Since you will deal with intense computational requirements, your choice of GPU will determine your deep learning algorithms. So it is critical to making right choice for GPU.I can recommend Titan X Pascal. Good luck.
I don't think so, this is a 1 GB main memory device, if you are thinking on exploring small things maybe you can do something. But if you are thinking on doing some real work then it won't be enough. Efehan's advice is definitively a good one, although expensive :)
I also would recommend something better. It is definitely OK for developing code (for example on your laptop) or validating results, but you won't get the expected benefits of using GPUs. If you have access to an HPC facility, you might be able to use better cards such as Tesla K20, K40 or K80.
If you want to use GPU then you are looking forward to use cuDNN library of nvidia. CuDNN supports GPU cards with compute capability >=3.0. so M320 is out of question (CC = 1.2). Since it is cuda capable card, you can use it for learning cuda and opencl.
- Badges
- Science topic