This reverts commit f1998375.

Dynasegformer: Added sparsity loss term for masks & replaced matmul in dgl layer to 1x1 Conv to save GPU memory

- reproduced some experiments
- added VSS pipeline
- added pruning pipeline

- reproduced some experiments
- added VSS pipeline
- added pruning pipeline

- reproduced some experiments

Co-authored-by: CSH <40987381+csatsurnh@users.noreply.github.com>

## Motivation

Change the dependency `mmcls` to `mmpretrain`

## Modification

- modify `mmcls` to `mmpretrain`
- modify CI requirements

## BC-breaking (Optional)

If users have installed mmcls but not install mmpretrain, it might raise some error.

- support dsdl seg dataset 
- add dsdl dataset citest
- validated accuracy on voc2012 and cityscapes

## Motivation

For support with reading multiple remote sensing image formats, please
refer to https://gdal.org/drivers/raster/index.html

.

Byte, UInt16, Int16, UInt32, Int32, Float32, Float64, CInt16, CInt32,
CFloat32 and CFloat64 are supported for reading and writing.

Support input of two images for change detection tasks, and support the
LEVIR-CD dataset.

## Modification

Add LoadSingleRSImageFromFile in 'mmseg/datasets/transforms/loading.py'.
Load a single remote sensing image for object segmentation tasks.

Add LoadMultipleRSImageFromFile in
'mmseg/datasets/transforms/loading.py'.
Load two remote sensing images for change detection tasks.

Add ConcatCDInput  in 'mmseg/datasets/transforms/transforms.py'.
Combine images that have been separately augmented for data enhancement.

Add BaseCDDataset in 'mmseg/datasets/basesegdataset.py'
Base class for datasets used in change detection tasks.

---------

Co-authored-by: xiexinch <xiexinch@outlook.com>

Ref: https://github.com/ydhongHIT/DDRNet#citation



Co-authored-by: xiexinch <xiexinch@outlook.com>

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 DDRNet
Paper: [Deep Dual-resolution Networks for Real-time and Accurate
Semantic Segmentation of Road Scenes](https://arxiv.org/pdf/2101.06085)
official Code: https://github.com/ydhongHIT/DDRNet


There is already a PR
https://github.com/open-mmlab/mmsegmentation/pull/1722 , but it has been
inactive for a long time.

## Current Result

### Cityscapes

#### inference with converted official weights

| Method | Backbone      | mIoU(official) | mIoU(converted weight) |
| ------ | ------------- | -------------- | ---------------------- |
| DDRNet | DDRNet23-slim | 77.8           | 77.84                  |
| DDRNet | DDRNet23 | 79.5 | 79.53 |

#### training with converted pretrained backbone

| Method | Backbone | Crop Size | Lr schd | Inf time(fps) | Device |
mIoU | mIoU(ms+flip) | config | download |
| ------ | ------------- | --------- | ------- | ------- | -------- |
----- | ------------- | ------------ | ------------ |
| DDRNet | DDRNet23-slim | 1024x1024 | 120000 | 85.85 | RTX 8000 | 77.85
| 79.80 |
[config](https://github.com/whu-pzhang/mmsegmentation/blob/ddrnet/configs/ddrnet/ddrnet_23-slim_in1k-pre_2xb6-120k_cityscapes-1024x1024.py)
| model \| log |
| DDRNet | DDRNet23 | 1024x1024 | 120000 | 33.41 | RTX 8000 | 79.53 |
80.98 |
[config](https://github.com/whu-pzhang/mmsegmentation/blob/ddrnet/configs/ddrnet/ddrnet_23_in1k-pre_2xb6-120k_cityscapes-1024x1024.py)
| model \| log |


The converted pretrained backbone weights download link:

1.
[ddrnet23s_in1k_mmseg.pth](https://drive.google.com/file/d/1Ni4F1PMGGjuld-1S9fzDTmneLfpMuPTG/view?usp=sharing)
2.
[ddrnet23_in1k_mmseg.pth](https://drive.google.com/file/d/11rsijC1xOWB6B0LgNQkAG-W6e1OdbCyJ/view?usp=sharing

)

## To do

- [x] support inference with converted official weights
- [x] support training on cityscapes dataset

---------

Co-authored-by: xiexinch <xiexinch@outlook.com>

## Motivation

- Create the `main` branch

## Modification

Modify links from `dev-1.x` to `main`

as title

## Motivation

Support SegNeXt in MMSeg 1.x branch.

