To download CUDA, download the CUDA toolkit from the CUDA Downloads site.

1. Select "Linux"

2. Select your system's architecture

   1. Our installation used the "x86_64" architecture

3. Select "Ubuntu"

4. Select your Ubuntu version

   1. Our installation used version "16.04"

5. Select "runfile (local)" as the installer type.

The CUDA Downloads site can be found here.

NOTE: Steps were copied from https://covijn.com/2016/11/fixing-darknet-opencv3-make-error-convolutional_kernels/

To install CUDA after download, do the following:

1. Open a terminal and navigate to CUDA's download directory

2. Run the following command
   sudo sh cuda_<your_cuda_version>_linux.run -override

   1. Select Yes for every prompt

sudo sh Downloads/cuda_8.0.27_linux.run –silent –toolkit –override

export PATH=/usr/local/cuda-8.0/bin${PATH:+:${PATH}}

export LD_LIBRARY_PATH=/usr/local/cuda-8.0/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}

sudo nvidia-xconfig

Then install cuDNN (re-install if like us you had it installed before)

Download from https://developer.nvidia.com/rdp/cudnn-download#collapseTwo

do something like:

cd ~/Downloads/
tar xvf cudnn*.tgz
cd cuda
sudo cp */*.h /usr/local/cuda/include/
sudo cp */libcudnn* /usr/local/cuda/lib64/
sudo chmod a+r /usr/local/cuda/lib64/libcudnn*

Only AFTER all above steps install the cuda_8.0.27.1_linux.run:

sudo sh /Downloads/cuda_8.0.27.1_linux.run