## Motivation
When using the - tta command for multi-scale prediction, and the test
set is not annotated, although format_only has been set true in
test_evaluator, but SegTTAModel class still threw error 'AttributeError:
'SegDataSample' object has no attribute '_gt_sem_seg''.
## Modification
The reason is SegTTAModel didn't determine if there were annotations in
the dataset, so I added the code to make the judgment and let the
program run normally on my computer.
## Motivation
Please describe the motivation of this PR and the goal you want to
achieve through this PR.
## Modification
- add dataset-index.yml
## Dependencies
- [ ] https://github.com/open-mmlab/mim/pull/212
## 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.
## Motivation
In encode_decoder.py , assertion logic is not working correctly if user
modifes cfg.test_cfg and defines it in a dictionary format. See:
https://github.com/open-mmlab/mmsegmentation/issues/3011
## Modification
Slight change to assertion behaviour to change assertion depending on if
received test_cfg object is a dict or not.
## BC-breaking (Optional)
Unsure - I believe this will not break any downstream tasks as the
previous logic is still included
## Use cases (Optional)
n/a
---------
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
Add Huasdorff distance loss
---------
Co-authored-by: xiexinch <xiexinch@outlook.com>
## Motivation
Suppose an image is named `jpg.jpg` and its corresponding segmap is
named `jpg.png`.
The original implementation will try to read segmap from `png.png` and
causes FileNotfoundError
## Modification
Only replace the suffix, instead of full string search and replacement.
## BC-breaking (Optional)
Probably no.
## Use cases (Optional)
## Checklist
1. Pre-commit or other linting tools are used to fix the potential lint
issues.
2. The modification is covered by complete unit tests. If not, please
add more unit test to ensure the correctness.
3. If the modification has potential influence on downstream projects,
this PR should be tested with downstream projects, like MMDet or
MMDet3D.
4. The documentation has been modified accordingly, like docstring or
example tutorials.
---------
Co-authored-by: 谢昕辰 <xiexinch@outlook.com>
Co-authored-by: CSH <40987381+csatsurnh@users.noreply.github.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
Enhance pretrained SwinTransformer loading when setting non-standard
backbone `depths`.
## Modification
Enhance pretrained SwinTransformer loading when setting non-standard
backbone `depths`.
## 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.
2. The modification is covered by complete unit tests. If not, please
add more unit test to ensure the correctness.
3. If the modification has potential influence on downstream projects,
this PR should be tested with downstream projects, like MMDet or
MMDet3D.
4. The documentation has been modified accordingly, like docstring or
example tutorials.
---------
Co-authored-by: SheffieldCao <1751899@tongji.edu.cn>
## Motivation
Fix bug cannot use both '--tta' and '--out' while testing.
For details, please refer to #3064 .
## Modification
Add 'img_path' in TTA predictions.
---------
Co-authored-by: xiexinch <xiexinch@outlook.com>
## Motivation
When processing data in the isaid experiment, generated images only have
binary pixel values of 0 or 1 instead of the corresponding class values.
This causes significant interference and prevents subsequent experiments
from proceeding. After investigation, it was found that the issue was
caused by using the wrong image format for saving the images. Saving the
images as PNG resulted in binary pixel values, while saving the images
as BMP resolved the issue and correctly saved the class values.
## Modification
`img_patch.save(save_path_image, format='BMP')`
This code will save the image data as BMP format.
## BC-breaking
Confirm that the modification does not introduce new issues and test
that the modified code successfully resolves the original problem.
---------
Co-authored-by: 谢昕辰 <xiexinch@outlook.com>
Co-authored-by: CSH <40987381+csatsurnh@users.noreply.github.com>
## Motivation
The original version of Visual Attention Network (VAN) can be found from
https://github.com/Visual-Attention-Network/VAN-Segmentation
添加Visual Attention Network (VAN)的支持。
## Modification
added a floder mmsegmentation/projects/van/
added 13 configs totally and aligned performance basically.
只增加了一个文件夹，共增加13个配置文件，基本对齐性能（没有全部跑）。
## Use cases (Optional)
Before running, you may need to download the pretrain model from
https://cloud.tsinghua.edu.cn/d/0100f0cea37d41ba8d08/
and then move them to the folder mmsegmentation/pretrained/, i.e.
"mmsegmentation/pretrained/van_b2.pth".
After that, run the following command:
cd mmsegmentation
bash tools/dist_train.sh
projects/van/configs/van/van-b2_pre1k_upernet_4xb2-160k_ade20k-512x512.py
4
---------
Co-authored-by: xiexinch <xiexinch@outlook.com>
ZiAn-Su
谢昕辰
OliverGrace
masaaki
legendchilli
tianbin li
Sizheng Guo
Leon Hamnett
jinxianwei
WRH
Xu CAO
shi gengtian
Tianlong Ai
nightrain01
Kedreamix
tang576225574