0.x PR: https://github.com/open-mmlab/mmsegmentation/pull/2600



---------

Co-authored-by: xiexinch <xiexinch@outlook.com>

## 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

## [Datasets] Add Mapillary Vistas Datasets to MMSeg Core Package .
## Motivation
Add Mapillary Vistas Datasets to core package.
Old PR #2484 

## Modification
- Add Mapillary Vistas Datasets to core package.
- Delete `tools/datasets_convert/mapillary.py` , dataset does't need
converting.
- Add `schedule_240k.py`  config.
- Add configs files.  
  ```none
  deeplabv3plus_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
  deeplabv3plus_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
  maskformer_swin-s_4xb2-240k_mapillary_v1-512x1024.py
  maskformer_swin-s_4xb2-240k_mapillary_v2-512x1024.py
  maskformer_r101-d8_4xb2-240k_mapillary_v1-512x1024.py
  maskformer_r101-d8_4xb2-240k_mapillary_v2-512x1024.py
  pspnet_r101-d8_4xb2-240k_mapillay_v1-512x1024.py
  pspnet_r101-d8_4xb2-240k_mapillay_v2-512x1024.py
  ```
- Synchronized changes to `projects/mapillary_datasets`

---------

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Co-authored-by: xiexinch <xiexinch@outlook.com>

[Fix] Add out_channels  in `CascadeEncoderDecoder` and update OCRNet and MobileNet v2 results (#2656)

## Motivation

As title.

## Modification

1. update results in readme
2. fix attr error in cascade encoder decoder

## Motivation

The registry now supports auto-import modules from the given location.

register_all_modules before running is no longer needed. The modules
will be lazy-imported during building.

- [x] This PR can be merged after
https://github.com/open-mmlab/mmengine/pull/643. The MMEngine version
should be updated.

Ref: https://github.com/open-mmlab/mmdetection/pull/9143

## Motivation

In MMEngine >= 0.2.0, it might directly determine what the backend is by
using the `data_root` path.

## Modification

Set all default `backend_args` values are `None`.

## Motivation 
Add REFUGE datasets
Old PR: https://github.com/open-mmlab/mmsegmentation/pull/2420



---------

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

## Motivation

The DETR-related modules have been refactored in
open-mmlab/mmdetection#8763, which causes breakings of MaskFormer and
Mask2Former in both MMDetection (has been fixed in
open-mmlab/mmdetection#9515) and MMSegmentation. This pr fix the bugs in
MMSegmentation.

### TO-DO List

- [x] update configs
- [x] check and modify data flow
- [x] fix unit test
- [x] aligning inference
- [x] write a ckpt converter
- [x] write ckpt update script
- [x] update model zoo
- [x] update model link in readme
- [x] update
[faq.md](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/notes/faq.md#installation

)

## Tips of Fixing other implementations based on MaskXFormer of mmseg

1. The Transformer modules should be built directly. The original
building with register manner has been refactored.
2. The config requires to be modified. Delete `type` and modify several
keys, according to the modifications in this pr.
3. The `batch_first` is set `True` uniformly in the new implementations.
Hence the data flow requires to be transposed and config of
`batch_first` needs to be modified.
4. The checkpoint trained on the old implementation should be converted
to be used in the new one.

