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

Update README.md

Browse Source
This commit is contained in:
Gangwei Xu 2023-03-12 22:10:49 +08:00 committed by GitHub
parent e4b5b25e37
commit a98be02f00
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@ -7,6 +7,15 @@ Gangwei Xu, Xianqi Wang, Xiaohuan Ding, Xin Yang<br/>
<img src="IGEV-Stereo/IGEV-Stereo.png">
## Demos
Pretrained models can be downloaded from [google drive](https://drive.google.com/drive/folders/1SsMHRyN7808jDViMN1sKz1Nx-71JxUuz?usp=share_link)
You can demo a trained model on pairs of images. To predict stereo for Middlebury, run
```
python demo.py --restore_ckpt ./pretrained_models/sceneflow/sceneflow.pth
```
<img src="IGEV-Stereo/demo-imgs.png", width="90%">
## Environment
* NVIDIA RTX 3090
* Python 3.8
@ -30,15 +39,6 @@ pip install tqdm
pip install timm==0.5.4
```
## Demos
Pretrained models can be downloaded from [google drive](https://drive.google.com/drive/folders/1SsMHRyN7808jDViMN1sKz1Nx-71JxUuz?usp=share_link)
You can demo a trained model on pairs of images. To predict stereo for Middlebury, run
```
python demo.py --restore_ckpt ./pretrained_models/sceneflow/sceneflow.pth
```
## Required Data
To evaluate/train IGEV-Stereo, you will need to download the required datasets.
* [Scene Flow](https://lmb.informatik.uni-freiburg.de/resources/datasets/SceneFlowDatasets.en.html)