Unet 3D for cardiac segmentation.
- Linux or macOS or Win
- Python 3
- CPU or NVIDIA GPU + CUDA CuDNN
-
Install PyTorch and 0.4+ and other dependencies (e.g., torchvision, visdom and dominate).
- For Conda users, you can create a new Conda environment using
conda env create -f environment.yml.
- For Conda users, you can create a new Conda environment using
-
Clone this repo:
git clone https://github.com/lino202/3Dseg
cd 3DsegExplore data/create_dataset.py to get your data ready and before running init the visdom server if you would like to see the training proccess with
python -m visdom.serverOur code is inspired by pytorch-CycleGAN-and-pix2pix and topological-losses.