a4c219e05d
Bump version to v1.1.0
2023-10-12 17:20:22 +08:00
d35c778a6f
Merge remote-tracking branch 'origin/main' into dev
2023-10-12 17:19:27 +08:00
c0766519b1
[Feature] Add minigpt4 gradio demo and training script. ( #1758 )
...
* Add minigpt4 gradio demo
* update minigpt4 demo
* update minigpt4 demo (inference with float16)
* update minigpt4 and some dependent files
* add minigpt4 dataset for training
* add training script for minigpt4
* restore files deleted by mistake
* fix an error
* remove useless modification
* provide command line arguments for minigpt4 gradio demo and update some comments
* update code
* Update minigpt-4 readme
---------
Co-authored-by: mzr1996 <mzr1996@163.com>
2023-10-12 10:36:17 +08:00
4849324629
Update train.py to compat with new config
2023-10-11 11:13:40 +08:00
b0a792eb08
Update OFA to compat with latest huggingface.
2023-10-11 11:13:40 +08:00
3bcf7e2d6e
[CodeCamp2023-341] 多模态数据集文档补充-COCO Retrieval
2023-10-08 15:46:47 +08:00
06bb586eb7
[Fix] Fix pipeline bug in image retrieval inferencer
2023-10-08 15:44:37 +08:00
5c71de6b8e
Merge pull request #1780 from timerring/dev
...
[CodeCamp2023-338] New Version of config Adapting Swin Transformer Algorithm
2023-09-08 16:01:38 +08:00
7734f073e4
set arch etc
2023-09-06 23:56:03 +08:00
b0b4422736
fix a redundant
2023-09-05 22:22:43 +08:00
9b75ce0aa4
only keep one file to set swin transformer v2 model config
2023-09-05 22:16:07 +08:00
f4d372ba7d
only keep one file to set swin transformer model config
2023-09-05 21:26:43 +08:00
ed3b7f8ae6
format all file names
2023-09-05 16:00:29 +08:00
ddc6d0b121
Merge remote-tracking branch 'upstream/dev' into dev
2023-09-05 15:23:21 +08:00
da1da48eb6
[Enhance] Add iTPN Supports for Non-three channel image ( #1735 )
...
* Add channel argments to mae_head
When trying iTPN pretrain, it only supports images with 3 channels. One of the restrictions is from MAEHead.
* Transfer other argments from iTPNHiViT to HiViT
The HiViT supports specifying channels, but the iTPNHiViT class can't pass channel argments to it. This is one of the reasons that iTPNHiViT implementation only support images with 3 channels.
* Update itpn.py
Fix hint problem
2023-09-04 13:11:16 +08:00
bb59c9ad82
[Feature] Implement of Zero-Shot CLIP Classifier ( #1737 )
...
* zero-shot CLIP
* modify zero-shot clip config
* add in1k_sub_prompt(8 prompts) for improvement
* add some annotations doc
* clip base class & clip_zs sub-class
* some modifications of details after review
* convert into and use mmpretrain-vit
* modify names of some files and directories
2023-09-04 10:30:28 +08:00
845b462190
[CodeCamp2023-340] New Version of config Adapting MobileNet Algorithm ( #1774 )
...
* add new config adapting MobileNetV2,V3
* add base model config for mobile net v3, modified all training configs of mobile net v3 inherit from the base model config
* removed directory _base_/models/mobilenet_v3
2023-09-01 17:54:18 +08:00
634852ad61
[CodeCamp2023-338] New Version of config Adapting Swin Transformer Algorithm
2023-08-31 18:15:47 +08:00
e1675e893e
[Docs] Update QRcode ( #1778 )
...
* Add miaomiao_qrcode.jpg
* Update qrcode
2023-08-30 19:47:21 +08:00
d2ccc44a2c
[CodeCamp2023-584]Support DINO self-supervised learning in project ( #1756 )
...
* feat: impelemt DINO
* chore: delete debug code
* chore: impplement pre-commit
* fix: fix imported package
* chore: pre-commit check
2023-08-23 10:45:18 +08:00
853f0c6bca
[DOC] Update datset download score from opendatalab to openXlab ( #1765 )
...
* update opendatalab to openXlab
* update dataset-index
---------
Co-authored-by: fangyixiao18 <fangyx18@hotmail.com>
2023-08-22 11:29:42 +08:00
732b0f4c98
Merge pull request #1766 from mzr1996/bump-v1.0.2
...
Bump version to v1.0.2
2023-08-15 15:10:04 +08:00
b65a96a89c
Apply suggestions from code review
...
