Commit Graph

116 Commits (1ee9bbe0508ce2ec83058559e24c3bfa95d1f32e)

Author SHA1 Message Date
Ma Zerun 3472ee5d2c
[Feature] Implememnt the universal visualizer for multiple task. (#1404)
* [Feature] Implememnt the universal visualizer for multiple task.

* Update tools

* Improve according to comments.

* Fix tools docs

* Add --test-cfg option and set default collate function.
2023-03-09 11:36:54 +08:00
Ma Zerun dbf3df21a3
[Refactor] Use `out_type` to specify ViT-like backbone output. (#1408)
* [Refactor] Use  to specify ViT-like backbone output.

* Fix ClsBatchNormNeck

* Update mmpretrain/models/necks/mae_neck.py

---------

Co-authored-by: Yixiao Fang <36138628+fangyixiao18@users.noreply.github.com>
2023-03-09 11:02:58 +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 a05c79e806
[Refactor] Move transforms in mmselfsup to mmpretrain. (#1396)
* [Refactor] Move transforms in mmselfsup to mmpretrain.

* Update transform docs and configs. And register some mmcv transforms in
mmpretrain.

* Fix missing transform wrapper.

* update selfsup transforms

* Fix UT

* Fix UT

* update gaussianblur inconfigs

---------

Co-authored-by: fangyixiao18 <fangyx18@hotmail.com>
2023-03-03 15:01:11 +08:00
Yixiao Fang c9670173aa
[Refactor] Move and refactor utils from mmselfsup. (#1385)
* add heads

* add losses

* fix

* remove mim head

* add modified backbones and target generators

* fix lint

* fix lint

* add heads

* add losses

* fix

* add data preprocessor from mmselfsup

* add ut for data prepocessor

* add GatherLayer

* add ema

* add batch shuffle

* add misc

* fix lint

* update

* update docstring
2023-02-28 17:04:40 +08:00
Yixiao Fang 63d9f27fde
[Refactor] Add necks, heads and losses for the self-supervised task. (#1376)
* add necks

* refactor linear neck

* rename simmim neck

* add heads

* add losses

* fix

* add unittest

* update

* update cae

* remove mim head

* update config
2023-02-28 10:05:00 +08:00
Yixiao Fang 89000c10eb
[Refactor] Refactor configs and metafile (#1369)
* update base datasets

* update base

* update barlowtwins

* update with new convention

* update

* update

* update

* add schedule

* add densecl

* add eva

* add mae

* add maskfeat

* add milan and mixmim

* add moco

* add swav simclr

* add simmim and simsiam

* refine

* update

* add to model index

* update config inheritance

* fix error in metafile

* Update pre-commit and metafile check script

* update metafile

* fix name error

* Fix classification model name and config name

---------

Co-authored-by: mzr1996 <mzr1996@163.com>
2023-02-23 11:17:16 +08:00
mzr1996 0979e78573 Rename the package name to `mmpretrain`. 2023-02-17 15:20:55 +08:00
takuoko 841256b630
[Feature] Support RetrieverRecall metric & Add ArcFace config (#1316)
* rebase

* add ap metric

* fix mlti-gpu bug in retrevel

* rebase

* rebase

* add training cfgs and update readme.md

* fix bugs(cannot load vecs in dist and diff test-val recall\)

* update configs and readme

* fix ut

* fix doc

* rebase

* fix rebase conflicts

* fix rebase error

* fix UT error

* fix docs

* fix typo

---------

Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>
2023-02-14 12:46:21 +08:00
aso538 6b9e2b55dd
[Feature] Support LeViT backbone. (#1238)
* 网络搭建完成、能正常推理

* 网络搭建完成、能正常推理

* 网络搭建完成、能正常推理

* 添加了模型转换未验证,配置文件 但有无法运行

* 模型转换、结构验证完成,可以推理出正确答案

* 推理精度与原论文一致 已完成转化

* 三个方法改为class 暂存

* 完成推理精度对齐 误差0.04

* 暂时使用的levit2mmcls

* 训练跑通,训练相关参数未对齐

* '训练相关参数对齐'参数'

* '修复训练时验证导致模型结构改变无法复原问题'

* '修复训练时验证导致模型结构改变无法复原问题'

