mmsegmentation/mmseg/models
谢昕辰 2825efe378
[Feature] add DPT head (#605)
* add DPT head

* [fix] fix init error

* use mmcv function

* delete code

* remove transpose clas

* support NLC output shape

* Delete post_process_layer.py

* add unittest and docstring

* rename variables

* fix project error and add unittest

* match dpt weights

* add configs

* fix vit pos_embed bug and dpt feature fusion bug

* match vit output

* fix gelu

* minor change

* update unitest

* fix configs error

* inference test

* remove auxilary

* use local pretrain

* update training results

* update yml

* update fps and memory test

* update doc

* update readme

* add yml

* update doc

* remove with_cp

* update config

* update docstring

* remove dpt-l

* add init_cfg and modify readme.md

* Update dpt_vit-b16.py

* zh-n README

* use constructor instead of build function

* prevent tensor being modified by ConvModule

* fix unittest

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-08-30 16:53:05 +08:00
..
backbones [Fix] The interface multiscale_output is defined but not used (#830) 2021-08-27 18:53:55 +08:00
decode_heads [Feature] add DPT head (#605) 2021-08-30 16:53:05 +08:00
losses [Dcos] Add header for files (#796) 2021-08-16 23:16:55 -07:00
necks [Dcos] Add header for files (#796) 2021-08-16 23:16:55 -07:00
segmentors [Dcos] Add header for files (#796) 2021-08-16 23:16:55 -07:00
utils [Enhancement] Delete convert function and add instruction to ViT/Swin README.md (#791) 2021-08-25 15:00:41 -07:00
__init__.py [Dcos] Add header for files (#796) 2021-08-16 23:16:55 -07:00
builder.py [Dcos] Add header for files (#796) 2021-08-16 23:16:55 -07:00