Some important required packages include:
- Pytorch version >=0.4.1.
- TensorBoardX
- Python == 3.6
- Efficientnet-Pytorch
pip install efficientnet_pytorch - Some basic python packages such as Numpy, Scikit-image, SimpleITK, Scipy ......
Follow official guidance to install Pytorch.
- Clone the repo:
git clone https://github.com/HiLab-git/SSL4MIS.git
cd SSL4MIS
-
Download the processed data and put the data in
../data/BraTS2019or../data/ACDC, please read and follow the README. -
Train the model
cd code
python train_XXXXX_3D.py or python train_XXXXX_2D.py or bash train_acdc_XXXXX.sh
- Test the model
python test_XXXXX.py
- Mean Teacher[2D/3D]
- Entropy Minimization[2D/3D]
- Deep Adversarial Networks[2D/3D]
- Uncertainty Aware Mean Teacher[2D/3D]
- Interpolation Consistency Training[2D/3D]
- Uncertainty Rectified Pyramid Consistency[2D/3D]
- Cross Pseudo Supervision[2D/3D]
- Cross Consistency Training[2D]
- Deep Co-Training[2D]
- Cross Teaching between CNN and Transformer[2D]
- Regularized Dropout[2D/3D]
- Part of the code is adapted from open-source codebase and original implementations of algorithms, we thank these author for their fantastic and efficient codebase, such as, UA-MT, Attention-Gated-Networks and segmentatic_segmentation.pytorch .