* '添加mixup和labelsmooth'

* '配置文件补齐'

* 添加模型转换

* 添加meta文件

* 添加meta文件

* 删除demo.py测试文件

* 添加模型README文件

* docs文件回滚

* model-index删除末行空格

* 更新模型metafile

* 更新metafile

* 更新metafile

* 更新README和metafile

* 更新模型README

* 更新模型metafile

* Delete the model class and get_LeViT_model methods in the mmcls.models.backone.levit file

* Change the class name to Google Code Style

* use arch to provide default architectures

* use nn.Conv2d

* mmcv.cnn.fuse_conv_bn

* modify some details

* remove down_ops from the architectures.

* remove init_weight function

* Modify ambiguous variable names

* Change the drop_path in config to drop_path_rate

* Add unit test

* remove train function

* add unit test

* modify nn.norm1d to build_norm_layer

* update metafile and readme

* Update configs and LeViT implementations.

* Update README.

* Add docstring and update unit tests.

* Revert irrelative modification.

* Fix unit tests

* minor fix

Co-authored-by: mzr1996 <mzr1996@163.com>
2023-01-17 17:43:42 +08:00
szwlh-c c98dc4555c
[Feature] Support VIG Backbone. (#1304)
* 添加vig源文件

* 某些模块修改到mmcls风格

* 修改到mmcls风格

* 修改

* 添加VIG模型及源文件

* update model file

* update model file and config

* change class name and some variable name

* change class name and some variable name

* update

* update

* change nn.BatchNorm to mmcv.cnn.build_norm_layer

* update

* change nn.Seq to mmcls

* change backbone to stage_blocks

* add vig_head

* update

* update config file

* update

* add readme and metafile

* update model-index.yml

* update model file

* rename config file and add docstring

* variable rename

* update readme and metafile

* update readme

* update

* Update VIG backbone implementation and docs.

* Fix configs.

Co-authored-by: mzr1996 <mzr1996@163.com>
2023-01-17 16:55:56 +08:00
Ma Zerun 060b0ed3b5
[Feature] Support ConvNeXt-V2 backbone. (#1294)
* [Feature] Support ConvNeXt-V2.

* Use registry of mmcls instead of mmengine.

* Add README.

* Add unit tests and docs.
2023-01-06 16:13:41 +08:00
QINGTIAN e880451a54
[Improve] Remove useless EfficientnetV2 config files. (#1300)
* update model file

* Delete xcit.py

* Delete efficientnet_v2_b0.py

* Delete efficientnet_v2_b1.py

* Delete efficientnet_v2_b2.py

* Delete efficientnet_v2_b3.py

* Delete efficientnet_v2_l.py

* Delete efficientnet_v2_m.py

* Delete efficientnet_v2_s.py

* Delete efficientnet_v2_xl.py

* Delete efficientnet_v2-b0_8xb32_in1k.py

* Delete efficientnet_v2-b1_8xb32_in1k.py

* Delete efficientnet_v2-b2_8xb32_in1k.py

* Delete efficientnet_v2-b3_8xb32_in1k.py

* Delete efficientnet_v2-l_8xb32_in1k.py

* Delete efficientnet_v2-l_8xb32_in21ft1k.py

* Delete efficientnet_v2-m_8xb32_in1k.py

* Delete efficientnet_v2-m_8xb32_in21ft1k.py

* Delete efficientnet_v2-s_8xb32_in1k.py

* Delete efficientnet_v2-s_8xb32_in21ft1k.py

* Delete efficientnet_v2-xl_8xb32_in21ft1k.py

Co-authored-by: qingtian <459291290@qq.com>
2023-01-06 16:10:59 +08:00
QINGTIAN 74743ef588
[Feature] [CodeCamp #68] Add EfficientnetV2 Backbone. (#1253)
* add efficientnet_v2.py

