Continuing the discussion from Jetson Nano 2GB, dlib in dockerfile:
Hello, I got the same error as mentioned in the previous topic.
In this case, I did not add a ‘runtime’ option while running the docker command.
Below is what I did.
docker command:
docker run -it --rm --runtime nvidia --network host nvcr.io/nvidia/l4t-ml:r32.7.1-py3
git clone dlib
git clone -b 'v19.21' --single-branch https://github.com/davisking/dlib.git dlib
cd dlib/ && mkdir build
cd build/ && cmake ..
cmake logs...
-- Found cuDNN: /usr/lib/aarch64-linux-gnu/libcudnn.so
-- Building a CUDA test project to see if your compiler is compatible with CUDA...
-- Building a cuDNN test project to check if you have the right version of cuDNN installed...
-- Enabling CUDA support for dlib. DLIB WILL USE CUDA
-- C++11 activated.
-- Configuring done
-- Generating done
-- Build files have been written to: /dlib/build/temp.linux-aarch64-3.6
cmake --build .
cd ../
python3 setup.py install
After build
Python 3.6.9 (default, Dec 8 2021, 21:08:43)
[GCC 8.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import dlib
>>> print(dlib.DLIB_USE_CUDA)
True
I hope this helps.
Thank you