92a87a8848
pre-commit check
2023-07-26 17:55:50 +04:00
b6117a4c18
using to modify cfg
2023-07-26 16:59:43 +04:00
4e57d84f68
modify data_root
2023-07-26 11:13:21 +04:00
690dca403c
add vit_base_p16_4xb544_ipu_in1k.py
2023-07-26 01:07:08 +04:00
49dba8cfe7
finish vit_base_p16_32xb128_mae_in1k.py
2023-07-26 00:47:02 +04:00
7d8aa8f782
finish 4 vit_large*.py
2023-07-26 00:33:55 +04:00
b22e3eb031
finish vit_base_p32_64xb64_in1k.py and 384px
2023-07-26 00:21:57 +04:00
90e1911ed8
finish vit_base_p16_64xb64_in1k_384px.py
2023-07-26 00:09:25 +04:00
ba09759d50
rename
2023-07-25 20:40:26 +04:00
c936d65df3
renew vit-base-p16_64xb64_in1k.py
2023-07-25 20:39:59 +04:00
55e2f02abe
add old config
2023-07-25 20:29:05 +04:00
5e672c1950
add old config
2023-07-25 20:27:53 +04:00
fcc24bc54c
add old config
2023-07-25 20:18:02 +04:00
2b8d8eecb2
[Fix] Fix the issue #1711 "GaussianBlur doesn't work" ( #1722 )
...
* Fix issue 1711. GaussianBlur.
* Fix UT
---------
Co-authored-by: mzr1996 <mzr1996@163.com>
2023-07-25 11:25:32 +08:00
60d780f99e
Fix docs
2023-07-20 10:21:15 +08:00
ae7a7b7560
Bump version to 1.0.0 ( #1686 )
...
* bump version to 1.0.0
* update
* update
* fix lint
* update
* update
* update changelog
* update
2023-07-05 11:51:12 +08:00
0d80ab4650
[Docs] fix doc typos ( #1629 )
...
* fix doc typos
* fix link
---------
Co-authored-by: fangyixiao18 <fangyx18@hotmail.com>
2023-07-05 11:25:55 +08:00
8eaf8090e6
docs(advances_guides.modules): Correcting a typo ( #1644 )
...
"涵盖了模型直接绝大多数的差异" -> "涵盖了模型之间绝大多数的差异"
English edition:
"backbone: usually a feature extraction network that records the major differences between models, e.g., ResNet, MobileNet."
2023-07-05 11:14:46 +08:00
130751185c
[DOC] Fix typo in docs/*/migration.md ( #1671 )
...
* Update migration.md
* Update migration.md
2023-07-05 11:12:25 +08:00
7cbfb36c14
[Refactor] Fix spelling ( #1681 )
...
* [Refactor] Fix spelling
* [Refactor] Fix spelling
* [Refactor] Fix spelling
* [Refactor] Fix spelling
2023-07-05 11:07:43 +08:00
feb0814b2f
[Feature] Transfer shape-bias tool from mmselfsup ( #1658 )
...
* Transfer shape-bias tool from mmselfsup
* run shape-bias successfully, add CN docs
* fix unit test bug
* add shape_bias to index.rst in docs
* modified mistakes in shape-bias docs
2023-07-03 11:39:23 +08:00
00030e3f7d
[Fix] refactor _prepare_pos_embed in ViT to fix bug in loading old checkpoint ( #1679 )
2023-07-03 11:36:44 +08:00
59c077746f
[Feat] Download dataset by using MIM&OpenDataLab ( #1630 )
...
* add dataset.index
* update preprocess shell
* update shell
* update docs
* update docs
2023-06-30 13:55:13 +08:00
8afad77a35
[Enhance] Update fsdp vit-huge and vit-large config ( #1675 )
...
* Update fsdp vit-huge and vit-large config
* Update fsdp vit-huge and vit-large config
* rename
2023-06-30 11:15:18 +08:00
658db80089
[Enhancement] Support deepspeed with flexible runner ( #1673 )
...