* add efficientnet_v2 in __init__.py

* add efficientnet_v2_s base config file

* add efficientnet_v2 config file

* add efficientnet_v2 config file

* update tuple output

* update config file

* update model file

* update model file

* update model file

* update config file

* update model file

* update config file

* update model file

* update model file

* update model file

* update model file

* update model file

* update config file

* update config file

* update model file

* update model file

* update model file

* update model file

* update model config file

* Update efficientnet_v2.py

* add config file and modify arch

* add config file and modify arch

* add the file about convert_pth from timm to mmcls

* update efficientnetv2 model file with mmcls style

* add the file about convert_pth from timm to mmcls

* add the file about convert_pth from timm to mmcls

* update convert file

* update model file

* update convert file

* update model file

* update model file

* update model file

* add metefile and README

* Update tools/model_converters/efficientnetv2-timm_to_mmcls.py

Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>

* update model file and convert file

* update model file and convert file

* update model file and convert file

* update model file and convert file

* update model file

* update model file

* update model file

* update config file and README file

* update metafile

* Update efficientnetv2_to_mmcls.py

* update model-index.yml

* update metafile.yml

* update b0 and s train pipeline

* update b0 and s train pipeline

* update b0 and s train pipeline

* add test_efficientnet_v2

* update test_efficientnet_v2

* update model file docs

* update test_efficientnet_v2

* update test_efficientnet_v2

* add efficientnet_v2.py

* add efficientnet_v2 in __init__.py

* add efficientnet_v2_s base config file

* add efficientnet_v2 config file

* add efficientnet_v2 config file

* update tuple output

* update config file

* update model file

* update model file

* update model file

* update model file

* update config file

* update config file

* update model file

* update model file

* update model file

* update model file

* update model file

* update config file

* update config file

* update model file

* update model file

* update model file

* update model file

* update model config file

* Update efficientnet_v2.py

* add config file and modify arch

* add config file and modify arch

* add the file about convert_pth from timm to mmcls

* update efficientnetv2 model file with mmcls style

* add the file about convert_pth from timm to mmcls

* add the file about convert_pth from timm to mmcls

* update convert file

* update model file

* update convert file

* update model file

* update model file

* update model file

* add metefile and README

* Update tools/model_converters/efficientnetv2-timm_to_mmcls.py

Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>

* update model file and convert file

* update model file and convert file

* update model file and convert file

* update model file and convert file

* update model file

* update model file

* update model file

* update config file and README file

* update metafile

* Update efficientnetv2_to_mmcls.py

* update model-index.yml

* update metafile.yml

* update b0 and s train pipeline

* update b0 and s train pipeline

* update b0 and s train pipeline

* add test_efficientnet_v2

* update test_efficientnet_v2

* update model file docs

* update test_efficientnet_v2

* update test_efficientnet_v2

* pass pre-commit hook

* refactor efficientnetv2

* refactor efficientnetv2

* update readme, metafile and weight links

* update model-index.yml

* fix lint

* fix typo

* Update efficientnetv2-b1_8xb32_in1k.py

* Update efficientnetv2-b2_8xb32_in1k.py

* Update efficientnetv2-b3_8xb32_in1k.py

* update two moduals and model file

* update modual file

* update accuracys

* update accuracys

* update metafile

* fix build docs

* update links

* update README.md

Co-authored-by: qingtian <459291290@qq.com>
Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>
2022-12-30 15:18:39 +08:00
Rongjie Li 5b266d9e7c
[Feature] Add clip backbone. (#1258)
* clip backbone added

* passed precommit

* update readme

* update according to PR review

* add missing file

* add unittest

* refine metafile

* refine metafile and readme for readdocs

* refine metafile

* refine metafile

* Update metafile

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-12-22 16:33:57 +08:00
Wangbo Zhao(黑色枷锁) 14dcb69092
[Feature] Add mixmim backbone with checkpoints. (#1224)
* add mixmim backbone

* add mixmim inference

* add docstring, metafile, test and modify readme

* Update README and metafile

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-12-20 16:52:54 +08:00
Songyang Zhang 5547f4cac4
[Feature] Add TinyViT for dev-1.x. (#1042)
* [Feature] add TinyViT for dev-1.x

* [Feature] update readme

* fix lint error

* refactor the code

* [Update] update the args

* [Update] add unit test and fix bugs

* Rename the configuration file

* delete invalid files

* [Feature] update tinyvit readme

* [Feature] update tinyvit readme

* [Feature] update metafile

* Update tinyvit metafile
2022-12-20 13:04:00 +08:00
Ma Zerun b63515111b
[Reproduce] Update ConvNeXt config files. (#1256)
* Update ConvNeXt training configs.

