9 Commits

Author SHA1 Message Date
Peng Lu
c46cc85cba
[Feature] Support VPD Depth Estimator (#3321)
Thanks for your contribution and we appreciate it a lot. The following
instructions would make your pull request more healthy and more easily
get feedback. If you do not understand some items, don't worry, just
make the pull request and seek help from maintainers.

## Motivation


Support depth estimation algorithm [VPD](https://github.com/wl-zhao/VPD)

## Modification

1. add VPD backbone
2. add VPD decoder head for depth estimation
3. add a new segmentor `DepthEstimator` based on `EncoderDecoder` for
depth estimation
4. add an integrated metric that calculate common metrics in depth
estimation
5. add SiLog loss for depth estimation 
6. add config for VPD 

## BC-breaking (Optional)

Does the modification introduce changes that break the
backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the
downstream projects should modify their code to keep compatibility with
this PR.

## Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases
here, and update the documentation.

## Checklist

1. Pre-commit or other linting tools are used to fix the potential lint
issues.
7. The modification is covered by complete unit tests. If not, please
add more unit test to ensure the correctness.
8. If the modification has potential influence on downstream projects,
this PR should be tested with downstream projects, like MMDet or
MMDet3D.
9. The documentation has been modified accordingly, like docstring or
example tutorials.
2023-09-13 15:31:22 +08:00
jinxianwei
bb93b482b8
[Feature] huasdorff distance loss (#2820)
Thanks for your contribution and we appreciate it a lot. The following
instructions would make your pull request more healthy and more easily
get feedback. If you do not understand some items, don't worry, just
make the pull request and seek help from maintainers.

## Motivation

Add Huasdorff distance loss

---------

Co-authored-by: xiexinch <xiexinch@outlook.com>
2023-06-19 14:26:08 +08:00
谢昕辰
dd47cef801
[Feature] Support PIDNet (#2609)
## Motivation

Support SOTA real-time semantic segmentation method in [Paper with
code](https://paperswithcode.com/task/real-time-semantic-segmentation)

Paper: https://arxiv.org/pdf/2206.02066.pdf
Official repo: https://github.com/XuJiacong/PIDNet

## Current results

**Cityscapes**

|Model|Ref mIoU|mIoU (ours)|
|---|---|---|
|PIDNet-S|78.8|78.74|
|PIDNet-M|79.9|80.22|
|PIDNet-L|80.9|80.89|

## TODO

- [x] Support inference with official weights
- [x] Support training on Cityscapes
- [x] Update docstring
- [x] Add unit test
2023-03-15 14:55:30 +08:00
MengzhangLI
ee7f340dff
[Feature] Support Tversky Loss in dev-1.x branch (#2000) 2022-08-31 10:58:21 +08:00
Rockey
07cd6c98e0 [Feature] Add focal loss (#1024)
* [Feature] add focal loss

* fix the bug of 'non' reduction type

* refine the implementation

* add class_weight and ignore_index; support different alpha values for different classes

* fixed some bugs

* fix bugs

* add comments

* modify test

* Update mmseg/models/losses/focal_loss.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* update test_focal_loss.py

* modified the implementation

* Update mmseg/models/losses/focal_loss.py

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

* update focal_loss.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2021-12-03 00:18:40 -08:00
Junjun2016
2fe0bddf5e [Dcos] Add header for files (#796)
* Add header for files

* Delete header in config files
2021-08-16 23:16:55 -07:00
谢昕辰
a3b523e3fd dice loss (#396)
* dice loss

* format code, add docstring and calculate denominator without valid_mask

* minor change

* restore
2021-03-10 18:32:37 -08:00
yamengxi
c8bbd3fa95 [New Feature]add lovasz loss (#351)
* add lovasz loss

* Modify as comments

* Modify paper url

* add unittest and remove Var

* impove unittest
2021-01-18 19:05:30 -08:00
Jiarui XU
b2724da80b init commit 2020-07-10 02:39:01 +08:00