STalign

①Install

需要手动将STalign.git上传到服务器上。

/cwStorage/home/chenzhh/package/python/STalign-main

然后mamba安装

mamba create -f /cwStorage/home/chenzhh/Env/STalign.yml

其中，STAlign.yml内容如下：

name: STalign
channels:
  - pytorch
  - nvidia
  - conda-forge
dependencies:
  - python=3.8
  - pip
  - numpy=1.23.4
  - pandas=2.0.0
  - networkx=3.1
  - scikit-image
  - matplotlib
  - plotly=5.14.1
  - tenacity=8.2.2
  - openpyxl=3.1.1
  - et_xmlfile=1.1.0
  - pillow=9.5.0
  - requests=2.28.1
  - pyyaml=6.0
  - filelock=3.11.0
  - webencodings=0.5.1
  - yarg=0.1.9
  - imagesize=1.4.1
  - kiwisolver=1.4.4
  - fonttools=4.39.3
  - docopt=0.6.2
  - pygments=2.15.0
  - markdown-it-py=2.2.0
  - mdit-py-plugins=0.3.5
  - mdurl=0.1.2
  - mpmath=1.3.0
  - pytz=2023.3
  - pynrrd=1.0.0
  - nptyping=2.5.0
  - sympy=1.11.1
  - tornado=6.2

然后安装对应依赖和源包安装

cd /cwStorage/home/chenzhh/package/python/STalign-main
pip install .

安装kernel

mamba install ipykernel -y
python -m ipykernel install --user --name stalign --display-name "Py38 STalign"

为了适配服务器CUDA版本，重新安装pytorch

pip install torch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 \
  --index-url https://download.pytorch.org/whl/cu121

⚠️待解决报错信息

  WARNING: Failed to remove contents in a temporary directory '/cwStorage/home/chenzhh/miniforge3/envs/STalign/lib/python3.8/site-packages/~vfuser'.
  You can safely remove it manually.
  WARNING: Failed to remove contents in a temporary directory '/cwStorage/home/chenzhh/miniforge3/envs/STalign/lib/python3.8/site-packages/torch/~ib'.
  You can safely remove it manually.
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
stalign 1.0 requires torch==2.0.0, but you have torch 2.4.1+cu121 which is incompatible.
Successfully installed fsspec-2025.3.0 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.9.86 nvidia-nvtx-cu12-12.1.105 torch-2.4.1+cu121 torchaudio-2.4.1+cu121 torchvision-0.19.1+cu121 triton-3.0.0

②代码模板