Hello Guys,
as one of many I have encountered the same frustrating warning regarding optimization with the DFC
[warning] Reducing optimization level to 0 (the accuracy won't be optimized and compression won't be used) because there's no available GPU
[warning] Running model optimization with zero level of optimization is not recommended for production use and might lead to suboptimal accuracy results
I’ve tried both the manual installation route and the docker container route, always facing the same issue.
I will only refer from this point on to the usage of the docker container, since it is the recommended way for using the DFC.
When I check in the ubuntu docker host (in WSL) the nvidia driver will be detected
NVIDIA-SMI 565.77.01 Driver Version: 566.36 CUDA Version: 12.7
But starting the docker container the driver won’t be found:
WARNING: The NVIDIA Driver was not detected. GPU functionality will not be available.
Use the NVIDIA Container Toolkit to start this container with GPU support; see
https://docs.nvidia.com/datacenter/cloud-native/ .
Also the nvidia-smi command is unknown to the docker container.
cuDNN 8.9 seems to be active inside the container:
(hailo_virtualenv) hailo@DESKTOP-Q07QB8F:/local/workspace$ dpkg -l | grep cudnn
ii cudnn-local-repo-ubuntu2204-8.9.0.131 1.0-1 amd64 cudnn-local repository configuration files
hi libcudnn8 8.9.6.50-1+cuda11.8 amd64 cuDNN runtime libraries
and CUDA 11.8 too:
(hailo_virtualenv) hailo@DESKTOP-Q07QB8F:/local/workspace$ dpkg -l | grep cuda
hi cuda-cccl-11-8 11.8.89-1 amd64 CUDA CCCL
hi cuda-compat-11-8 520.61.05-1 amd64 CUDA Compatibility Platform
hi cuda-cudart-11-8 11.8.89-1 amd64 CUDA Runtime native Libraries
hi cuda-cudart-dev-11-8 11.8.89-1 amd64 CUDA Runtime native dev links, headers
hi cuda-driver-dev-11-8 11.8.89-1 amd64 CUDA Driver native dev stub library
hi cuda-keyring 1.0-1 all GPG keyring for the CUDA repository
hi cuda-libraries-11-8 11.8.0-1 amd64 CUDA Libraries 11.8 meta-package
hi cuda-nvcc-11-8 11.8.89-1 amd64 CUDA nvcc
hi cuda-nvrtc-11-8 11.8.89-1 amd64 NVRTC native runtime libraries
hi cuda-nvtx-11-8 11.8.86-1 amd64 NVIDIA Tools Extension
hi cuda-toolkit-11-8-config-common 11.8.89-1 all Common config package for CUDA Toolkit 11.8.
hi cuda-toolkit-11-config-common 11.8.89-1 all Common config package for CUDA Toolkit 11.
hi cuda-toolkit-config-common 12.3.52-1 all Common config package for CUDA Toolkit.
hi libcudnn8 8.9.6.50-1+cuda11.8 amd64 cuDNN runtime libraries
hi libnccl2 2.15.5-1+cuda11.8 amd64 NVIDIA Collective Communication Library (NCCL) Runtime
Of course, I’ve installed nvidia-docker2 before I’ve started the container
distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
&& curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add - \
&& curl -s -L \
https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list \
| sudo tee /etc/apt/sources.list.d/nvidia-docker.list
sudo apt-get update
sudo apt-get install -y nvidia-docker2
sudo systemctl restart docker
Sorry for the formatting of the terminal content looks like crap.