11 Commits

Author SHA1 Message Date
Ma Zerun
274a67223e
[Feature] Implement layer-wise learning rate decay optimizer constructor. (#1399)
* [Feature] Implement layer-wise learning rate decay optimizer constructor.

* Use num_layers instead of max_depth to avoid misleading

* Add UT

* Update docstring

* Update log info

* update LearningRateDecay configs

---------

Co-authored-by: fangyixiao18 <fangyx18@hotmail.com>
2023-03-07 17:30:39 +08:00
Yixiao Fang
08dc8c75d3
[Refactor] Add selfsup algorithms. (#1389)
* remove basehead

* add moco series

* add byol simclr simsiam

* add ut

* update configs

* add simsiam hook

* add and refactor beit

* update ut

* add cae

* update extract_feat

* refactor cae

* add mae

* refactor data preprocessor

* update heads

* add maskfeat

* add milan

* add simmim

* add mixmim

* fix lint

* fix ut

* fix lint

* add eva

* add densecl

* add barlowtwins

* add swav

* fix lint

* update readtherdocs rst

* update docs

* update

* Decrease UT memory usage

* Fix docstring

* update DALLEEncoder

* Update model docs

* refactor dalle encoder

* update docstring

* fix ut

* fix config error

* add val_cfg and test_cfg

* refactor clip generator

* fix lint

* pass check

* fix ut

* add lars

* update type of BEiT in configs

* Use MMEngine style momentum in EMA.

* apply mmpretrain solarize

---------

Co-authored-by: mzr1996 <mzr1996@163.com>
2023-03-06 16:53:15 +08:00
Ma Zerun
dda3d6565b
[Docs] Update generate_readme.py and readme files. (#1388)
* Update generate_readme.py and readme files.

* Update reamde

* Update docs

* update metafile

* update simmim readme

* update

* update mae

* fix lint

* update mocov2

* update readme pic

* fix lint

* Fix mmcls download links.

* Fix Chinese docs.

* Decrease readthedocs requirements.

---------

Co-authored-by: fangyixiao18 <fangyx18@hotmail.com>
2023-03-02 13:29:07 +08:00
Ma Zerun
a3f2effb17
[Feature] Add ImageClassificationInferencer. (#1261)
* [Feature] Add ImageClassificationInferencer.

* Update inferencer implementation and add unit tests.

* Update documentations.

* Update pre-commit hook

* Update docs
2023-02-08 14:30:12 +08:00
Ma Zerun
7b9a1010f5
[Enhance] Support evaluate on both EMA and non-EMA models. (#1204)
* [Enhance] Support evaluate on both EMA and original models.

* Fix lint
2022-12-05 14:16:12 +08:00
Ezra-Yu
b0007812d6
[Enhance] Enhance ArcFaceClsHead. (#1181)
* update arcface

* fix unit tests

* add adv-margins

add adv-margins

update arcface

* rebase

* update doc and fix ut

* rebase

* update code

* rebase

* use label data

* update set-margins

* Modify Arcface related method names.

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-11-21 18:10:39 +08:00
Ezra-Yu
c3c1cb93aa
[Feature] Add Switch Recipe Hook. (#1101)
* add switch hook and UTs

* update doc

* update doc

* fix lint

* fix ci

* fix ci

* fix typo

* fix ci

* switchTrainAugHook to switchRecipeHook

* fix lint

* Refactor the `SwitchRecipeHook`.

* Fix windows CI

* Fix windows CI

* Fix windows CI.

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-11-18 18:12:03 +08:00
Ma Zerun
0b61b76325
[Docs] Add Migration documentation. (#997)
* [Docs] Add Migration documentation.

* Fix the train_cfg argument

* [WIP] Improve according to comments

* Imporve according to comments.
2022-08-31 13:31:48 +08:00
Ezra-Yu
ccece7e6dc
[Docs] Refactor dataset tutorial (#916)
* refactor dataset tutorials

* split into user_guide and advance_guide

* refine

* Fix dataset preparasion tutorial.

* refine CN docs

* update docs API doc link

* refine new a dataset

* refine new a dataset

* refine new a dataset

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-08-30 18:45:58 +08:00
Ezra-Yu
e34588a315
[Docs] Refactor API docs. (#958)
* rebase

* update process

* add TODOs in moved classes

* update APIs

* modify the preprocess_cfg to data_preprocessor

* Fix api docs.

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-08-29 15:35:10 +08:00
Ma Zerun
b4e39d51d6
[Refactor] Refactor the docs structure. (#988)
* [Refactor] Refactor the rest data transforms and fix some docstring.

* Use `mmengine` instead of `mmcv`

* Refactor KFold dataset tools

* Fix docstring according to comments

* [Refactor] Refactor the docs structure.

* Rename `getting_started.md` to `get_started.md`

* Rename `transforms` to `data_process`
2022-08-24 16:00:36 +08:00