EdgeTrans4Mark

KO | EN

gitlite — search

#python #hacktoberfest #react #ai #llm #golang #machine-learning #rust #nodejs #kubernetes #awesome-list #pytorch #openai #open-source

(★ 10)

pytorch implementation of ECCV2022 "One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement"

EdgeTrans4Mark 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# EdgeTrans4Mark
pytorch implementation of ECCV2022 "One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinement"
![Framework](https://raw.githubusercontent.com/GoldExcalibur/EdgeTrans4Mark/main/figures/eccv_2stage_scheme.png)

## Dataset
Download image & annotations from [IEEE ISBI2015 Challenge](http://www-o.ntust.edu.tw/~cweiwang/ISBI2015/challenge1).
Or use provided data copy [DATA COPY](https://pan.baidu.com/s/1b5N1nKciIonEj3sBEjLtEA)(file extraction code: xjvh) with converted coco format annotations. 
Then place this dataset under /data folder.
```txt
${ROOT}
`-- data
    `-- cephalometric
`-- pretrained_models 
    `-- hrnetv2_w18_imagenet_pretrained.pth
```

## Requirements
```py
conda create -n landmark python==3.6.3
pip install -r requirements.txt
```
For torch and torchvision, you can find whl in [pytorch_whl](https://download.pytorch.org/whl/torch_stable.html/cu100) and pip install offline. 
## Training & Testing
- train stage1 
```py
CUDA_VISIBLE_DEVICES=0,1 python3 scripts/train_st1.py \
--cfg experiments/cephalometric/train_st1.yaml \
--gpus 0,1 
```

- use stage1 model to infer label 
```py
CUDA_VISIBLE_DEVICES=0 python3 scripts/test_st1.py \
--model [BEST STAGE1 MODEL] \
--cfg experiments/cephalometric/train_st1.yaml \
--gpus 0 --local-iter 4 --infer-train 
```

- train stage2 
```py
CUDA_VISIBLE_DEVICES=0,1 python3 scripts/train_st2.py \  --cfg experiments/cephalometric/train_st2.yaml \
--gpus 0,1 
```

## Acknowledgements 
Great thanks for the following works and their opensource codes [HRNet](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch), [DETR](https://github.com/facebookresearch/detr).

EdgeTrans4Mark

EdgeTrans4Mark 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

EdgeTrans4Mark

EdgeTrans4Mark 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README