pytorch-unflow - GitLite

KO | EN

gitlite — search

#python #hacktoberfest #react #ai #typescript #golang #android #machine-learning #rust #deep-learning #java #windows #cli #awesome-list

pytorch-unflow

(★ 146)

a reimplementation of UnFlow in PyTorch that matches the official TensorFlow version

파일 탐색기

최종 버전 다운로드 (.zip)

- comparison.gif
- comparison.py
- official - tensorflow.png
- this - pytorch.png
- correlation.py
- README.md
- one.png
- README.md
- two.png
LICENSE
README.md
requirements.txt
run.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/sniklaus/pytorch-unflow

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd pytorch-unflow

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

python run.py

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# pytorch-unflow
This is a personal reimplementation of UnFlow [1] using PyTorch. Should you be making use of this work, please cite the paper accordingly. Also, make sure to adhere to the <a href="https://github.com/simonmeister/UnFlow/blob/master/LICENSE">licensing terms</a> of the authors. Should you be making use of this particular implementation, please acknowledge it appropriately [2].

<a href="https://arxiv.org/abs/1711.07837"><img src="http://www.arxiv-sanity.com/static/thumbs/1711.07837v1.pdf.jpg" alt="Paper" width="100%"></a>

For the original TensorFlow version of this work, please see: https://github.com/simonmeister/UnFlow
<br />
Other optical flow implementations from me: [pytorch-pwc](https://github.com/sniklaus/pytorch-pwc), [pytorch-spynet](https://github.com/sniklaus/pytorch-spynet), [pytorch-liteflownet](https://github.com/sniklaus/pytorch-liteflownet)

## setup
The correlation layer is implemented in CUDA using CuPy, which is why CuPy is a required dependency. It can be installed using `pip install cupy` or alternatively using one of the provided [binary packages](https://docs.cupy.dev/en/stable/install.html#installing-cupy) as outlined in the CuPy repository.

## usage
To run it on your own pair of images, use the following command. You can choose between two models, please make sure to see their paper / the code for more details.

```
python run.py --model css --one ./images/one.png --two ./images/two.png --out ./out.flo
```

I am afraid that I cannot guarantee that this reimplementation is correct. However, it produced results identical to the implementation of the original authors in the examples that I tried. Please feel free to contribute to this repository by submitting issues and pull requests.

## comparison
<p align="center"><img src="comparison/comparison.gif?raw=true" alt="Comparison"></p>

## license
As stated in the <a href="https://github.com/simonmeister/UnFlow/blob/master/LICENSE">licensing terms</a> of the authors of the paper, the models subject to an MIT license. Please make sure to further consult their licensing terms.

## references
```
[1]  @inproceedings{Meister_AAAI_2018,
         author = {Simon Meister and Junhwa Hur and Stefan Roth},
         title = {{UnFlow}: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss},
         booktitle = {AAAI},
         year = {2018}
     }
```

```
[2]  @misc{pytorch-unflow,
         author = {Simon Niklaus},
         title = {A Reimplementation of {UnFlow} Using {PyTorch}},
         year = {2018},
         howpublished = {\url{https://github.com/sniklaus/pytorch-unflow}}
    }
```