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
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
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
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
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
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
c127c474b9
[Feature] Support getting model from the name defined in the model-index file. ( #1236 )
...
* [Feature] Support getting model from the name defined in the model-index file.
* Add unit tests.
* Prevent import `timm` if the `TIMMBackbone` is not used.
* Fix Windows CI.
* Move `init_model` to `mmcls.apis.hub`, and support pass nn.Module to all
model components.
* Fix requirements
* Rename `hub.py` to `model.py` and add unit tests.
2022-12-06 17:00:22 +08:00
df2f122daa
[Fix] Fix dict update in BeIT. ( #1234 )
...
* fix dict update
* remove breakpoint
* fix key error
* fix lint
* update
* update
2022-12-05 17:59:36 +08:00
d80ec5a4b8
[Refactor] Refactor BEiT backbone and support v1/v2 inference. ( #1144 )
...
* refactor beit backbone
* use LinearClsHead
* fix mean and std value
* fix lint
* support inference if beit-v2
* update encoder layer and init
* update
* add ut
* add prepare_relative_position_bias_table function
* add cls_token
* fix lint
* add pos_embed check
* update metafile and readme
* update weights link
* update link of weights
* update metafile
* update
* update docstrings
* update according to review
* rename readme
* update docstring
* fix lint
2022-11-29 12:56:33 +08:00
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
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
4fb44f8770
[Feature] EfficientNets NoisyStudent & L2. ( #1122 )
...
* add mvit 21k
* add mvit 21k
* add effnet noisy student
* Revert "add mvit 21k"
This reverts commit f51067c559
2022-11-21 16:57:13 +08:00
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
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
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
992d13e772
[Enhance] add deleting params info in swinv2. ( #1142 )
2022-11-14 17:07:21 +08:00
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
cf5879988d
[Feature] Support Activation Checkpointing for ConvNeXt. ( #1153 )
...
* Support Activation Checkpointing for ConvNeXt
* Add docstring.
Co-authored-by: mzr1996 <mzr1996@163.com>
2022-11-14 15:04:28 +08:00
542143cb41
[Feature] Add TIMM and HuggingFace wrappers to build classifiers from them directly. ( #1102 )
...
* [Feature] Add TIMM and HuggingFace wrappers to build classifiers from them directly.
* Support `with_cp` and add docstring.
* Add unit tests.
* Update CI.
* Update docs.
2022-11-10 14:56:19 +08:00
9eb6fc4368
[Feature] Add reduction for neck ( #978 )
...
* feat: add reduction for neck
* feat: add reduction for neck
* feat: add reduction for neck
* feat:add linear reduction neck
* feat: add reduction neck
* mod out of linearReduction as tuple
* fix typo
* fix unit tests
* fix unit tests
Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>
2022-11-04 15:44:37 +08:00
8cc1fdef52
[Enhancement] RepVGG for YOLOX-PAI for dev-1.x. ( #1126 )
2022-11-04 15:36:18 +08:00
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
9506241f73
[Feature] Add arcface head. ( #926 )
...
* feat: add arcface head
* feat: add arcface head
* update arcface
* refactor archface head
* update archface head
* update archface head
* use torch.cat instead of torch.hstack to fix ci
Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>
2022-11-02 17:45:33 +08:00
693596bc2f
[Feature] Add Base Retriever and Image2Image Retriever for retrieval tasks. ( #1055 )
...
* feat: add image retriever
* feat: add image retriever
* feat: add image retriever
* feat: add image retriever
* feat: add image retriever
* feat: add image retriever
* feat: add image retriever
* feat: add image retriever
* feat: add image retriever
* update retriever
* fix lint
* add hook unit test
* Use `register_buffer` to save prototype vectors and add a progress bar
during preparing prototype.
* update UTs
* update UTs
* fix typo
* modify the hook
Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>
Co-authored-by: mzr1996 <mzr1996@163.com>
2022-11-02 17:43:56 +08:00
b526f018db
[Fix] Fix broken inference api because of the modification in data
...
preprocessor.
