mmsegmentation

mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00

History

sennnnn c01abb4f30 [Refactor] Using mmcv transformer bricks to refactor vit. (#571 )

* [Refactor] Using mmcv bricks to refactor vit

* Follow the vit code structure from mmclassification

* Add MMCV install into CI system.

* Add  to 'Install MMCV' CI item

* Add 'Install MMCV_CPU' and 'Install MMCV_GPU CI' items

* Fix & Add

1. Fix low code coverage of vit.py;

2. Remove HybirdEmbed;

3. Fix doc string of VisionTransformer;

* Add helpers unit test.

* Add converter to convert vit pretrain weights from timm style to mmcls style.

* Clean some rebundant code and refactor init

1. Use timm style init_weights;

2. Remove to_xtuple and trunc_norm_;

* Add comments for VisionTransformer.init_weights()

* Add arg: pretrain_style to choose timm or mmcls vit pretrain weights.

2021-06-17 10:41:25 -07:00

backbones

[Refactor] Using mmcv transformer bricks to refactor vit. (#571 )

2021-06-17 10:41:25 -07:00

decode_heads

[Refactor]: Unified parameter initialization (#567 )

2021-06-16 21:41:29 -07:00

losses

[Enhance] Support reading class_weight from file in loss functions to help MMDet3D (#513 )

2021-04-29 01:04:15 -07:00

necks

[Refactor]: Unified parameter initialization (#567 )