Docker build Error about mmfashion

[RoganInglis]

This seems to be related to the cuda repo key rotation that happened earlier this year. More info here.

I was able to get it to build by adding this line to the docker file, before the apt-get update line:

RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub

(after building there are still problems with even the test scripts, I decided not to use this repo in the end)

[maizer2]

NVIDIA/nvidia-container-toolkit#257

ARG PYTORCH="1.5"
ARG CUDA="10.1"
ARG CUDNN="7"

FROM pytorch/pytorch:1.5-cuda10.1-cudnn7-devel

ENV TORCH_CUDA_ARCH_LIST="6.0 6.1 7.0+PTX"
ENV TORCH_NVCC_FLAGS="-Xfatbin -compress-all"
ENV CMAKE_PREFIX_PATH="$(dirname $(which conda))/../"

RUN rm /etc/apt/sources.list.d/cuda.list
RUN rm /etc/apt/sources.list.d/nvidia-ml.list
RUN apt-get update && apt-get -y dist-upgrade \
    && apt-get install -y git libglib2.0-0 libsm6 libxrender-dev \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# Install mmfashion
RUN conda clean --all
RUN git clone --recursive https://github.com/open-mmlab/mmfashion.git /mmfashion
WORKDIR /mmfashion
ENV FORCE_CUDA="1"
RUN pip install -r requirements.txt
RUN pip install --no-cache-dir -e .