2022-10-18 17:50:35 +08:00
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
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
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
2153a16dc5
[Docs] Fix some docstrings.
2022-10-10 11:17:48 +08:00
8c5d86a388
[Fix] Fix `loss_weight` in `LabelSmoothLoss`. ( #1058 )
2022-09-28 08:18:12 +08:00
51b7c754e7
[Fix] Fix the output position of Swin-Transformer. ( #947 )
...
* [Fix] Fix the output position of Swin-Transformer.
* Rename `downsample` argument to `do_downsample`.
2022-09-22 17:11:52 +08:00
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
f7191ca686
[Feature] Add ViT huge architecture. ( #1049 )
...
* [Feature]: Add ViT huge settings
* [Feature]: Add comments
2022-09-21 13:27:54 +08:00
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
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
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
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
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
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
2b88df4484
[Refactor] Refactor the data flow. ( #989 )
...
* [Refactor] Refactor the data flow.
* Add comments about data preprocessor.
* Fix after mmengine folder structure refactoring.
2022-08-26 10:40:43 +08:00
b7d0d521eb
[Refactor] Use `mmengine` instead of `mmcv` and refactor some transforms. ( #986 )
...
* [Refactor] Refactor the rest data transforms and fix some docstring.
* Use `mmengine` instead of `mmcv`
* Refactor KFold dataset tools
* Fix docstring according to comments
2022-08-24 15:59:02 +08:00
5665b8349a
[Refactor] Refactor import dependency. ( #977 )
...
Co-authored-by: mzr1996 <mzr1996@163.com>
2022-08-22 15:17:33 +08:00
20f9ace5c5
[CI] Add Circle CI for mmcls 1.x. ( #970 )
...
* [CI] Add Circle CI for mmcls 1.x
* Fix circle-ci config
* Use `torch.cat` instead of `torch.hstack` to compat with PyTorch 1.6
* Compat the behavior of LongTensor in PyTorch 1.6
* Avoid random behavior in the unit test of Lighting
* Fix cuda ci
* Remove github workflow temporarily.
2022-08-22 15:02:08 +08:00
e4252d6848
[Feature]: Support BEiT Transformer layer. ( #919 )
...
* [Feature]: Add BEiT-style transformer encoder layer
* [Feature]: Add average token
* [Fix]: Fix lint
* [Fix]: Refactor CAE config
* [Fix]: Change cv2 backend to pillow backend
* [Fix]: Fix MAE and CAE reshape bug
* [Feature]: Add freeze vit layers
* [Feature]: Add mc
* [Fix]: Fix lint
* [Fix]: Fix dataset bug
* [Fix]: Delete cae selfsup config
* [Fix]: docstring
* [Refactor]: Add init_values to layer_scalue_init_value
* [Fix]: Refine the docstring of avg_token
* [Fix]: Call super init weight in beit attention
* [Fix]: remove mc
* [Fix]: Fix docstring
* [Fix]: Fix docstring
* [Fix]: Fix lint
* [Fix]: Fix init_value bug and change the logic of outputting cls token
* [Fix]: Fix docstring
2022-08-17 00:07:06 +08:00
43e60ad5a6
[Improve] Rename `mmcls.data` to `mmcls.structures`. ( #941 )
2022-07-29 14:18:13 +08:00
9118b97239
refactor evaluation
2022-07-18 11:11:13 +08:00
6ed3860ea6
refactor UTs
2022-07-18 11:11:13 +08:00
0f30c392a3
from core to engine
2022-07-18 11:11:13 +08:00
24bcf069f8
[Refactor] Refactor dev scripts
2022-07-18 11:11:13 +08:00
e9342d9e4c
Add multi_label heads
2022-07-18 11:11:13 +08:00
Rongjie Li
Wangbo Zhao(黑色枷锁)
Songyang Zhang
Ma Zerun
takuoko
Yixiao Fang
Ezra-Yu
Hubert
Jiahao Wang
Hakjin Lee
zzc98
whcao
Yuan Liu
Ezra-Yu