revilokeb

revilokeb / tf_serving_cuda_inception_v3_client_on_docker_host

Created July 15, 2016 21:08

Tensorflow Serving with CUDA 7.5 / cuDNN5 on Docker serving inception v3, query with client from within docker and from host

	#docker, start with port 9000 as in TF serving example on old commit https://gist.github.com/revilokeb/02894302701fcea7ef4e85a92514e246
	nvidia-docker run --rm -ti -p 9000 -v /myhosthome:/mydockerhome tf_serving_old_commit_cuda7.5_cudnn5:latest bash

	#docker, upgrade six
	sudo pip install --upgrade six

	#docker, install grpcio
	sudo pip install grpcio

	#docker, download inception-v3 pre-trained model and export (https://tensorflow.github.io/serving/serving_inception.html)

revilokeb / cuda7.5_on_fresh_ubuntu_server_14

Created January 22, 2017 19:35

Installing CUDA 7.5 / cuDNN 5.1 on a fresh Ubuntu Server 14.04

	# following http://kislayabhi.github.io/Installing_CUDA_with_Ubuntu/
	# Problem was the following: package installer always installed CUDA 8.0
	# Run-File install as in https://devtalk.nvidia.com/default/topic/920308/how-to-install-cuda-7-5-with-the-newest-nvidia-driver-361-28-/ resulted in "login loop"

	# After setting up the OS in Ubuntu 14.04 there is initially only command line
	# Download: A reasonably up-to-date NVIDIA driver: http://www.nvidia.com/download/driverResults.aspx/98373/en-us#axzz41eljfR2P
	# Download: CUDA 7.5 Run-File: http://developer.download.nvidia.com/compute/cuda/7.5/Prod/local_installers/cuda_7.5.18_linux.run
	# Download: cuDNN 5.1

	sudo apt-get install build-essential