mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
mmsegmentation/mmseg/models/utils
History
sennnnn c27ef91942 Adjust vision transformer backbone architectures (#524) 
* Adjust vision transformer backbone architectures;

* Add DropPath, trunc_normal_ for VisionTransformer implementation;

* Add class token buring intermediate period and remove it during final period;

* Fix some parameters loss bug;

* * Store intermediate token features and impose no processes on them;

* Remove class token and reshape entire token feature from NLC to NCHW;

* Fix some doc error

* Add a arg for VisionTransformer backbone to control if input class token into transformer;

* Add stochastic depth decay rule for DropPath;

* * Fix output bug when input_cls_token=False;

* Add related unit test;

* * Add arg: out_indices to control model output;

* Add unit test for DropPath;

* Apply suggestions from code review

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
 		2021-04-30 10:37:47 -07:00
..
__init__.py Adjust vision transformer backbone architectures (#524) 2021-04-30 10:37:47 -07:00
drop.py Adjust vision transformer backbone architectures (#524) 2021-04-30 10:37:47 -07:00
inverted_residual.py Fix typo: upsampe_cfg -> upsample_cfg (#449) 2021-03-30 09:51:38 -07:00
make_divisible.py [New model] Support MobileNetV3 (#268) 2020-12-26 00:02:50 -08:00
res_layer.py Support ResNeSt backbone (#47) 2020-08-17 00:54:01 +08:00
se_layer.py Fix typo: upsampe_cfg -> upsample_cfg (#449) 2021-03-30 09:51:38 -07:00
self_attention_block.py init commit 2020-07-10 02:39:01 +08:00
up_conv_block.py Fix typo: upsampe_cfg -> upsample_cfg (#449) 2021-03-30 09:51:38 -07:00
weight_init.py Adjust vision transformer backbone architectures (#524) 2021-04-30 10:37:47 -07:00