Pytorch implementation of TCSM
Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation
- Install Pytorch 1.1.0 and CUDA 9.0
- Clone this repo
git clone https://github.com/xmengli999/TCSM
cd TCSM
- Download Skin dataset, REFUGE dataset, Liver CT dataset
- Put the data under
./data/
- cd
scripts_skin
- Run
sh train_50tcsm.sh
to start the training process
- Specify the model path in
eval.sh
- Run
sh eval.sh
to start the evaluation.
Some code is reused from the Pytorch implementation of mean teacher.
- Contact: Xiaomeng Li (xmengli999@gmail.com)