If you have a working experience on theano, you probably wouldn’t have forgot that such a pain in the ass task it was. So I felt it really worth to blog about it for people aspiring to get in Deep Learning. Installation instructions given on the official website are capable enough to break down the morale of any newbie who wants to get started. Follow the instructions
mentioned below to setup theano on Ubuntu.
After you have successfully setup cuda on your system you need to follow these instructions to install and integrate your Nvidia GPU with theano.
Please follow the instructions for theano installation:-
$sudo apt-get install python-numpy python-scipy python-dev python-pip python-nose g++ libopenblas-dev git $sudo pip install Theano
After installation following paths are to be added in the bashrc file
Add these paths at the end of the bashrc file-
(Make sure you check your cuda version and edit it accordingly in these path definations)
Following instructions need to be added in theanorc file
floatX = float32
device = gpu
fastmath = True
ldflags = -lopenblas
Once installation is done testing of theano on GPU can be done from the following code:-
Copy and paste the following code in python interpreter to test if GPU is integrated with theano.