zoe2718
commented
2 years ago Here is the command line output when running ./run_sample.sh --build-container:
Sending build context to Docker daemon 11.36MB Step 1/14 : ARG BASE_IMAGE=pytorch/pytorch:1.7.1-cuda11.0-cudnn8-devel Step 2/14 : FROM $BASE_IMAGE ---> 7554ac65eba5 Step 3/14 : RUN apt-get update && apt-get install -y --no-install-recommends pkg-config libglvnd0 libgl1 libglx0 libegl1 libgles2 libglvnd-dev libgl1-mesa-dev libegl1-mesa-dev libgles2-mesa-dev cmake curl ---> Using cache ---> 2021ade4a5c8 Step 4/14 : ENV PYTHONDONTWRITEBYTECODE=1 ---> Using cache ---> ca9221b6d071 Step 5/14 : ENV PYTHONUNBUFFERED=1 ---> Using cache ---> ec3e675141ce Step 6/14 : ENV LD_LIBRARY_PATH /usr/lib64:$LD_LIBRARY_PATH ---> Using cache ---> 54956580fb6d Step 7/14 : ENV NVIDIA_VISIBLE_DEVICES all ---> Using cache ---> 400b43470c33 Step 8/14 : ENV NVIDIA_DRIVER_CAPABILITIES compute,utility,graphics ---> Using cache ---> 1bead4e2f9e5 Step 9/14 : ENV PYOPENGL_PLATFORM egl ---> Using cache ---> 2ac6364927ab Step 10/14 : COPY docker/10_nvidia.json /usr/share/glvnd/egl_vendor.d/10_nvidia.json ---> Using cache ---> f7bcbcf17535 Step 11/14 : RUN pip install ninja imageio imageio-ffmpeg ---> Running in 40f85408f32e Collecting ninja Downloading ninja-1.10.2.3-py2.py3-none-manylinux_2_5_x86_64.manylinux1_x86_64.whl (108 kB) Collecting imageio Downloading imageio-2.13.0-py3-none-any.whl (3.3 MB) Collecting imageio-ffmpeg Downloading imageio_ffmpeg-0.4.5-py3-none-manylinux2010_x86_64.whl (26.9 MB) Collecting pillow>=8.3.2 Downloading Pillow-8.4.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.1 MB) Requirement already satisfied: numpy in /opt/conda/lib/python3.8/site-packages (from imageio) (1.19.2) Installing collected packages: ninja, pillow, imageio, imageio-ffmpeg Attempting uninstall: pillow Found existing installation: Pillow 8.1.0 Uninstalling Pillow-8.1.0: Successfully uninstalled Pillow-8.1.0 Successfully installed imageio-2.13.0 imageio-ffmpeg-0.4.5 ninja-1.10.2.3 pillow-8.4.0 Removing intermediate container 40f85408f32e ---> 7d9a9bf8ff95 Step 12/14 : COPY nvdiffrast /tmp/pip/nvdiffrast/ ---> e07b7ff78278 Step 13/14 : COPY README.md setup.py /tmp/pip/ ---> a985488b664c Step 14/14 : RUN cd /tmp/pip && pip install . ---> Running in bafb10e7d7e5 Processing /tmp/pip Requirement already satisfied: numpy in /opt/conda/lib/python3.8/site-packages (from nvdiffrast==0.2.7) (1.19.2) Building wheels for collected packages: nvdiffrast Building wheel for nvdiffrast (setup.py): started Building wheel for nvdiffrast (setup.py): finished with status 'done' Created wheel for nvdiffrast: filename=nvdiffrast-0.2.7-py3-none-any.whl size=92264 sha256=bcb73fab8d4628893c608442ab57cde8fc5cddd963469b2b545bba14b5533e71 Stored in directory: /tmp/pip-ephem-wheel-cache-vkr9plma/wheels/3c/e6/6c/927e643f0816c802008017bea0b43743b6e13629535e616820 Successfully built nvdiffrast Installing collected packages: nvdiffrast Successfully installed nvdiffrast-0.2.7 Removing intermediate container bafb10e7d7e5 ---> e5fd4265b280 Successfully built e5fd4265b280 Successfully tagged name:tagname
No python sample given or file '' not found. Exiting.
s-laine
Environment：
cuda 11.2
I have tried pytorch:1.8.0-cuda11.1-cudnn8 and pytorch:1.7.1-cuda11.0-cudnn8, but both are failed. I use the provided Dockerfile with only pytorch and cuda version changed. The command _bash ./runsample.sh --build-container (or docker build -f docker/Dockerfile -t name:tagname .) can be executed successfully, but after that the nvdiffrast is still not installed (when import nvdiffrast.torch, raise ModuleNotFoundError: No module named 'nvdiffrast.torch').
I have successfully installed nvdiffrast with the same steps on 2080ti GPU+cuda10.2, but failed on 3090 GPU+cuda11.2. Is there anyone know how to install nvdiffrast on 3090 GPU? Thanks.