## Motivation
Make MMSeginferencer easier to be used
## Modification
1. Add `_load_weights_to_model` to MMSeginferencer, it is for get
`dataset_meta` from ckpt
2. Modify and remove some parameters of `__call__`, `visualization` and
`postprocess`
3. Add function of save seg mask, remove dump pkl.
4. Refine docstring of MMSeginferencer and SegLocalVisualizer
5. Add the user documentation of MMSeginferencer
## BC-breaking (Optional)
yes, remove some parameters, we need to discuss whether keep them with
deprecated waring or just remove them as the MMSeginferencer just merged
in mmseg a few days.
Co-authored-by: xiexinch <xiexinch@outlook.com>
## Motivation
As the mmdet and mmcls are not very stabel, and mim can install repo
from source code, we remove them from mminstall and they won't be
installed automatically when run `mim install mmsegmentation`
## Modification
1. remove mmdet and mcls from mminstall
2. add explanation in faq
---------
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
## 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
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 Chinese version of Synapse dataset preparation.
- Modify all `，` and `。` to `,` and `.` in
`docs/zh_cn/user_guides/2_dataset_prepare.md`.
* [Doc]Translate the 1_config.md and modify a wrong statement in 1_config.md
* Translate the 1_config.md and modify a wrong statement in 1_config.md
* Modify some expressions
* Apply suggestions from code review
CSH
jinxianwei
MengzhangLI
谢昕辰
Miao Zheng
wangjiangben-hw
Yijie Zheng
Andrew Lau
Qingyun
Siddharth Ancha
王永韬
pofengdenihong
MeowZheng
MingJian.L
Range King