## 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
Support `MMSegInferencer` for providing an easy and clean interface for
single or multiple images inferencing.
Ref: https://github.com/open-mmlab/mmengine/pull/773https://github.com/open-mmlab/mmocr/pull/1608
## Modification
- mmseg/apis/mmseg_inferencer.py
- mmseg/visualization/local_visualizer.py
- demo/image_demo_with_inferencer.py
## Use cases (Optional)
Based on https://github.com/open-mmlab/mmengine/tree/inference
Add a new image inference demo with `MMSegInferencer`
- demo/image_demo_with_inferencer.py
```shell
python demo/image_demo_with_inferencer.py demo/demo.png fcn_r50-d8_4xb2-40k_cityscapes-512x1024
```
---------
Co-authored-by: MeowZheng <meowzheng@outlook.com>
## 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.
* upload original backbone and configs
* ConvNext Refactor
* ConvNext Refactor
* convnext customization refactor with mmseg style
* convnext customization refactor with mmseg style
* add ade20k_640x640.py
* upload files for training
* delete dist_optimizer_hook and remove layer_decay_optimizer_constructor
* check max(out_indices) < num_stages
* add unittest
* fix lint error
* use MMClassification backbone
* fix bugs in base_1k
* add mmcls in requirements/mminstall.txt
* add mmcls in requirements/mminstall.txt
* fix drop_path_rate and layer_scale_init_value
* use logger.info instead of print
* add mmcls in runtime.txt
* fix f string && delete
* add doctring in LearningRateDecayOptimizerConstructor and fix mmcls version in requirements
* fix typo in LearningRateDecayOptimizerConstructor
* use ConvNext models in unit test for LearningRateDecayOptimizerConstructor
* add unit test
* fix typo
* fix typo
* add layer_wise and fix redundant backbone.downsample_norm in it
* fix unit test
* give a ground truth lr_scale and weight_decay
* upload models and readme
* delete 'backbone.stem_norm' and 'backbone.downsample_norm' in get_num_layer()
* fix unit test and use mmcls url
* update md2yml.py and metafile
* fix typo
* add dice evaluation metric
* add dice evaluation metric
* add dice evaluation metric
* support 2 metrics
* support 2 metrics
* support 2 metrics
* support 2 metrics
* fix docstring
* use np.round once for all
Miao Zheng
谢昕辰
Qingyun
MengzhangLI
Junjun2016
Jerry Jiarui XU
谢昕辰
sshuair
Kai Chen