* Update ConvNeXt network.

* Update metafile and README.

* Update README
2022-12-19 13:54:24 +08:00
takuoko 2535c1ecd7
[Feature] Support EVA. (#1239)
* add eva

* add eva

* add eva

* sklearn -> scikit-learn

* add large

* Update model names and links.

* Fix resize pos embed error when loading fp16 weight.

* Remove verbose configs.

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-12-14 13:21:33 +08:00
Songyang Zhang 210373c093
[Feature] Implementation of RevViT. (#1127)
* [Feature] implement rev-vit network

* can reproduce the RevViT-Small accuracy 79.9

* update

* [Feature] update revvit

* [Feature] update revvit readme

* Update links

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-12-14 11:46:39 +08:00
Ma Zerun f9be21ab74
[Docs] Add version selection in the banner. (#1217)
* [Docs] Add version selection in the banner.

* Small fix.
2022-11-23 13:38:23 +08:00
Ma Zerun 13ff394985
Bump version to v1.0.0rc3. (#1211)
* Bump version to v1.0.0rc3

* Update pre-commit hook
2022-11-21 18:21:48 +08:00
takuoko 4fb44f8770
[Feature] EfficientNets NoisyStudent & L2. (#1122)
* add mvit 21k

* add mvit 21k

* add effnet noisy student

* Revert "add mvit 21k"

This reverts commit f51067c559.

* revert mvit pr

* update link and readme

* update readme

* update l2 link

* update link

Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>
2022-11-21 16:57:13 +08:00
Ezra-Yu 4969830c8a
[Enhance] Reproduce mobileone training accuracy. (#1191)
* add switch hook and UTs

* update doc

* update doc

* fix lint

* fix ci

* fix ci

* fix typo

* fix ci

* update configs names

* update configs

* update configs

* update links

* update readme

* update vis_scheduler

* update metafile

* update configs

* rebase

* fix ci

* rebase
2022-11-21 10:43:34 +08:00
Hubert 629f6447ef
[Feature] Migrate CSRA head to 1.x. (#1177)
* [Feat] add csra to 1x

* minor fix

* add voc metrics

* refine

* add unittest

* minor fix

* add more comments

* Fix docs and metafile.

* Fix docs.

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-11-21 10:39:16 +08:00
Jiahao Wang 72c6bc4864
[Feature] Support RepLKnet backbone. (#1129)
* update replknet configs

* update replknet test

* update replknet model

* update replknet model

* update replknet model

* update replknet model

* Fix docs and config names

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-11-21 10:18:58 +08:00
takuoko c4f3883a22
[Feature] Support DaViT. (#1105)
* add davit

* fix mixup config

* convert scripts

* lint

* test

* test

* Add checkpoint links.

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-11-16 17:23:55 +08:00
Hubert 1b98fc13d9
[Enhance] Add more mobilenetv3 pretrains. (#1154)
* add small-050/075 and move files

* add previous results

* Update checkpoint link

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-11-14 17:06:39 +08:00
Yang Gao 11cd88f39a
[Fix] Fix configs due to api refactor of `num_classes`. (#1184) 2022-11-14 14:43:56 +08:00
takuoko d05cbbcf9b
[Feature] Support HorNet Backbone for dev1.x. (#1094)
* add hornet

* add hornet

* fix mixup config

* add optim cfgs

Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>
2022-11-04 15:33:46 +08:00
Ezra-Yu 63b124e2d7
[Docs] Improve Swin Doc and Add Tabs enxtation. (#1145)
* improve_swin_doc

* fix requirments

* improve swin2 docs

* improve swin2 docs

* update

* update CN doc

* update CN doc

* update comments

* fix error

* update register_all_modules

* Update README.md

* Update stat.py

* Update readme

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-11-04 11:58:39 +08:00
Hubert bcca619066
[Feature] Support MobileViT backbone. (#1068)
* init

* fix

* add config

* add meta

* add unittest

* fix for comments

* Imporvee docstring and support custom arch.

* Update README

* Update windows CI

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-10-18 17:05:59 +08:00
Ma Zerun 29f066f7fb
[Improve] Speed up data preprocessor. (#1064)
* [Improve] Speed up data preprocessor.

