cuDNN not available: how to fix on Linux

Download CudNN from NVidia

$ python
Python 2.7.12 (default, Jul  1 2016, 15:12:24)
[GCC 5.4.0 20160609] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import theano
Using gpu device 0: GeForce GTX 1060 6GB (CNMeM is enabled with initial size: 95.0% of memory, cuDNN not available)

Download the CudNN for your OS

https://developer.nvidia.com/cudnn

http://deeplearning.net/software/theano/library/sandbox/cuda/dnn.html

• Alternatively, on Linux, you can set the environment variables LD_LIBRARY_PATH, LIBRARY_PATH and CPATH to the directory extracted from the download. If needed, separate multiple directories with : as in the PATH environment variable.
  example:
  

  export LD_LIBRARY_PATH=/home/user/path_to_CUDNN_folder/lib64:$LD_LIBRARY_PATH
  export CPATH=/home/user/path_to_CUDNN_folder/include:$CPATH
  export LIBRARY_PATH=/home/user/path_to_CUDNN_folder/lib64:$LD_LIBRARY_PATH 

sudo mkdir /usr/local/cudnn
sudo mkdir /usr/local/cudnn
cp cuda/* /usr/local/cudnn

add the following to your ~/.bashrc
export CUDNN_ROOT=/usr/local/cudnn
export LD_LIBRARY_PATH=$CUDNN_ROOT/lib64:$LD_LIBRARY_PATH
export CPATH=$CUDNN_ROOT/include:$CPATH
export LIBRARY_PATH=$CUDNN_ROOT/lib64:$LD_LIBRARY_PATH

Fixed:
$ python
Python 2.7.12 (default, Jul  1 2016, 15:12:24)
[GCC 5.4.0 20160609] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import theano
Using gpu device 0: GeForce GTX 1060 6GB (CNMeM is enabled with initial size: 95.0% of memory, cuDNN 5105)
>>>