* [Feature] Support deepspeed with flexible runner
* [Fix] Reformat with yapf
* [Refacor] Rename configs
* [Fix] Reformat with yapf
* [Refactor] Remove unused keys
* [Refactor] Change the _base_ path
* [Refactor] Reformat
2023-06-29 10:16:27 +08:00
68758db7a8
[Fix] freeze pre norm in vision transformer. ( #1672 )
2023-06-28 17:00:27 +08:00
10685fc81c
[Refactor] Replace if '_base_' with read_base(). ( #1665 )
2023-06-28 16:57:18 +08:00
70ff2abbf7
[Refactor] Refactor _prepare_pos_embed in ViT ( #1656 )
...
* deal with cls_token
* Update implement
---------
Co-authored-by: mzr1996 <mzr1996@163.com>
2023-06-20 17:37:08 +08:00
d4a6dfa00a
Add benchmark options ( #1654 )
...
* update dev_scripts
* update metafile
* update multimodal floating range
* fix lint
* update
* update
* fix lint
* Update metric map
---------
Co-authored-by: mzr1996 <mzr1996@163.com>
2023-06-20 14:18:57 +08:00
7d850dfadd
[Improve] Update Otter and LLaVA docs and config. ( #1653 )
2023-06-19 20:16:13 +08:00
dbef2b41c6
[Fix] Align COCO dataset format.
2023-06-19 07:24:07 +00:00
d6056af2b8
[Fix][New_config] Fix demo bug ( #1647 )
...
* Fix demo
* Update implement
---------
Co-authored-by: mzr1996 <mzr1996@163.com>
2023-06-19 15:15:28 +08:00
6d7fe91a98
[Feature] Support Flickr30k Retrieval dataset ( #1625 )
...
* format
* remove abs path
* init add flickr30k caption
* remove abs dir
* update blip readme
* add convert sscripts
* minor
* minor
2023-06-19 15:15:03 +08:00
a1cfe888e2
[Feature] Support SparK. ( #1531 )
...
* add spark configs
* fix configs
* remove repeat aug
* add module codes
* support lr layer decay of resnet
* update
* fix lint
* add metafile and readme
* fix lint
* add models and logs
* refactor codes
* fix lint
* update model rst
* update name
* add docstring
* add ut
* fix lint
---------
Co-authored-by: Ma Zerun <mzr1996@163.com>
2023-06-19 11:27:50 +08:00
bfd49b0d52
[Feature] Support LLaVA ( #1652 )
2023-06-17 16:05:52 +08:00
e69bace03f
[Feature] Support otter ( #1651 )
...
* [Feature] Support Otter
* Update docs
2023-06-17 16:03:21 +08:00
9d3fc43073
[Feature] Support MiniGPT-4 ( #1642 )
...
* support inference of MiniGPT-4
* refine codes
* update metafile, readme and docs
* fix typo
* fix lint
* add ckpt load hook
2023-06-16 22:50:34 +08:00
a673b048a5
[Feature] Add support for VizWiz dataset. ( #1636 )
...
* add vizwiz
* update dataset
* [Fix] Build img_path in data_sample.
* Fix isort.
---------
Co-authored-by: ZhangYuanhan-AI <yuanhan002@ntu.edu.sg>
2023-06-16 17:16:17 +08:00
aac398a83f
[Feature] Support new configs. ( #1639 )
...
* [Feature] Support new configs (#1638 )
* add new config of mae and simclr
* update
* update setup.cfg
* update eva
* update
* update new config
* Add new config
* remove __init__.py
* 1. remove ; 2. remove mmpretrain/configs/_base_/models/convnext
* remove model_wrapper_cfg and add out type
* Add comment for setting default_scope to NOne
* update if '_base_' order
* update
* revert changes
---------
Co-authored-by: fangyixiao18 <fangyx18@hotmail.com>
* Add warn at the head of new config files
---------
Co-authored-by: Mashiro <57566630+HAOCHENYE@users.noreply.github.com>
Co-authored-by: mzr1996 <mzr1996@163.com>
2023-06-16 16:54:45 +08:00
93e0f107c4
[Fix] Fix bug loading IN1k dataset. ( #1641 )
2023-06-16 15:35:27 +08:00
7581b76233
[Feature] Add support for vsr dataset ( #1634 )
...
