21e2110673
Refactor Diff Mutator
2022-07-15 23:04:13 +08:00
31b60501c9
Update registry and fix ci
2022-07-15 23:04:13 +08:00
804a595fc6
Refactor DiffMutable, DiffOP and DiffChoiceRoute.
2022-07-15 23:04:13 +08:00
99e7993376
Refactor backbone
2022-07-15 23:04:13 +08:00
910b131183
Refactor Mutator
2022-07-15 23:04:13 +08:00
3e4b04a02f
Refactor Mutable
2022-07-15 23:04:13 +08:00
dee5352f92
[CI] Add mypy and mdformat
2022-07-15 23:04:10 +08:00
590bfa448c
[Refactor] Refactor SPOS & DetNAS interface
2022-07-15 23:02:57 +08:00
4b5ddaf642
[Refactor] Refactor Registry
2022-07-15 23:02:57 +08:00
2efe63e9a4
[CI] Add Gitlab CI
2022-07-15 23:02:57 +08:00
baa8c8614e
[Deprecated] Clean up code that will be deprecated in OpenMMLab 2.0
2022-07-15 23:02:37 +08:00
8b57a07b5e
[Bug] fix bug in find_make_group_parser for depthwise ( #195 )
...
Co-authored-by: yangmin <yangmin@microbt.com>
2022-07-08 13:49:03 +08:00
c83a0718ef
Fix darts metafile
2022-07-06 21:51:56 +08:00
1abad087eb
[Bug]Autoslim different checkpoints have the same size ( #193 )
...
* fix: split autoslim different checkpoint has equal model size
* chore: pre-commit
* chore: pre-commit
Co-authored-by: Lance（Yongle） Wang <lance.wang@vastaitech.com>
2022-07-05 13:32:03 +08:00
3cc359e364
Test commands of mim in CI ( #186 )
2022-06-23 10:25:22 +08:00
16c643d946
[Fix] Fix init mmdet model api ( #179 )
...
* fix init_mmdet_model
* add test
2022-06-15 19:21:01 +08:00
9db5fe5547
[Docs] Fix mdformat version to support python3.6 ( #181 )
...
* fix mdformat version to support python3.6
* fix readme
2022-06-15 19:20:15 +08:00
474d4703c3
Add mim to extras_require in setup.py ( #180 )
2022-06-15 19:19:35 +08:00
4f0f5ff9c0
[Installation] Add MANIFEST.in ( #173 )
...
* add manifest.in
* remove setup.py modify
* fix Upgrade pip lint
2022-06-09 09:04:37 +08:00
5fa35829eb
[Docs] Reformat README ( #169 )
...
* reformat readme
* reformat model zoo
* fix comma
* fix img
2022-06-09 09:03:00 +08:00
71a196490b
[Docs] Configure Myst-parser to parse anchor tag ( #164 )
2022-05-31 16:22:29 +08:00
b8daedf544
[Docs] Replace markdownlint with mdformat ( #163 )
...
* markdonwlint -> mdformat
* update mmcv min and max version
* fix README_zh-CN links
2022-05-31 16:21:53 +08:00
2dad24044d
Bump version to 0.3.1 ( #155 )
...
* [Enhance] Add extra dataloader settings in configs (#141 )
* [Docs] fix md link failure in docs (#142 )
* [Docs] update Cream readme
* delete 'readme.md' in model_zoo.md
* fix md link failure in docs
* [Docs] add myst_parser to extensions in conf.py
* [Docs] delete the deprecated recommonmark
* [Docs] delete recommandmark from conf.py
* [Docs] fix md link failure and lint failture
* [Fix] Fix seed error in mmseg/train_seg.py and typos in train.md (#152 )
* [Docs] update Cream readme
* delete 'readme.md' in model_zoo.md
* fix cwd docs and fix seed in #151
* delete readme of cream
* [Enhancement]Support broadcast_object_list in multi-machines & support Searcher running in single GPU (#153 )
* broadcast_object_list support multi-machines
* add userwarning
* [Fix] Fix configs (#149 )
* fix configs
* fix spos configs
* fix readme
* replace the official mutable_cfg with the mutable_cfg searched by ourselves
* update https prefix
Co-authored-by: pppppM <gjf_mail@126.com>
* [BUG]Support to prune models containing GroupNorm or InstanceNorm. (#144 )
* suport GN and IN
* test pruner
* limit pytorch version
* fix pytest
* throw an error when tracing groupnorm with torch version under 1.6.0
Co-authored-by: caoweihan <caoweihan@sensetime.com>
* Bump version to 0.3.1
Co-authored-by: qiufeng <44188071+wutongshenqiu@users.noreply.github.com>
Co-authored-by: PJDong <1115957667@qq.com>
Co-authored-by: humu789 <88702197+humu789@users.noreply.github.com>
Co-authored-by: whcao <41630003+HIT-cwh@users.noreply.github.com>
Co-authored-by: caoweihan <caoweihan@sensetime.com>
2022-05-05 01:02:45 +08:00
e4e95131a2
Update version to 0.3.0
2022-04-02 19:39:47 +08:00
49f1bee45b
Bump version to v0.3.0 ( #135 )
...
* [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>
2022-04-02 19:30:50 +08:00
81e0e3452a
[Feature] Resume from the latest checkpoint automatically. ( #61 )
...
* support auto-resume
* support auto-resume
* support auto-resume
* support auto-resume
Co-authored-by: pppppM <67539920+pppppM@users.noreply.github.com>
2022-03-08 11:25:19 +08:00
366fd0f095
Bump version to v0.2.0 ( #106 )
2022-03-07 23:22:44 +08:00
ef1637e866
[FEATURE] Mobilenet Series Search Space ( #82 )
...
