mirrors
/
mmclassification
mirror of https://github.com/open-mmlab/mmclassification.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
779 Commits
8 Branches
41 Tags
36 MiB
Commit Graph

22 Commits (8352951f3de379d7e4b21d85e42da7020ff4c0c1)

Author SHA1 Message Date
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
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
Yixiao Fang 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
Yuan Liu f7191ca686
[Feature] Add ViT huge architecture. (#1049) 
* [Feature]: Add ViT huge settings

* [Feature]: Add comments
 2022-09-21 13:27:54 +08:00
Ma Zerun 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
Yuan Liu 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
mzr1996 24bcf069f8 [Refactor] Refactor dev scripts 2022-07-18 11:11:13 +08:00
yingfhu de002e455f [Refactor] Use `MMLogger` from MMEngine in `get_logger` and `print_log`. 2022-07-18 10:53:27 +08:00
Ezra-Yu 088d5b5add [Refactor] Inherit all registries from MMEngine and use inherited registries. 2022-07-18 10:53:27 +08:00
Ma Zerun c708770b42
[Enhance] Support dynamic input shape for ViT-based algorithms. (#706) 
* Move `resize_pos_embed` to `mmcls.models.utils`

* Refactor Vision Transformer

* Refactor DeiT

* Refactor MLP-Mixer

* Refactor Swin-Transformer

* Remove `indexing` arg

* Support dynamic inputs for t2t_vit

* Add copyright

* Fix bugs in swin transformer

* Add `pad_small_maps` option

* Update swin transformer

* Handle `attn_mask` in checkpoints of swin

* Imporve by comments
 2022-03-03 13:10:12 +08:00
Ma Zerun f9a2b04cee
[Feature] Add DeiT backbone and checkpoints. (#576) 
* Support DeiT backbone.

* Use hook to automatically resize pos embed

* Update ViT training setting

* Add deit configs and update docs

* Fix vit arch assertion

* Remove useless init function

* Add unit tests.

* Fix resize_pos_embed for DeiT

* Improve according to comments.
 2021-12-15 22:44:57 +08:00
Ma Zerun f2c1c57398
[Docs] Fix docs build dependency. (#584) 
* Fix docs.

* Add MMHuman3D
 2021-12-07 11:16:33 +08:00
Ma Zerun 2932f9d8a3
[Refactor] Refator ViT (Continue #295) (#395) 
* [Squash] Refator ViT (from #295)

* Use base variable to simplify auto_aug setting

* Use common PatchEmbed, remove HybridEmbed and refactor ViT init
structure.

* Add `output_cls_token` option and change the output format of ViT and
input format of ViT head.

* Update unit tests and add test for `output_cls_token`.

* Support out_indices.

* Standardize config files

* Support resize position embedding.

* Add readme file of vit

* Rename config file

* Improve docs about ViT.

* Update docstring

* Use local version `MultiheadAttention` instead of mmcv version.

* Fix MultiheadAttention

* Support `qk_scale` argument in `MultiheadAttention`

* Improve docs and change `layer_cfg` to `layer_cfgs` and support
sequence.

* Use init_cfg to init Linear layer in VisionTransformerHead

* update metafile

* Update checkpoints and configs

* Imporve docstring.

* Update README

* Revert GAP modification.
 2021-10-18 16:07:00 +08:00
Ma Zerun 2e6c7cf87d
[Docs] Add code-spell pre-commit hook and fix a large mount of typos. (#470) 
* Add code spell check hook

* Add codespell config

* Fix a lot of typos.

* Add formating.py to keep compatibility.
 2021-10-13 14:33:07 +08:00
Ma Zerun f9eb9b409b
[Docs] Add Copyright information. (#413) 2021-08-17 19:52:42 +08:00
Ma Zerun 899047a3b3
Fix duplicate `init_weights` call in ViT init function. (#373) 2021-07-26 05:33:11 -04:00
Ma Zerun d04ebc1eb5
[Docs] Add API Reference in the docs (#342) 
* Add API inference in the docs and fix readthedocs config.

