Shuffle-Transformer - GitLite

KO | EN

gitlite — search

#javascript #python #react #ai #go #machine-learning #rust #deep-learning #nodejs #macos #awesome #kubernetes #pytorch #open-source

Shuffle-Transformer

(★ 98)

No description available.

파일 탐색기

최종 버전 다운로드 (.zip)

- shuffle_vit_base_patch4_window7_224.yaml
- shuffle_vit_small_patch4_window7_224.yaml
- shuffle_vit_tiny_patch4_window7_224.yaml
- - __init__.cpython-36.pyc
  - build.cpython-36.pyc
  - cached_image_folder.cpython-36.pyc
  - samplers.cpython-36.pyc
  - zipreader.cpython-36.pyc
- __init__.py
- build.py
- cached_image_folder.py
- samplers.py
- zipreader.py
- shuffle-transformer.jpg
- - __init__.cpython-36.pyc
  - build.cpython-36.pyc
  - shuffle_transformer.cpython-36.pyc
  - swin_transformer.cpython-36.pyc
- __init__.py
- build.py
- shuffle_transformer.py
- swin_transformer.py
config.py
LICENSE
logger.py
lr_scheduler.py
main.py
optimizer.py
README.md
utils.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/mulinmeng/Shuffle-Transformer

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd Shuffle-Transformer

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. 공식 설치 스크립트

쉬움 추천

사전 준비물

Python 3 pip 명령어를 쓰려면 Python이 필요합니다.

pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

pip install opencv-python==4.4.0.46 termcolor==1.1.0 yacs==0.1.8

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

pip install einops

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Shuffle Transformer

The implementation of "[Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer](https://arxiv.org/abs/2106.03650)"

## Introduction

Very recently, window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been devoted to the cross-window connection which is the key element to improve the representation ability. **Shuffle Transformer** revisit the spatial shuffle as an efficient way to build connections among windows, which is highly efficient and easy to implement by modifying two lines of code. Furthermore, the depth-wise convolution is introduced to complement the spatial shuffle for enhancing neighbor-window connections. The proposed architectures achieve excellent performance on a wide range of visual tasks including image-level classification, object detection, and semantic segmentation.

![st](https://raw.githubusercontent.com/mulinmeng/Shuffle-Transformer/main/figs/shuffle-transformer.jpg)

## Requirements

- PyTorch==1.7.1
- torchvision==0.8.2
- timm==0.3.2

The [Apex](https://github.com/NVIDIA/apex) is optional for faster training speed.

```
git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
```

Other Requirements

```
pip install opencv-python==4.4.0.46 termcolor==1.1.0 yacs==0.1.8
pip install einops
```

## Main Results

##### Results on **ImageNet-1K**

| name      | acc@1 | #params | FLOPs | Throughputs(Images/s) | Weights                                                      |
| --------- | ----- | ------- | ----- | --------------------- | ------------------------------------------------------------ |
| Shuffle-T | 82.4  | 28M     | 4.6G  | 791                   | [google drive](https://drive.google.com/drive/folders/1goDJtcnxgBAcHhZnNwrgOlG_WBftpmOS?usp=sharing) |
| Shuffle-S | 83.6  | 50M     | 8.9G  | 450                   | [google drive](https://drive.google.com/drive/folders/1GUBBQyDldY145vDiK-BHqivmpj3K6HK2?usp=sharing) |
| Shuffle-B | 84.0  | 88M     | 15.6  | 279                   | [google drive](https://drive.google.com/drive/folders/1x0biaJRdN4nxLmp_3lQcA_6hO_sDBoUM?usp=sharing) |

## Usage

For classification on ImageNet-1K, to train from scratch, run:

```
python -m torch.distributed.launch --nproc_per_node <num-of-gpus-to-use>  main.py \ 
--cfg <config-file> --data-path <imagenet-path> [--batch-size <batch-size-per-gpu> --output <output-directory>]
```

To evaluate, run:

```
python -m torch.distributed.launch --nproc_per_node <num-of-gpus-to-use> main.py --eval \
--cfg <config-file> --resume <checkpoint> --data-path <imagenet-path> 
```

## In progress

- Semantic Segmentation
- Instance Segmentation

## Citing Shuffle Transformer

```
@article{huang2021shuffle,
 title={Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer},
 author={Huang, Zilong and Ben, Youcheng and Luo, Guozhong and Cheng, Pei and Yu, Gang and Fu, Bin},
 journal={arXiv preprint arXiv:2106.03650},
 year={2021}
}
```

## Acknowledgement

Thanks to open-source implementation of [Swin-Transformer](https://github.com/microsoft/Swin-Transformer).