Commit Graph

12 Commits (3bbdd6dc4a1ad98d4e4dd4e85ae76e5300be0142)

Author SHA1 Message Date
xiexinch 26a0b4814b add _delete_=True to optim wrapper 2022-07-06 17:26:52 +08:00
xiexinch 28a3d89b7a Update pre-commit yaml and md2yml.py 2022-07-05 15:58:48 +08:00
MengzhangLI 2c4bcbd7c6 [Fix] Remove _delete_=True in optimizer 2022-06-20 17:53:36 +08:00
zhengmiao b23982d1b3 [Refactory] Refactory BaseSegmentor based BaseModel 2022-06-19 06:32:09 +00:00
limengzhang.vendor 11493c4851 [Fix] Fix no LoadAnnotations in testpipeline 2022-06-13 05:33:34 +00:00
limengzhang.vendor 34711422ac [Fix] Fix batch size of val_dataloader to 1. 2022-06-12 09:10:26 +00:00
linfangjian.vendor dd9c411335 [Refactor] Refactor decode_head and segmentors and add preprocess_cfg 2022-06-10 14:02:40 +00:00
limengzhang.vendor fcb9cb4571 [Refactor] Refactor lr_config 2022-06-08 09:25:00 +00:00
limengzhang.vendor c84a58b7b5 [Refactor] Refacor default_hooks and train & val & test loops in configs 2022-06-08 06:28:35 +00:00
limengzhang.vendor 5b9c29f992 [Refactor] Refactor Dataset and its Transform Config files 2022-05-31 14:28:42 +00:00
MengzhangLI 799486e124 [Fix] Fix main line link in MAE README.md (#1556) 2022-05-05 17:49:38 +08:00
Yuan Liu 43b8a1d8dc [Feature]: Add MAE (#1307)
* [Fix]: Fix lint

* [WIP]: Add mae seg config

* [Feature]: Add MAE seg

* [Fix]: Fix mae dataset img scale bug

* [Fix]: Fix lint

* [Feature]: Change mae config to mae_segmentation's config

* [Feature]: Add interpolate pe when loading

* [Fix]: Fix pos_embed not used bug

* [Fix]: Fix lint

* [Fix]: Init rel pos embed with zeros

* [Fix]: Fix lint

* [Fix]: Change the type name of backbone to MAE

* [Fix]: Delete ade20k_512x512.py

* [Fix]: Use mmseg provided ade20k.py

* [Fix]: Change 1 sample per gpu to 2 samples per gpu

* [Fix]: Fix conflict

* [Refactor]: Use the TransformerEncoderLayer of  BEiT

* [Feature]: Add UT

* [Fix]: Change the default value of qv bias to False

* [Fix]: Initialize relative pos table with zeros

* [Fix]: Delete redundant code in mae

* [Fix]: Fix lint

* [Fix]: Rename qkv_bias to qv_bias

* [Fix]: Add docstring to weight_init of MAEAttention

* [Refactor]: Delete qv_bias param

* [Fix]: Add reference to fix_init_weight

* [Fix]: Fix lint

* [Fix]: Delete extra crop size

* [Refactor]: Rename mae

* [Fix]: Set bias to True

* [Fix]: Delete redundant params

* [Fix]: Fix lint

* [Fix]: Fix UT

* [Fix]: Add resize abs pos embed

* [Fix]: Fix UT

* [Refactor]: Use build layer

* [Fix]: Add licsense and fix docstring

* [Fix]: Fix docstring

* [Feature]: Add README metafile

* [Fix]: Change 640 to 512

* [Fix]: Fix README

* fix readme of MAE

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-04-28 00:54:20 +08:00