Question: Execution error (stopped and won't proceed)
BioSpace9 opened this issue · comments
I attempted to launch localcolabfold from the following Docker image, but it stopped partway through execution and wouldn't proceed.
FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04
ENV PATH="/root/miniconda3/bin:${PATH}"
ARG PATH="/root/miniconda3/bin:${PATH}"
WORKDIR /root
RUN ln -sf /usr/share/zoneinfo/Asia/Tokyo /etc/localtime
RUN apt-get update && apt-get install -y --no-install-recommends \
build-essential \
cmake \
curl \
dssp \
git \
vim \
wget \
ca-certificates \
libjpeg-dev \
libpng-dev && \
rm -rf /var/lib/apt/lists/* \
&& wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \
&& mkdir /root/.conda \
&& bash Miniconda3-latest-Linux-x86_64.sh -b \
&& rm -f Miniconda3-latest-Linux-x86_64.sh \
&& conda --version
RUN conda update -n base -c defaults conda \
&& conda config --set ssl_verify no \
&& conda init bash \
&& conda clean -afy
ARG env_name=localcolabfold
RUN conda create -n ${env_name} -y \
python=3.8 \
pytorch=1.11 \
pyg \
jupyterlab \
biopython \
abnumber \
anarci \
logomaker \
numpy==1.21.5 \
pandas \
pathlib2 \
matplotlib \
seaborn \
scipy==1.7.3 \
requests==2.28.1 \
packaging pip \
openmm==7.7.0 \
pdbfixer \
-c pytorch -c dglteam -c pyg -c conda-forge -c bioconda
# Acitivate environment
ENV CONDA_DEFAULT_ENV ${env_name}
# Switch default environment
RUN echo "conda activate ${env_name}" >> ~/.bashrc
ENV PATH /opt/conda/envs/${env_name} /bin:$PATH
WORKDIR /work
RUN wget https://raw.githubusercontent.com/YoshitakaMo/localcolabfold/main/install_colabbatch_linux.sh
RUN bash install_colabbatch_linux.sh
RUN cd localcolabfold
ENV PATH="/work/localcolabfold/colabfold-conda/bin:${PATH}"
/work/localcolabfold/colabfold-conda/bin/colabfold_batch --amber --num-recycle 3 --use-gpu-relax inputfile outputdir
2024-04-02 15:00:28,123 Running colabfold 1.5.5 (61df3b853140ca79dbdf64349824beb14364ebfd)
WARNING: You are welcome to use the default MSA server, however keep in mind that it's a
limited shared resource only capable of processing a few thousand MSAs per day. Please
submit jobs only from a single IP address. We reserve the right to limit access to the
server case-by-case when usage exceeds fair use. If you require more MSAs: You can
precompute all MSAs with `colabfold_search` or host your own API and pass it to `--host-url`
2024-04-02 15:00:28,789 Running on GPU
2024-04-02 15:00:29,077 generated new fontManager
2024-04-02 15:00:29,336 Found 6 citations for tools or databases
2024-04-02 15:00:29,336 Query 1/1: sp_P61823 (length 150)
2024-04-02 15:00:29,672 Setting max_seq=512, max_extra_seq=2404
Regarding the setup, initially, the GPU was not recognized (no GPU detected, will be using CPU). And after installing cuDNN, I encountered the aforementioned issue.
If anyone knows a solution, I would appreciate your guidance.