Co-authored-by: Yixiao Fang <36138628+fangyixiao18@users.noreply.github.com>
2023-08-15 14:43:21 +08:00
6bb0c8a987
Bump version to v1.0.2
2023-08-15 11:51:12 +08:00
bf62497e02
Merge remote-tracking branch 'origin/main' into dev
2023-08-15 11:37:22 +08:00
6474d6befa
[CodeCamp2023-336] New Version of `config` Adapting MAE Algorithm ( #1750 )
...
* fix typo MIMHIVIT to MAEHiViT
* fix typo MIMHiViT to MAEHiViT
* [CodeCamp2023-336] New version of config adapting MAE algorithm
* pre-commit check
* Revert soft-link modification
---------
Co-authored-by: mzr1996 <mzr1996@163.com>
2023-08-14 17:20:39 +08:00
1be28ea7c4
[CodeCamp2023-337] New Version of config Adapting ConvNeXt Algorithm ( #1760 )
...
* add configs\_base_\datasets\imagenet21k_bs128.py
* update convnext_base_32xb128_in1k_384px.py
* add convnext-base_32xb128_in1k.py
* add convnext-base_32xb128_in21k.py
* add convnext-large_64xb64_in1k-384px.py
* add convnext-large_64xb64_in1k.py
* add convnext-large_64xb64_in21k.py
* add convnext-small_32xb128_in1k-384px.py
* add convnext-small_32xb128_in1k.py
* add convnext-tiny_32xb128_in1k-384px.py
* add convnext-tiny_32xb128_in1k.py
* add convnext-xlarge_64xb64_in1k-384px.py
* add convnext-xlarge_64xb64_in1k.py
* add convnext-xlarge_64xb64_in21k.py
* pre-commit check
2023-08-14 15:25:59 +08:00
bff80d3c48
[CodeCamp2023-335]New version of config adapting BeitV2 Algorithm ( #1755 )
2023-08-14 15:04:42 +08:00
29d706248c
[Enhancement] Support training of BLIP2 ( #1700 )
...
* [Fix] Fix BEiT pre_norm
* [Enhancement] Support BLIP2 training
* [Fix] Fix quoted strings
* [Fix] Fix init_weights
* [Fix] Fix with_cls_token
* [Fix] Fix tokenizer
* [Fix] Fix quoted strings
* [Fix] Fix predict
* [Fix] Cancel changing BEiT
* [Fix] Add loading hook
* [Fix] Reformat with yapf
* [Fix] Fix prompt
* [Fix] Fix typo
2023-08-10 11:15:38 +08:00
fa53174fd9
[Feature]: Add MFF ( #1725 )
...
* [Feature]: Add MFF
* [Feature]: Add mff linear prob
* [Feature]: Add ft
* [Fix]: Update docstring
* [Feature]: Update out_indices
* [Feature]: Add prefix to ft
* [Feature]: Add README
* [Feature]: Update readme
* [Feature]: Update README
* [Feature]: Add metafile
* [Feature]: Update README
* [Fix]: Fix lint
* [Feature]: Add UT
* [Feature]: Update paper link
2023-08-08 16:01:07 +08:00
827a216155
[Fix] Fix typo MIMHIVIT to MAEHiViT ( #1749 )
...
* fix typo MIMHIVIT to MAEHiViT
* fix typo MIMHiViT to MAEHiViT
2023-08-08 15:38:18 +08:00
1dda91bf24
[CodeCamp2023-343] Update dataset_prepare.md ( #1732 )
...
* Update dataset_prepare.md
* Enhanced docstring for RefCOCO and updated datasets.rst
* fix ln
* update
---------
Co-authored-by: No-518 <wybang@gmail.com>
Co-authored-by: fangyixiao18 <fangyx18@hotmail.com>
2023-08-03 19:24:23 +08:00
2fb52eefdc
[CodeCamp2023-339] New Version of `config` Adapting Vision Transformer Algorithm ( #1727 )
...
* add old config
* add old config
* add old config
* renew vit-base-p16_64xb64_in1k.py
* rename
* finish vit_base_p16_64xb64_in1k_384px.py
* finish vit_base_p32_64xb64_in1k.py and 384px
* finish 4 vit_large*.py
* finish vit_base_p16_32xb128_mae_in1k.py
* add vit_base_p16_4xb544_ipu_in1k.py
* modify data_root
* using to modify cfg
* pre-commit check
* ignore ipu
* keep other files no change
* remove redefinition
* only keep vit_base_p16.py
* move init_cfg into model.update
2023-08-02 10:06:08 +08:00
340d187765
Support Infographic VQA dataset and ANLS metric. ( #1667 )
2023-08-01 16:22:34 +08:00
4f2f3752d9
Support IconQA dataset. ( #1670 )
2023-08-01 16:14:40 +08:00
5c71eba13d
Bump version to 1.0.1 ( #1731 )
...
