a85675c16f
Note that this PR is a modified version of the withdrawn PR https://github.com/open-mmlab/mmsegmentation/pull/1748 ## Motivation In the last years, panoptic segmentation has become more into the focus in reseach. Weber et al. [[Link]](http://www.cvlibs.net/publications/Weber2021NEURIPSDATA.pdf) have published a quite nice dataset, which is in the same style like Cityscapes, but for KITTI sequences. Since Cityscapes and KITTI-STEP share the same classes and also a comparable domain (dashcam view), interesting investigations, e.g. about relations in the domain e.t.c. can be done. Note that KITTI-STEP provices panoptic segmentation annotations which are out of scope for mmsegmentation. ## Modification Mostly, I added the new dataset and dataset preparation file. To simplify the first usage of the new dataset, I also added configs for the dataset, segformer and deeplabv3plus. ## BC-breaking (Optional) No BC-breaking ## Use cases (Optional) Researchers want to test their new methods, e.g. for interpretable AI in the context of semantic segmentation. They want to show, that their method is reproducible on comparable datasets. Thus, they can compare Cityscapes and KITTI-STEP. --------- Co-authored-by: CSH <40987381+csatsurnh@users.noreply.github.com> Co-authored-by: csatsurnh <cshan1995@126.com> Co-authored-by: 谢昕辰 <xiexinch@outlook.com>
KITTI STEP Dataset
Support KITTI STEP Dataset
Description
Author: TimoK93
This project implements KITTI STEP Dataset
Dataset preparing
After registration, the data images could be download from KITTI-STEP
You may need to follow the following structure for dataset preparation after downloading KITTI-STEP dataset.
mmsegmentation
├── mmseg
├── tools
├── configs
├── data
│ ├── kitti_step
│ │ ├── testing
│ │ ├── training
│ │ ├── panoptic_maps
Run the preparation script to generate label files and kitti subsets by executing
python tools/convert_datasets/kitti_step.py /path/to/kitti_step
After executing the script, your directory should look like
mmsegmentation
├── mmseg
├── tools
├── configs
├── data
│ ├── kitti_step
│ │ ├── testing
│ │ ├── training
│ │ ├── panoptic_maps
│ │ ├── training_openmmlab
│ │ ├── panoptic_maps_openmmlab
Training commands
# Dataset train commands
# at `mmsegmentation` folder
bash tools/dist_train.sh projects/kitti_step_dataset/configs/segformer/segformer_mit-b5_368x368_160k_kittistep.py 8
Testing commands
mim test mmsegmentation projects/kitti_step_dataset/configs/segformer/segformer_mit-b5_368x368_160k_kittistep.py --work-dir work_dirs/segformer_mit-b5_368x368_160k_kittistep --checkpoint ${CHECKPOINT_PATH} --eval mIoU
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | model | log |
|---|---|---|---|---|---|---|---|---|---|---|
| Segformer | MIT-B5 | 368x368 | 160000 | - | - | 65.05 | - | config | model | log |
Checklist
-
Milestone 1: PR-ready, and acceptable to be one of the
projects/.-
Finish the code
-
Basic docstrings & proper citation
-
Test-time correctness
-
A full README
-
-
Milestone 2: Indicates a successful model implementation.
- Training-time correctness
-
Milestone 3: Good to be a part of our core package!
-
Type hints and docstrings
-
Unit tests
-
Code polishing
-
Metafile.yml
-
-
Move your modules into the core package following the codebase's file hierarchy structure.
-
Refactor your modules into the core package following the codebase's file hierarchy structure.