HTensor/GwcNet
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update code environment

Browse Source
This commit is contained in:
Xiaoyang Guo 2019-04-17 17:57:51 +08:00
parent a491f3804c
commit edebced658
1 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -1,16 +1,20 @@
# GwcNet
# GwcNet
This is the implementation of the paper **Group-wise Correlation Stereo Network**, CVPR 19, Xiaoyang Guo, Kai Yang, Wukui Yang, Xiaogang Wang, and Hongsheng Li
[\[Arxiv\]](https://arxiv.org/)
# How to use
## Data Preparation
Download [Scene Flow Datasets](https://lmb.informatik.uni-freiburg.de/resources/datasets/SceneFlowDatasets.en.html), [KITTI 2012](http://www.cvlibs.net/datasets/kitti/eval_stereo_flow.php?benchmark=stereo), [KITTI 2015](http://www.cvlibs.net/datasets/kitti/eval_scene_flow.php?benchmark=stereo)
## Environment
* python 3.6
* Pytorch >= 0.4.1
## Data Preparation
Download [Scene Flow Datasets](https://lmb.informatik.uni-freiburg.de/resources/datasets/SceneFlowDatasets.en.html), [KITTI 2012](http://www.cvlibs.net/datasets/kitti/eval_stereo_flow.php?benchmark=stereo), [KITTI 2015](http://www.cvlibs.net/datasets/kitti/eval_scene_flow.php?benchmark=stereo)
## Training
**Scene Flow Datasets**
run the script `./scripts/sceneflow.sh` to train on Scene Flow datsets. Please update `DATAPATH` in the bash file as your training data path.
**KITTI 2012 / 2015**
@ -18,7 +22,7 @@ run the script `./scripts/sceneflow.sh` to train on Scene Flow datsets. Please u
run the script `./scripts/kitti12.sh` and `./scripts/kitti15.sh` to finetune on the KITTI 12/15 dataset. Please update `DATAPATH` and `--loadckpt` as your training data path and pretrained SceneFlow checkpoint file.
## Evaluation
run the script `./scripts/kitti12_save.sh` and `./scripts/kitti15_save.sh` to save png predictions on the test set of the KITTI datasets to the folder `./predictions`.
run the script `./scripts/kitti12_save.sh` and `./scripts/kitti15_save.sh` to save png predictions on the test set of the KITTI datasets to the folder `./predictions`.
## Pretrained Models
[KITTI 2012/2015](https://drive.google.com/file/d/1fOw2W7CSEzvSKzBAEIIeftxw6CuvH9Hl/view?usp=sharing)
@ -37,4 +41,4 @@ If you find this code useful in your research, please cite:
# Acknowledgements
Thanks to Jia-Ren Chang for opening source of his excellent work PSMNet. Our work is inspired by this work and part of codes in `models` are migrated from [PSMNet](https://github.com/JiaRenChang/PSMNet).
Thanks to Jia-Ren Chang for opening source of his excellent work PSMNet. Our work is inspired by this work and part of codes in `models` are migrated from [PSMNet](https://github.com/JiaRenChang/PSMNet).