* add mbv2 block and identity
* add mbv2 block and identity unittests
* expand_factor -> expand_ratio
* add searchable mobilenet v2
* fix lints
* add spos subnet retraining config
* fix mmcls slurm search
* add proxyless_gpu setting for mbv2
* use bn default
* add angelnas spos config
* update spos readme
* fix SELayer's useage
* add docstring
* rename mbv2 to mb
* add some unittest of mb
* rename mb to mobilenet
* add some rename-mb in configs
* update README of spos
* add rename-mb in unittest
* update test_mmcls
Co-authored-by: wutongshenqiu <690364065@qq.com>
Co-authored-by: humu789 <humu@pjlab.org.cn>
2022-03-07 23:15:18 +08:00
f59e059cf7
[Fix]Modify BN to SyncBN ( #103 )
...
* modify syncBN and bn_training_mode
* undo modify bn_training_mode
2022-03-07 22:51:05 +08:00
91415b92a5
[Enhancement] Add distributed scripts ( #105 )
...
* add dist scripts
* add PYTHONPATH
2022-03-07 22:07:13 +08:00
608d9514c6
[Enhancement] Reorganizing OpenMMLab projects in readme ( #98 )
2022-03-02 20:30:50 +08:00
c5a097b150
Add a new pre-commit-hook to automatically add a copyright ( #96 )
...
* Add a new pre-commit-hook to automatically add a copyright
* add check-algo-readme
Co-authored-by: qiufeng <44188071+wutongshenqiu@users.noreply.github.com>
* fix alg-readme lints
Co-authored-by: qiufeng <44188071+wutongshenqiu@users.noreply.github.com>
2022-03-02 20:29:28 +08:00
931a0a60c3
[Docs] Add Algorithm Metafiles ( #87 )
...
* add metafiles
* fix lints
* add model-index.yml
* rename metafile.yaml to metafile.yml
* fix lint
* add spaces
* add spaces
* add spaces
2022-03-02 18:16:17 +08:00
b319c1f553
[CI] update pre-commit-config ( #93 )
2022-02-23 19:31:18 +08:00
cf738c15e6
[CI] Add CI for windows and redesign CI ( #95 )
...
* seperate lint and update matrix
* remove experimental
* redesign github ci
* add windows test
* fix windows permission issue
* fix pytorch link
* download opencv
* delete unused command
2022-02-23 19:29:34 +08:00
3b6423d39b
fix slurm search shell scripts ( #90 )
2022-02-17 14:51:57 +08:00
5ec23273c6
[Docs]Update README according to OpenMMLab standard. ( #65 )
...
* Update README according to OpenMMLab standard.
* [Refactor]Deprecate the support for ``python setup.py test`` (#60 )
* Deprecate the support for ``python setup.py test``
* Update requirements
* Upgrade isort in pre-commit hook (#70 )
* Update README according to OpenMMLab standard.
* modify uppercase and lowercase
Co-authored-by: whcao <41630003+HIT-cwh@users.noreply.github.com>
2022-02-16 18:06:07 +08:00
cb6f579fa0
[Fix] Fix typo in BaseDistiller ( #73 )
2022-02-11 13:03:34 +08:00
4121e58fcc
Upgrade isort in pre-commit hook ( #70 )
2022-02-10 10:02:02 +08:00
0dd407abc4
[Refactor]Deprecate the support for ``python setup.py test`` ( #60 )
...
* Deprecate the support for ``python setup.py test``
* Update requirements
2022-01-27 09:43:20 +08:00
64ccbc03fd
[Enhance] Add setup multi-processes for all tasks ( #59 )
...
* Add setup-multi-processes for all tasks
* Add setup-multi-processes for all tasks
* Add test for setup-multi-processes
2022-01-26 19:17:55 +08:00
8b6c084e40
[Fix] Fix bug in non-distributed training/testing for all tasks ( #63 )
...
* Fix bug in non-distributed training/testing for all tasks
* Fix add warning infos
2022-01-26 19:16:29 +08:00
f67d2ab10e
Support CPU training ( #62 )
2022-01-26 19:13:38 +08:00
5da63685fd
add OpenMMLab website and platform links and mmdeploy ( #58 )
...
Co-authored-by: qiufeng <qiufeng3217@gmail.com>
2022-01-26 19:12:58 +08:00
a37133d04c
[Bug]Fix train api ( #55 )
...
* fix a bug about registering custom_hooks twice
* update train.py in mmdet and mmseg
* update train.py in mmdet and mmseg
Co-authored-by: caoweihan <caoweihan@sensetime.com>
2022-01-26 19:12:09 +08:00
9596379bb3
[Fix] Fix `show_result` error during test ( #53 )
...
* move from algorithm to model
* rename model to algorithm
2022-01-19 19:32:37 +08:00
1f55e234b3
[Docs] Fix some unconsistency ( #51 )
...
* del ceph setting in configs
* fix some unconsistency between algo's README and configs
2022-01-17 16:09:35 +08:00
721abc4a42
[Docs] Use shared menu from theme instead ( #38 )
...
* fix share menu
* initialize zh_cn
Co-authored-by: qiufeng <qiufeng3217@gmail.com>
2022-01-12 19:58:03 +08:00
b6c5fffe8f
fix symlink error on windows ( #41 )
...
Co-authored-by: qiufeng <qiufeng3217@gmail.com>
2022-01-06 15:35:14 +08:00
d5a9e38efe
[Docs]Update logos ( #30 )
...
* replace logos
* update logo
* update logo
Co-authored-by: caoweihan <caoweihan@sensetime.com>
2021-12-31 12:45:25 +08:00
pppppM
PJDong
qiufeng
NickYangMin
lance
humu789
whcao
Xiaolin Wang