# MobileStereoNet

**Repository Path**: ykuo/mobile-stereo-net

## Basic Information

- **Project Name**: MobileStereoNet
- **Description**: 复现先进算法：MobileStereoNet
复现代码来源于开源代码：cogsys-tuebingen/mobilestereonet
复现论文：MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-03-08
- **Last Updated**: 2025-08-16

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# MobileStereoNet

#### 介绍

- 复现先进算法：MobileStereoNet
- 复现代码来源于开源代码：[cogsys-tuebingen/mobilestereonet](https://github.com/cogsys-tuebingen/mobilestereonet)
- 复现论文：MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching

#### 软件架构

- python3.11
- pytorch2.1.0+cu121

#### 安装教程

1.  xxxx
2.  xxxx
3.  xxxx

#### 使用说明

1.  tensorboard --logdir=./logs --port=6006
2.  watch -n 1 nvidia-smi
3.  netstat -ano | findstr :6006
4.  nohup python ./main.py > ./logs/nohup.log 2>&1 &
5.  tail -f ./logs/nohup.log
6.  ps aux|grep python

#### 训练Training
    # Train MobileStereoNet on Scene Flow,
    python train.py --model MSNet2D --dataset sceneflow --trainlist ./filenames/sceneflow_train.txt --testlist ./filenames/sceneflow_test.txt --epochs 20 --lrepochs "10,12,14,16:2" --batch_size 8 --test_batch_size 8 --num_workers 8

#### 微调Finetune
    # Finetune MobileStereoNet on KITTI (using pretrained model on Scene Flow),
    python train.py --model MSNet2D --dataset kitti --batch_size 8 --test_batch_size 8 --num_workers 8
    # Finetune MobileStereoNet on USVInland (using pretrained model on Scene Flow),
    python train.py --model MSNet2D --dataset usvinland --maxdisp 64 --trainlist ./filenames/usvinland_train.txt --testlist ./filenames/usvinland_val.txt --batch_size 8 --test_batch_size 8 --num_workers 8
    # Finetune MobileStereoNet on USVInland_seg (using pretrained model on Scene Flow),
    python train.py --model MSNet2D --dataset usvinland_seg --maxdisp 64 --trainlist ./filenames/usvinland_seg_train.txt --testlist ./filenames/usvinland_seg_val.txt --batch_size 8 --test_batch_size 8 --num_workers 8

#### 保存Save
    # Generate disparity images of KITTI test set,
    python prediction.py --model MSNet2D --dataset kitti --datapath $DATAPATH --testlist ./filenames/kitti15_test.txt --loadckpt ./checkpoints/finetuned.ckpt --colored True

#### 参与贡献

1.  Fork 本仓库
2.  新建 Feat_xxx 分支
3.  提交代码
4.  新建 Pull Request

#### 特技

1.  使用 Readme\_XXX.md 来支持不同的语言，例如 Readme\_en.md, Readme\_zh.md
2.  Gitee 官方博客 [blog.gitee.com](https://blog.gitee.com)
3.  你可以 [https://gitee.com/explore](https://gitee.com/explore) 这个地址来了解 Gitee 上的优秀开源项目
4.  [GVP](https://gitee.com/gvp) 全称是 Gitee 最有价值开源项目，是综合评定出的优秀开源项目
5.  Gitee 官方提供的使用手册 [https://gitee.com/help](https://gitee.com/help)
6.  Gitee 封面人物是一档用来展示 Gitee 会员风采的栏目 [https://gitee.com/gitee-stars/](https://gitee.com/gitee-stars/)

#### 引用
@inproceedings{shamsafar2022mobilestereonet,
  title={MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching},
  author={Shamsafar, Faranak and Woerz, Samuel and Rahim, Rafia and Zell, Andreas},
  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  pages={2417--2426},
  year={2022}
}