Skip to content

Repository files navigation

CardiacSeg

The official implementation of paper "Customizing Pre-Training Volumetric Transformers with Scaling Pyramid for 3D Cardiac Segmentation".

Getting Started

1. Clone the Project & Install Requirements

git clone git@openi.pcl.ac.cn:OpenMedIA/CardiacSeg.git
pip install -r requirements.txt

2. Training

cd CardiacSeg
sh scripts/train_imagechd.sh

3. Inference

python inference.py --ckpt_url {model_path} --in_file {data_path} --out_file {output_path}

Our CardiacSeg model trained on the ImageCHD dataset can be downloaded here.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages