Experiments performed using reference methods to benchmark for ViM-UNet described in our preprint (accepted to MIDL 2024 - Short Paper):
Here is the detailed instruction on how to install nnU-Net.
TLDR:
$ git clone https://github.com/MIC-DKFZ/nnUNet.git
$ cd nnUNet
$ pip install -e .
Here is the detailed instruction on how to install U-Mamba.
Below is my piece of installation (dropping it here as some parts needed some attention)
Create a new mamba environment:
$ mamba env create -n umamba python=3.10 -y
$ mamba activate umamba
Install PyTorch
:
mamba install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia
Install packaging: pip install packaging
CUDA_HOME
needs to match the installed cuda version, and the path should be visible. For HLRN users, here's an example:export CUDA_HOME=/usr/local/cuda-11.8/
.
causal-conv1d
: pip install causal-conv1d==1.1.1
pip install mamba-ssm
U-Mamba/data
for performing the experiments)
$ git clone https://github.com/bowang-lab/U-Mamba.git
$ cd U-Mamba/umamba
$ pip install -e .
To cite our paper: