## 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
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
Make projects contribution more clear
## Modification
1. Add description on project/README
2. Modify comments to reference in example_project/README
3. Add faq for projects
## BC-breaking (Optional)
No
## 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
Docs for Visualization featusre map using wandb backend.
## Modification
Add a new markdown file and result demo of wandb.
---------
Co-authored-by: MeowZheng <meowzheng@outlook.com>
## Motivation
Supplementary PR #2444
Fix tiny bug and add loss_by_feat() to compute loss to train.
The inference process have verified to be accurate.
## Modification
- modify `sep_aspp_contrast_head.py` , add `loss_by_feat()` function to
train(training still has bug, will fix in future😫)
- fix testing commands path error `bash tools/dist_test.sh
projects/HieraSeg_project/` to `bash tools/dist_test.sh
projects/HieraSeg/` at README.md
## 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
This is essentially #2535 that I had intended to submit to the `dev-1.x`
branch but accidentally submitted it directly to the `1.x` branch
(apologies!). This also got approved possibly because the core devs also
didn't realize this.
The problem is that now `1.x` and `dev-1.x` are out of sync -- the
changes introduced by #2535 will never be reflected in `dev-1.x`.
## Modification
I'm proposing this "backward-merge" so that `1.x` and `dev-1.x` can be
in sync again. If you look at "files changed", they are exactly the
changes introduced by #2535.
Co-authored-by: MeowZheng <meowzheng@outlook.com>
## Motivation
This is motivated by a previously unfinished PR (#2332). In that PR, the
label -1 was changed to 255 in `BaseSegDataset`, which is correct.
However, it was changed at only one location. There is another location
in `mmseg/datasets/basesegdataset.py` where -1 was still being used that
was not converted to 255. I have now converted it to 255.
This is exactly same as a similar fix to the `master` branch via #2515 .
## Modification
I've simply converted the snipped
```python
if new_id != -1:
new_palette.append(palette[old_id])
```
to
```python
if new_id != 255:
new_palette.append(palette[old_id])
```
## Checklist
- [x] Pre-commit or other linting tools are used to fix the potential
lint issues.
- _I've fixed all linting/pre-commit errors._
- [x] The modification is covered by complete unit tests. If not, please
add more unit test to ensure the correctness.
- _No unit tests need to be added or were affected.
- [x] If the modification has potential influence on downstream
projects, this PR should be tested with downstream projects, like MMDet
or MMDet3D.
- _I don't think this change affects MMDet or MMDet3D._
- [x] The documentation has been modified accordingly, like docstring or
example tutorials.
- _This change fixes an existing bug and doesn't require modifying any
documentation/docstring._
This is an almost exact duplicate of #2500 (that was made to the
`master` branch) now applied to the `1.x` branch.
---
## Motivation
I want to fix a bug through this PR. The bug occurs when two options --
`reduce_zero_label=True`, and custom classes are used.
`reduce_zero_label` remaps the GT seg labels by remapping the zero-class
to 255 which is ignored. Conceptually, this should occur *before* the
`label_map` is applied, which maps *already reduced labels*. However,
currently, the `label_map` is applied before the zero label is reduced.
## Modification
The modification is simple:
- I've just interchanged the order of the two operations by moving a few
lines from bottom to top.
- I've added a test that passes when the fix is introduced, and fails on
the original `master` branch.
## BC-breaking (Optional)
I do not anticipate this change braking any backward-compatibility.
## Checklist
- [x] Pre-commit or other linting tools are used to fix the potential
lint issues.
- _I've fixed all linting/pre-commit errors._
- [x] The modification is covered by complete unit tests. If not, please
add more unit test to ensure the correctness.
- _I've added a unit test._
- [x] If the modification has potential influence on downstream
projects, this PR should be tested with downstream projects, like MMDet
or MMDet3D.
- _I don't think this change affects MMDet or MMDet3D._
- [x] The documentation has been modified accordingly, like docstring or
example tutorials.
- _This change fixes an existing bug and doesn't require modifying any
documentation/docstring._
## Motivation
Support for biomedical 3d images augmentation.
## Modification
Add BioMedical3DRandomFlip in mmseg/datasets/transforms/transforms.py.
Co-authored-by: MeowZheng <meowzheng@outlook.com>
## Support `Mapillary Vistas Dataset`
## Motivation
Support **`Mapillary Vistas Dataset`**
Dataset Paper link : https://ieeexplore.ieee.org/document/9878466/
Download and more information view
https://www.mapillary.com/dataset/vistas
```
@InProceedings{Neuhold_2017_ICCV,
author = {Neuhold, Gerhard and Ollmann, Tobias and Rota Bulo, Samuel and Kontschieder, Peter},
title = {The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}
```
## Modification
Add `Mapillary_dataset` in `mmsegmentation/projects`
Add `configs/_base_/mapillary_v1_2.py` and
`configs/_base_/mapillary_v2_0.py`
Add `configs/deeplabv3plus_r18-d8_4xb2-80k_mapillay-512x1024.py` to test
training and testing on Mapillary datasets
Add `docs/en/user_guides/2_dataset_prepare.md` , add Mapillary Vistas
Dataset Preparing and Structure.
Add `tools/dataset_converters/mapillary.py` to convert RGB labels to
Mask labels.
Co-authored-by: 谢昕辰 <xiexinch@outlook.com>
## Motivation
The motivation of this PR is to add `gt_edge_map` field to support
boundary loss.
## Modification
- GenerateEdge
Modify `gt_edge` field to `gt_edge_map`.
- PackSegInputs
Add `gt_edge_map` to data_sample.
- stack_batch
Pad `gt_edge_map` to max_shape.
## BC-breaking (Optional)
No
## Use cases (Optional)
Reference `GenerateEdge`.
## Motivation
- Add Chinese version of Synapse dataset preparation.
- Modify all `，` and `。` to `,` and `.` in
`docs/zh_cn/user_guides/2_dataset_prepare.md`.
谢昕辰
Miao Zheng
Tianlong Ai
jinxianwei
wangjiangben-hw
CSH
vansin
Yijie Zheng
MengzhangLI
Andrew Lau
zccjjj
Qingyun
Siddharth Ancha
Leeinsn
Vladimir Loginov
Wencheng Wu