谢昕辰 b379b5a5b3 support transformer backbone (#465) ...

* vit backbone

* fix lint

* add docstrings and fix pretrained pos_embed dim not match prob

* add unittest for vit

* fix lint

* add vit based fcn configs

* fix import error

* support multiple resolution input images

* upsample pos_embed at init_weights

* support resize pos_embed at evaluation

* fix training errors

* add more unitest code for vit backbone

* unitest for uncovered code

* add norm_eval unittest

* refactor _pos_embeding

* minor change

* change var name

* rafactor init_weight

* load weights after resize

* ignore 'module' in pretrain checkpoint

* add with_cp

* add with_cp

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>

2021-04-21 20:19:55 -07:00

..

__init__.py

support transformer backbone (#465)

2021-04-21 20:19:55 -07:00

cgnet.py

Fix typo: upsampe_cfg -> upsample_cfg (#449)

2021-03-30 09:51:38 -07:00

fast_scnn.py

[Enhance] Refactor inverted residual (#164)

2020-09-28 00:33:51 +08:00

hrnet.py

Fix typo: upsampe_cfg -> upsample_cfg (#449)

2021-03-30 09:51:38 -07:00

mobilenet_v2.py

[Enhance] Refactor inverted residual (#164)

2020-09-28 00:33:51 +08:00

mobilenet_v3.py

Fix typo: upsampe_cfg -> upsample_cfg (#449)

2021-03-30 09:51:38 -07:00

resnest.py

Support ResNeSt backbone (#47)

2020-08-17 00:54:01 +08:00

resnet.py

Add Colab Tutorial (#7)

2020-07-10 16:55:47 +08:00

resnext.py

init commit

2020-07-10 02:39:01 +08:00

unet.py

Save base_channels for UNet (#450)

2021-03-30 09:52:08 -07:00

vit.py

support transformer backbone (#465)

2021-04-21 20:19:55 -07:00