* Add ClsDataSample serialization override functions.

* Add unit tests

* Modify configs to fit new mixup args.

* Fix `num_classes` of the ImageNet-21k config.

* Update docs.
2022-10-17 17:08:18 +08:00
takuoko a49c3076e1
[Feature] Support DeiT3. (#1065)
* deit3

deit3

lint

* add tools and test

* deit3

* deit3

* fix preprocess

* lint

* Update config names and checkpoint paths

* Update convert tools to use mmengine, and fix docstring.

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-10-10 14:54:20 +08:00
Ma Zerun 034683cfcd
[Feature] Support MViT for MMCLS 1.x (#1023)
* [Feature] Support MViT for MMCLS 1.x

* Add unit tests

* Update documentation
2022-09-22 09:23:49 +08:00
Songyang Zhang 81f10ccbb7
[Feature] Support EdgeNeXt for dev-1.x. (#1037)
* [Feature] add EdgeNeXt for dev-1.x

* [Feature] add update

* Imporve EdgeNeXt

* Fix div error in low pytorch version

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-09-21 13:27:04 +08:00
Ma Zerun e9e2d48cb2
[Improve] Update benchmark scripts (#1028)
* Update train benchmark scripts

* Add `--cfg-options` for dev scripts and enhance `--range`.

* Fix bug of regex expression.

* Fix minor bugs

* Update ShuffleNet configs

* Update rsb-a1 configs and label smooth loss mode.

* Update inference dev scripts

* From `mmengine` instead of `mmcv` import fileio.

* Fix lint

* Update pre-commit hook

* Use `use_sigmoid` option instead of "bce" mode in label smooth loss.
2022-09-20 15:50:21 +08:00
Hubert e4e8047563
[Feature] Support Swin Transformer V2 for MMCLS 1.x. (#1029)
* [Feature] support swin v2 in mmcls 1.x

* fix configs

* fix clamp max

* Fix meshgrid

* Imporve swin v2

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-09-20 15:45:27 +08:00
Ezra-Yu aaf127c5e1
[Feature] Add efficientformer Backbone for MMCls 1.x. (#1031)
* rebase

* update filename

* update URL

* update UT

* fix lint

* update head

* add efficientformer

* update filename

* update UT

* fix lint

* update configs

* rebase

* fix unit tests

* Fix comments and docs.

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-09-20 14:56:45 +08:00
Ezra-Yu f1d2f50c21
[Feature] Add MobileOne Backbone For MMCls 1.x. (#1030)
* add mobileOne

* add train cfg

* update cfgs

* update URL

* update configs

* update inceptionv3 metafile

* add configs

* fix lint

* update checkpoint urls

* Update configs

* Update README

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-09-16 11:55:10 +08:00
Ezra-Yu 0e3e8e91cc
[Refactor] Refactor Config Doc. (#987)
* refactor config doc

* refine

* Fix the config docs.

* update CN config

* Fix some grammar erros.

* Fix Chinese docs.

Co-authored-by: mzr1996 <mzr1996@163.com>
2022-08-29 11:10:05 +08:00
mzr1996 735a3ee11f Update auto_scale_lr fields 2022-07-18 11:11:13 +08:00
mzr1996 24bcf069f8 [Refactor] Refactor dev scripts 2022-07-18 11:11:13 +08:00
mzr1996 c0f3ba68a8 Add MAE version ViT-base training results and fix some errors in configs. 2022-07-18 11:11:13 +08:00
Ezra-Yu d8f556668e Refactor vis scheduler tool 2022-07-18 11:11:13 +08:00
Ezra-Yu 7bca2516f0 Add CUB dataset 2022-07-18 11:11:13 +08:00
Ezra-Yu a9057e88c4 Add multi label metrics 2022-07-18 11:11:13 +08:00
mzr1996 f3299b4ca2 [Refactor] Refactor batch augmentations 2022-07-18 11:11:13 +08:00
mzr1996 522ab1fd84 [Feature] Add Visualization hook 2022-07-18 11:11:04 +08:00
yingfhu c78b5597d8 [Refactor] refactor randomCrop, randomResizeCrop and CenterCrop。 2022-07-18 10:57:17 +08:00