Skip to content

Latest commit

 

History

History
49 lines (42 loc) · 1.08 KB

README.md

File metadata and controls

49 lines (42 loc) · 1.08 KB
Raw

EffectiveSemiSegmentation

[FLARE2022]Effective Semi Segmentation for Medical Image

Usage

  1. clone the repo
git clone https://github.com/JohnMasoner/EffectiveSemiSegmentation.git
  1. Install Apex[]
git clone https://github.com/NVIDIA/apex.git
cd apex
pip install -v --no-cache-dir ./
  1. Install repo requirements
pip install -r requirements.txt

Training

  1. Noteworthy, you could download the pre-train model by BaiDuNetDisk(link:https://pan.baidu.com/s/1K2AS4qBlbl710KlPFcyTgg?pwd=bs87 code: bs87)
  2. prepare you config, you could set your config file by the requirements. (main parms are every path)
vim FlareSeg/data_prepare/config.yaml
  1. train the model 2.1 coarse segmentation(set the param by your training params)
vim FlareSeg/coarse_base_seg/config.yaml
vim FlareSeg/coarse_base_seg/run.sh
cd FlareSeg/coarse_base_seg
sh run.sh

2.2 Fine Segmentation

vim FlareSeg/fine_efficient_seg/config.yaml
vim FlareSeg/fine_efficient_seg/run.sh
cd FlareSeg/fine_efficient_seg
sh run.sh

2.3 Inference

sh predict.sh