Installation steps for Deepstream 5.0 for x86_64

remove previous gst installations:

$ sudo rm -rf /usr/local/deepstream /usr/lib/x86_64-linux-gnu/gstreamer-1.0/libgstnv* /usr/bin/deepstream* /usr/lib/x86_64-linux-gnu/gstreamer-1.0/libnvdsgst*
/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream*
/opt/nvidia/deepstream/deepstream*
$ sudo rm -rf /usr/lib/x86_64-linux-gnu/libv41/plugins/libcuvidv4l2_plugin.so

install dependencies

$ sudo apt install \
    libssl1.0.0 \
    libgstreamer1.0-0 \
    gstreamer1.0-tools \
    gstreamer1.0-plugins-good \
    gstreamer1.0-plugins-bad \
    gstreamer1.0-plugins-ugly \
    gstreamer1.0-libav \
    libgstrtspserver-1.0-0 \
    libjansson4

install cuda drivers via apt

# sudo apt install cuda cuda-drivers nvidia-cuda-toolkit

install cudnn https://docs.nvidia.com/deeplearning/cudnn/install-guide/index.html install the runtime, developer and code samples sudo dpkg -i libcudnn8_x.x.x-1+cudax.x_amd64.deb (runtime) sudo dpkg -i libcudnn8-dev_8.x.x.x-1+cudax.x_amd64.deb (developer) sudo dpkg -i libcudnn8-samples_8.x.x.x-1+cudax.x_amd64.deb (code samples)

add to cuda and ld_library to $PATH

export PATH=/usr/local/cuda/bin:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda/lib64\${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}

Verification

check nvidia driver/cuda installation with:

nvidia-smi

check cuda:

nvcc  – version

check cudnn:

/sbin/ldconfig -N -v $(sed ‘s/:/ /’ <<< $LD_LIBRARY_PATH) 2>/dev/null | grep libcudnn

Install pycuda

https://medium.com/leadkaro/setting-up-pycuda-on-ubuntu-18-04-for-gpu-programming-with-python-830e03fc4b81

References: https://github.com/hsekia/learning-keras/wiki/How-to-install-Keras-to-Ubuntu-18.04

lackdaz/x86_deepstream_install.md

Verification

Install pycuda