* add VSR dataset
* [Fix] Modify example and load gt_answer as string.
---------
Co-authored-by: ZhangYuanhan-AI <yuanhan002@ntu.edu.sg>
2023-06-15 19:17:02 +08:00
53648baca5
[Fix] fix sam bug ( #1633 )
2023-06-15 10:10:51 +08:00
3eaf719a64
[Feature] Add InternImage Classification project ( #1569 )
...
* [Feature] add internimage project
* [Feature] add internimage project
* update license
* [Feature] add internimage project
* [Feature] add internimage project
* [Feature] add internimage project
* [Feature] add internimage project
* [Feature] add internimage project
* [Feature] add internimage project
* update license
* [Feature] add internimage project
* [Feature] add internimage project
* [Feature] add internimage project
* [Feature] add internimage project
* update internimage configs
* support internimage project
* support internimage project
* support internimage project
* internimage
2023-06-13 19:11:54 +08:00
8e9e880601
[Feat] Add download link for coco caption and retrieval annotations. ( #1607 )
...
* [Feat] Add download link for coco caption and retrieval annotations.
* minor fix
2023-06-13 10:29:54 +08:00
bb415b91be
[Feature] Support OCR-VQA dataset ( #1621 )
...
* support ocrvqa dataset
* minor
* remove abs path
* refine README
2023-06-13 10:28:45 +08:00
dbfb84ccbd
[Feature] Support OK-VQA dataset ( #1615 )
...
* add okvqa
* refine README
2023-06-08 16:57:18 +08:00
057d7c6d6a
[BUG] Fixed circular import error for new transform ( #1609 )
2023-06-08 14:00:41 +08:00
bddbc085fc
[Feature]: Add image_only param ( #1613 )
...
* [Feature]: Add image_only param
* [Feature]: Use image_only
2023-06-06 12:50:42 +08:00
3a277ee9e6
[Feature] support TextVQA dataset ( #1596 )
...
* [Support] Suport TextVQA dataset
* add folder structure
* fix readme
2023-06-02 11:50:38 +08:00
bc3c4a35ee
[Refactor] Support to use "split" to specify training set/validation set in the ImageNet dataset ( #1535 )
...
* [Feature]: Add caption
* [Feature]: Update scienceqa
* [CI] Add test mim CI. (#879 )
* refactor imagenet dataset
* refactor imagenet dataset
* refactor imagenet dataset
* update imagenet21k
* update configs
* update mnist
* update dataset_prepare.md
* fix sun397 url and update user_guides/dataset_prepare.md
* update dataset_prepare.md
* fix sun397 dataset
* fix sun397
* update chinese dataset_prepare.md
* update dataset_prepare.md
* [Refactor] update voc dataset
* [Refactor] update voc dataset
* refactor imagenet
* refactor imagenet
* use mmengine.fileio
---------
Co-authored-by: liuyuan <3463423099@qq.com>
Co-authored-by: Ma Zerun <mzr1996@163.com>
Co-authored-by: Ezra-Yu <18586273+Ezra-Yu@users.noreply.github.com>
2023-06-02 11:03:18 +08:00
zeyuanyin
liyl
mzr1996
Yixiao Fang
liweiwp
Minato
Lamply
fanqiNO1
Wang Xiang
Peng Lu
Ezra-Yu
Mashiro
Wangbo Zhao(黑色枷锁)
Yiqin Wang 王逸钦
Yike Yuan
zzc98
Hubert
Mr.Li
Yuan Liu