mmpretrain

Commit Graph

Author	SHA1	Message	Date
Ma Zerun	833152b1f4	[Docs] Update README in configs according to OpenMMLab standard. (#672 ) * Update README according to OpenMMLab standard. * Update model zoo docs generation. * Revert modification for paperlink	2022-01-26 18:26:01 +08:00
Ma Zerun	159b38d276	[Reproduction] Reproduce training results of T2T-ViT (#610 ) * Add cosine cool down lr updater * Use ema hook * Update decay mult * Update configs. * Update T2T-ViT readme and format all readme * Update swin readme * Update tnt readme * Add docstring for `CosineAnnealingCooldownLrUpdaterHook`. * Update t2t readme and metafile	2021-12-28 15:09:40 +08:00
Zhiliang Peng	18f6bb0b10	[Feature] Implement the conformer backbone. (#494 ) * implement the conformer * format code style * format code style * reuse the TransformerEncoderLayer in the vision_transformer.py * Modify variable name * delete unused params * Remove warning info in Conformer head since it already exists in Conformer. * Rename some variables * Add unit tests * Use `getattr` instead of `get_submodule`. * Remove some useless layers * Refactor conformer and add configs * Update configs and add metafile. * Fix unit tests * Update README Co-authored-by: mzr1996 <mzr1996@163.com>	2021-12-07 14:00:17 +08:00

Author

SHA1

Message

Date

Ma Zerun

833152b1f4

[Docs] Update README in configs according to OpenMMLab standard. (#672 )

* Update README according to OpenMMLab standard.

* Update model zoo docs generation.

* Revert modification for paperlink

2022-01-26 18:26:01 +08:00

Ma Zerun

159b38d276

[Reproduction] Reproduce training results of T2T-ViT (#610 )

* Add cosine cool down lr updater

* Use ema hook

* Update decay mult

* Update configs.

* Update T2T-ViT readme and format all readme

* Update swin readme

* Update tnt readme

* Add docstring for `CosineAnnealingCooldownLrUpdaterHook`.

* Update t2t readme and metafile

2021-12-28 15:09:40 +08:00

Zhiliang Peng

18f6bb0b10

[Feature] Implement the conformer backbone. (#494 )

* implement the conformer

* format code style

* format code style

* reuse the TransformerEncoderLayer in the vision_transformer.py

* Modify variable name

* delete unused params

* Remove warning info in Conformer head since it already exists in
Conformer.

* Rename some variables

* Add unit tests

* Use `getattr` instead of `get_submodule`.

* Remove some useless layers

* Refactor conformer and add configs

* Update configs and add metafile.

* Fix unit tests

* Update README

Co-authored-by: mzr1996 <mzr1996@163.com>

2021-12-07 14:00:17 +08:00

3 Commits (a19c28fe9538fd1c06dbc08c4dc7ad59d67d4217)