* Replace some relative link in docs.

* Format docstring for reStructuredText syntax.

* Fix vit paper link

* Fix docstring of `show_results` function in `BaseClassifier`.
 2021-07-14 15:06:50 +08:00
whcao 5e1a02103f
[Feature]Delete comments (#298) 
* add mytrain.py for test

* test before layers

* test attr in layers

* test classifier

* delete mytrain.py

* delete comments
 2021-06-12 21:45:22 +08:00
Miao Zheng 4ca21c7d03
[WIP] Refactoring weights initialization (#270) 
* [WIP] Refactoring weights initialization

* fix lint and constant init cfg

* fix pretrained bug

* fix typo

* fix isort

* revise model utils
 2021-06-10 10:54:34 +08:00
whcao 16947f1239
[Bug]Fix weight decay (#227) 
* add imagenet bs 4096

* add vit_base_patch16_224_finetune

* add vit_base_patch16_224_pretrain

* add vit_base_patch16_384_finetune

* add vit_base_patch16_384_finetune

* add vit_b_p16_224_finetune_imagenet

* add vit_b_p16_224_pretrain_imagenet

* add vit_b_p16_384_finetune_imagenet

* add vit

* add vit

* add vit head

* vit unitest

* keep up with ClsHead

* test vit

* add flag to determiine whether to calculate acc during training

* Changes related to mmcv1.3.0

* change checkpoint saving interval to 10

* add label smooth

* default_runtime.py recovery

* docformatter

* docformatter

* delete 2 lines of comments

* delete configs/_base_/schedules/imagenet_bs4096.py

* add configs/_base_/schedules/imagenet_bs2048_AdamW.py

* rename imagenet_bs4096.py to imagenet_bs2048_AdamW.py

* add AutoAugment

* fix weight decay in vit

* change eval interval to 10

* add mytrain.py for test

* test before layers

* test attr in layers

* test classifier

* delete mytrain.py

* delete @torch.jit.ignore

* change eval interval back to 1

* add some comments to imagenet_bs2048_AdamW

* add some comments
 2021-04-28 17:16:43 +08:00
whcao 31a6a362ba
Add some vit configs (#217) 
* add vit_base_patch32_384_finetune.py

* add vit_base_patch32_384_finetune_imagenet.py to vision_transformer

* add vit_large_patch16_384_finetune.py to models

* add vit_large_patch16_384_finetune_imagenet.py to vision_transformer

* add vit_large_patch32_384_finetune to models

* add vit_large_patch32_384_finetune_imagenet to vision_transformer

* add vit_large_patch16_224_finetune.py to models

* add vit_large_patch16_224_finetune_imagenet.py to vision_transformer

* delete some useless comments
 2021-04-20 11:32:20 +08:00
whcao affb39fe07
[Feature]Add Vit (#214) 
* add imagenet bs 4096

* add vit_base_patch16_224_finetune

* add vit_base_patch16_224_pretrain

* add vit_base_patch16_384_finetune

* add vit_base_patch16_384_finetune

* add vit_b_p16_224_finetune_imagenet

* add vit_b_p16_224_pretrain_imagenet

* add vit_b_p16_384_finetune_imagenet

* add vit

* add vit

* add vit head

* vit unitest

* keep up with ClsHead

* test vit

* add flag to determiine whether to calculate acc during training

* Changes related to mmcv1.3.0

* change checkpoint saving interval to 10

* add label smooth

* default_runtime.py recovery

* docformatter

* docformatter

* delete 2 lines of comments

* delete configs/_base_/schedules/imagenet_bs4096.py

* add configs/_base_/schedules/imagenet_bs2048_AdamW.py

* rename imagenet_bs4096.py to imagenet_bs2048_AdamW.py

* add helpers.py

* test vit hybrid backbone

* fix HybridEmbed

* use to_2tuple instead
 2021-04-16 19:22:41 +08:00