#121)

* Add brief installation

* add brief installtion ref to mmediting pr#816

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* [BUG]Fix bugs in pruner (#126)

* fix bugs in pruner when pruning models with shared modules

* pruner can trace models with dilation conv2d

* fix deploy_subnet

* fix add_pruning_attrs

* fix bugs in modify_forward

* fix lint

* fix StructurePruner

* test tracing models with shared modules

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* [Docs]Add some more details to docs (#133)

* add docs for dataset

* add cfg-options for distillation

* fix docs

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* reset norm running status after prepare_from_supernet (#81)

* [Improvement]Sync train api (#115)

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* [Feature]Support Relational Knowledge Distillation (#127)

* add rkd

* add rkd pytest

* add rkd configs

* fix readme

* fix rkd

* split rkd loss to distance-wise and angle-wise losses

* rename rkd losses

* add rkd metaflie

* add rkd related links

* rename rkd metafile and add to model index

* delete cifar100

Co-authored-by: caoweihan <caoweihan@sensetime.com>
Co-authored-by: pppppM <gjf_mail@126.com>

Co-authored-by: qiufeng <44188071+wutongshenqiu@users.noreply.github.com>
Co-authored-by: wutongshenqiu <690364065@qq.com>
Co-authored-by: whcao <41630003+HIT-cwh@users.noreply.github.com>
Co-authored-by: caoweihan <caoweihan@sensetime.com>
pppppM added a commit to pppppM/mmrazor that referenced this pull request Jul 15, 2022
* [Feature] Add function to meet mmdeploy support (open-mmlab#102)

* add init_model function for mmdeploy

* fix lint

* add unittest for init_xxx_model

* fix lint

* mv test_inference.py to test_apis directory

* [Feature] Add function to meet mmdeploy support (open-mmlab#102)

* add init_model function for mmdeploy

* fix lint

* add unittest for init_xxx_model

* fix lint

* mv test_inference.py to test_apis directory

* [Refactor] Delete redundant `set_random_seed` function (open-mmlab#104)

* refactor set_random_seed

* add unittests

* fix unittests error

* fix lint

* avoid bc breaking

* [Feature] Add diff seeds to diff ranks and set torch seed in worker_init_fn (open-mmlab#113)

* add init_random_seed

* Set diff seed to diff workers

* [Feature] Add multi machine dist_train (open-mmlab#114)

* support multi nodes

* update training doc

* fix lints

* remove fixed seed

* fix ddp wrapper registry (open-mmlab#128)

* [Docs] Add brief installation steps in README(_zh-CN).md (open-mmlab#121)

* Add brief installation

* add brief installtion ref to mmediting pr#816

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* [BUG]Fix bugs in pruner (open-mmlab#126)

* fix bugs in pruner when pruning models with shared modules

* pruner can trace models with dilation conv2d

* fix deploy_subnet

* fix add_pruning_attrs

* fix bugs in modify_forward

* fix lint

* fix StructurePruner

* test tracing models with shared modules

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* [Docs]Add some more details to docs (open-mmlab#133)

* add docs for dataset

* add cfg-options for distillation

* fix docs

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* reset norm running status after prepare_from_supernet (open-mmlab#81)

* [Improvement]Sync train api (open-mmlab#115)

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* [Feature]Support Relational Knowledge Distillation (open-mmlab#127)

* add rkd

* add rkd pytest

* add rkd configs

* fix readme

* fix rkd

* split rkd loss to distance-wise and angle-wise losses

* rename rkd losses

* add rkd metaflie

* add rkd related links

* rename rkd metafile and add to model index

* delete cifar100

Co-authored-by: caoweihan <caoweihan@sensetime.com>
Co-authored-by: pppppM <gjf_mail@126.com>

Co-authored-by: qiufeng <44188071+wutongshenqiu@users.noreply.github.com>
Co-authored-by: wutongshenqiu <690364065@qq.com>
Co-authored-by: whcao <41630003+HIT-cwh@users.noreply.github.com>
Co-authored-by: caoweihan <caoweihan@sensetime.com>
pppppM added a commit to pppppM/mmrazor that referenced this pull request Jul 15, 2022
* [Feature] Add function to meet mmdeploy support (open-mmlab#102)

* add init_model function for mmdeploy

* fix lint

* add unittest for init_xxx_model

* fix lint

* mv test_inference.py to test_apis directory

* [Feature] Add function to meet mmdeploy support (open-mmlab#102)

* add init_model function for mmdeploy

* fix lint

* add unittest for init_xxx_model

* fix lint

* mv test_inference.py to test_apis directory

* [Refactor] Delete redundant `set_random_seed` function (open-mmlab#104)

* refactor set_random_seed

* add unittests

* fix unittests error

* fix lint

* avoid bc breaking

* [Feature] Add diff seeds to diff ranks and set torch seed in worker_init_fn (open-mmlab#113)

* add init_random_seed

* Set diff seed to diff workers

* [Feature] Add multi machine dist_train (open-mmlab#114)

* support multi nodes

* update training doc

* fix lints

* remove fixed seed

* fix ddp wrapper registry (open-mmlab#128)

* [Docs] Add brief installation steps in README(_zh-CN).md (open-mmlab#121)

* Add brief installation

* add brief installtion ref to mmediting pr#816

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* [BUG]Fix bugs in pruner (open-mmlab#126)

* fix bugs in pruner when pruning models with shared modules

* pruner can trace models with dilation conv2d

* fix deploy_subnet

* fix add_pruning_attrs

* fix bugs in modify_forward

* fix lint

* fix StructurePruner

* test tracing models with shared modules

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* [Docs]Add some more details to docs (open-mmlab#133)

* add docs for dataset

* add cfg-options for distillation

* fix docs

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* reset norm running status after prepare_from_supernet (open-mmlab#81)

* [Improvement]Sync train api (open-mmlab#115)

Co-authored-by: caoweihan <caoweihan@sensetime.com>

* [Feature]Support Relational Knowledge Distillation (open-mmlab#127)

* add rkd

* add rkd pytest

* add rkd configs

* fix readme

* fix rkd

* split rkd loss to distance-wise and angle-wise losses

* rename rkd losses

* add rkd metaflie

* add rkd related links

* rename rkd metafile and add to model index

* delete cifar100

Co-authored-by: caoweihan <caoweihan@sensetime.com>
Co-authored-by: pppppM <gjf_mail@126.com>

Co-authored-by: qiufeng <44188071+wutongshenqiu@users.noreply.github.com>
Co-authored-by: wutongshenqiu <690364065@qq.com>
Co-authored-by: whcao <41630003+HIT-cwh@users.noreply.github.com>
Co-authored-by: caoweihan <caoweihan@sensetime.com>
humu789 pushed a commit to humu789/mmrazor that referenced this pull request Feb 13, 2023
* add readme zn-cn

* update punctuation
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

use autoslim for yolof How to make pruner to support FPN like structure?
2 participants