DataloaderListGenertor
Software Environment
- OS Environment
$ os >= linux 16.04
$ cudaToolKit >= 10.1
$ cudnn >= 7.3.6
- Python Environment
$ python >= 3.8.5
$ pythorch >= 1.15.0
$ numpy >= 1.14.5
$ PIL >= 5.1.0
Software Environment
This framework is only used in Linux.
How to use our DataloaderListGenertor:
- Install the DataloaderListGenertor lib
$ ./bulid.sh
- How to use the DataloaderListGenertor
$ DatasetListGenerator --task "stereo matching" --dataset "SceneFlow" --dataset_folder_path /data/datasets/StereoMatching/SceneFlow/ --save_folder_path ./
-
parameter information
-
--task
default=stereo matching -
--dataset
default='KITTI2012'
Other Parameters
Parameters Description 'WHUStereo' WHUStereoList 'CREStereo' CreStereoLis 'KITTI2012' KITTI2012StereoList 'KITTI2015': KITTI2015StereoList 'ETH3D' ETH3DStereoList 'Middlebury' MiddleburyStereoList 'US3D' US3DStereoList 'SceneFlow' SceneFlowStereoList - --dataset_folder_path
your datasets path - --save_folder_path
The path where your.csv file is saved.
-
-
Clean the project (if you want to clean generating files)
$ ./clean.sh
File Structure
DataloaderListGenertor
├── Source # source code
│ ├──setup.py
│ └── DataloaderListGenertor/
│ ├── Reconstruction/
│ ├── Stereo/
│ ├── SysBasic/
│ ├── Template/
│ └── main.py
├── Scripts/
│ ├── gen_stereo_list.sh
│ ├── install.sh
│ └── ...
├── Example/
│ ├── whu_stereo_training_list.csv
│ └── ...
├── LICENSE
├── build.sh
├── clean.sh
└── README.md
Update log
2023-11-02
- Write the ReadMe.