### Convert script

```Python
import argparse
from copy import deepcopy
from collections import OrderedDict

import torch

from mmengine.config import Config
from mmseg.models import build_segmentor
from mmseg.utils import register_all_modules
register_all_modules(init_default_scope=True)


def parse_args():
    parser = argparse.ArgumentParser(
        description='MMSeg convert MaskXFormer model, by Li-Qingyun')
    parser.add_argument('Mask_what_former', type=int,
                        help='Mask what former, can be a `1` or `2`',
                        choices=[1, 2])
    parser.add_argument('CFG_FILE', help='config file path')
    parser.add_argument('OLD_CKPT_FILEPATH', help='old ckpt file path')
    parser.add_argument('NEW_CKPT_FILEPATH', help='new ckpt file path')
    args = parser.parse_args()
    return args


args = parse_args()

def get_new_name(old_name: str):
    new_name = old_name

    if 'encoder.layers' in new_name:
        new_name = new_name.replace('attentions.0', 'self_attn')

    new_name = new_name.replace('ffns.0', 'ffn')

    if 'decoder.layers' in new_name:

        if args.Mask_what_former == 2:
            # for Mask2Former
            new_name = new_name.replace('attentions.0', 'cross_attn')
            new_name = new_name.replace('attentions.1', 'self_attn')
        else:
            # for Mask2Former
            new_name = new_name.replace('attentions.0', 'self_attn')
            new_name = new_name.replace('attentions.1', 'cross_attn')

    return new_name
    
def cvt_sd(old_sd: OrderedDict):
    new_sd = OrderedDict()
    for name, param in old_sd.items():
        new_name = get_new_name(name)
        assert new_name not in new_sd
        new_sd[new_name] = param
    assert len(new_sd) == len(old_sd)
    return new_sd
    
if __name__ == '__main__':
    cfg = Config.fromfile(args.CFG_FILE)
    model_cfg = cfg.model

    segmentor = build_segmentor(model_cfg)

    refer_sd = segmentor.state_dict()
    old_ckpt = torch.load(args.OLD_CKPT_FILEPATH)
    old_sd = old_ckpt['state_dict']

    new_sd = cvt_sd(old_sd)
    print(segmentor.load_state_dict(new_sd))

    new_ckpt = deepcopy(old_ckpt)
    new_ckpt['state_dict'] = new_sd
    torch.save(new_ckpt, args.NEW_CKPT_FILEPATH)
    print(f'{args.NEW_CKPT_FILEPATH} has been saved!')
```

Usage:
```bash
# for example
python ckpt4pr2532.py 1 configs/maskformer/maskformer_r50-d32_8xb2-160k_ade20k-512x512.py original_ckpts/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724-cbd39cc1.pth cvt_outputs/maskformer_r50-d32_8xb2-160k_ade20k-512x512_20221030_182724.pth
python ckpt4pr2532.py 2 configs/mask2former/mask2former_r50_8xb2-160k_ade20k-512x512.py original_ckpts/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055-4c62652d.pth cvt_outputs/mask2former_r50_8xb2-160k_ade20k-512x512_20221204_000055.pth
```

---------

Co-authored-by: MeowZheng <meowzheng@outlook.com>

## Motivation

Use the new fileio from mmengine
https://github.com/open-mmlab/mmengine/pull/533

## Modification

1. Use `mmengine.fileio` to repalce FileClient  in mmseg/datasets
2. Use `mmengine.fileio` to repalce FileClient in
mmseg/datasets/transforms
3. Use `mmengine.fileio` to repalce FileClient in mmseg/visualization

## BC-breaking (Optional)

we modify all the dataset configurations, so please use the latest config file.

## Motivation

Add Synapse dataset in MMSegmentation.
Old PR: https://github.com/open-mmlab/mmsegmentation/pull/2372.

* tta init

* use mmcv transform

* test city

* add multiscale

* fix merge

* add softmax to post process

* add ut

* add tta pipeline to other datasets

* remove softmax

* add encoder_decoder_tta ut

* add encoder_decoder_tta ut

* rename

* rename file

* rename config

* rm aug_test

* move flip to post process

* fix channel