GPU Setup

gpu_setup.md

1. Check GPU capability
   https://developer.nvidia.com/cuda-gpus#compute

2. Check TF version configurations with Cuda
   https://www.tensorflow.org/install/source#tested_build_configurations
   https://www.tensorflow.org/install/gpu

3. Cuda Installation
   Guide
   https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#ubuntu-installation
   https://developer.nvidia.com/cuda-toolkit-archive

   Removing Cuda
   https://askubuntu.com/questions/530043/removing-nvidia-cuda-toolkit-and-installing-new-one

   cuDNN Installation
   https://docs.nvidia.com/deeplearning/sdk/cudnn-install/index.html#installlinux
   https://developer.nvidia.com/rdp/cudnn-archive

4. Check if Cuda installed
   https://arnon.dk/check-cuda-installed/
   $nvcc -V

5. Check if Tensorflow using GPU
   https://stackoverflow.com/questions/38009682/how-to-tell-if-tensorflow-is-using-gpu-acceleration-from-inside-python-shell

   import tensorflow as tf
   
   assert tf.test.is_gpu_available()
   assert tf.test.is_built_with_cuda()
   

   TF GPU Usage guide
   https://www.tensorflow.org/guide/gpu