* bump version to 1.0.1
* update changelog
* update readme
* Update changelog.md
* update requirements
---------
Co-authored-by: Ma Zerun <mzr1996@163.com>
2023-07-31 17:08:05 +08:00
58a2243d99
Merge branch 'main' into dev
2023-07-28 15:35:55 +08:00
1f99279657
[Fix] Fix dict update in minigpt4. ( #1709 )
2023-07-28 15:30:30 +08:00
0b96dcaa67
[Enhance] Add init_cfg with type='pretrained' to downstream tasks. ( #1717 )
2023-07-28 15:28:29 +08:00
b1cd05caf2
[Enhance] Set 'is_init' in some multimodal methods ( #1718 )
...
* update is_init of multimodal
* Update minigpt4.py
---------
Co-authored-by: Ma Zerun <mzr1996@163.com>
2023-07-28 15:28:07 +08:00
e7fc25cf64
[Fix] Fix nested predict for multi-task prediction. ( #1716 )
...
* fix: multi task predict
* change the loop
---------
Co-authored-by: Pierre Colle <piercus@gmail.com>
2023-07-28 13:44:12 +08:00
c5248b17b7
[Enhance] Adapt test cases on Ascend NPU. ( #1728 )
2023-07-28 13:39:38 +08:00
4d1dbafaa2
[Enhance] Add GPU Acceleration Apple silicon mac ( #1699 )
...
* Add GPU Acceleration Apple silicon mac
* lint fix
* Update launch.py
* Use to refactor the device selection.
* Update launch.py
---------
Co-authored-by: mzr1996 <mzr1996@163.com>
2023-07-26 17:51:00 +08:00
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
64c446d507
[Feature] Support LoRA. ( #1687 )
...
* [Feature] Support LoRA
* [Feature] Support LoRA
* [Fix] Fix bugs
* [Refactor] Add copyright
* [Fix] Fix bugs
* [Enhancement] Add
* [Fix] Fix bugs
* [Fix] Fix bugs
* [Fix] Fix bugs
* [Fix] Fix bugs
* [Fix] Fix bugs
* [Docs] Update docstring
* [Docs] Update docstring
* [Refactor] Reformat with yapf
* [Docs] Update docstring
* [Refactor] Docformat
* [Refactor] Fix double-quote-string
* [Fix] fix pytorch version
* [Fix] isort
* [Fix] isort
* [Enhancement] Extend forward
* [Enhancement] Extend test
* [Fix] Fix targets
* [Enhancement] Extend LoRA to frozen models
* [Fix] Fix spelling
* [Fix] Override __getattr__
* [Fix] Add init_cfg
* [Enhancement] Add example config
* [Fix] Fix init_cfg
* [Enhancement] Add merging script
* [Fix] Remove init_cfg
* [Fix] Change lora key
* [Fix] Fix merge scripts
* [Fix] Fix merge scripts
* [Docs] Add docs
* [Fix] fix
2023-07-24 11:30:57 +08:00
60d780f99e
Fix docs
2023-07-20 10:21:15 +08:00
569324b180
Just to correct a typo of 'target' ( #1655 )
2023-07-14 16:16:35 +08:00
db395d35b1
fix_freeze_without_cls_token_vit ( #1693 )
2023-07-14 15:43:19 +08:00
465b6bdeec
[Refactor] Fix spelling ( #1689 )
2023-07-13 15:38:58 +08:00
5c43d3ef42
[Refactor] BEiT refactor ( #1705 )
...
* [Refactor] BEiT refactor
* [Fix] Fix arch zoo
* [Fix] Fix arch zoo
* [Fix] Fix freeze stages
* [Fix] Fix freeze ln2
* [Fix] Fix freezing vit ln2
2023-07-11 15:49:41 +08:00
mzr1996
hmtbgc
飞飞
John
ZhangYiqin
Coobiw
DE009
zhengjie.xu
LALBJ
Ezra-Yu
mstwutao
AzulaFire
Am_mu
fanqiNO1
Yuan Liu
No-518
Zeyuan
Yike Yuan
Yixiao Fang
fangyixiao18
marouane amzil
Yinlei Sun
Nripesh Niketan
liyl
BBC
Fabien Merceron PRL