Skip to content

Instantly share code, notes, and snippets.

@revilokeb
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
@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
revilokeb / setup_tf_serving_cuda_docker_v0.2
Last active October 16, 2017 06:42
Setting up Tensorflow Serving with CUDA 7.5 / cuDNN5 on Docker based on TF Serving commit from May 2016
# Create docker image with TF serving on GPU
# Ubuntu 14.04 LTS with nvidia-docker (https://github.com/NVIDIA/nvidia-docker)
# docker: docker bash
# host: bash on host machine
#host, pull nvidia-docker latest
nvidia-docker pull nvidia/cuda
#docker, start docker bash
nvidia-docker run --rm -ti -v /myhosthome:/mydockerhome nvidia/cuda:latest bash
@revilokeb
revilokeb / setup_tf_serving_cuda_docker_v0.1
Last active March 14, 2018 23:57
Setting up Tensorflow Serving with CUDA 7.5 / cuDNN5 on Docker - error "missing dependency ... eigen3/Eigen/Core..."
# Create docker image with TF serving on GPU
# Ubuntu 14.04 LTS with nvidia-docker (https://github.com/NVIDIA/nvidia-docker)
# docker: docker bash
# host: bash on host machine
#host, pull nvidia-docker latest
nvidia-docker pull nvidia/cuda
#docker, start docker bash
nvidia-docker run --rm -ti -v /myhosthome:/mydockerhome nvidia/cuda:latest bash
@revilokeb
revilokeb / wide_residual_net_28_10_dropout_caffe
Created June 10, 2016 05:59
caffe train_val for training wide residual nets with dropout wrn_28_10_dropout
name: "wrn_28_10_dropout"
layer {
name: "Data1"
type: "Data"
top: "Data1"
top: "Data2"
include {
phase: TRAIN
}
transform_param {
@revilokeb
revilokeb / wide_residual_net_28_10_solver_caffe
Created June 7, 2016 21:05
Caffe solver for training wide residual net wrn_28_10
net: "MY_PATH/wrn_28_10_train_val.prototxt"
test_iter: 157
test_interval: 390
test_initialization: false
iter_size: 1
#type: "RMSProp"
#rms_decay: 0.9
#delta: 1.0
type: "Nesterov"
display: 390
@revilokeb
revilokeb / wide_residual_net_28_10_caffe
Created June 7, 2016 21:01
Caffe train_val for training wide residual net wrn_28_10 on CIFAR10
name: "wrn_28_10"
layer {
name: "Data1"
type: "Data"
top: "Data1"
top: "Data2"
include {
phase: TRAIN
}
transform_param {
@revilokeb
revilokeb / inception_resnet_v2_solver_2ndtry.txt
Created April 24, 2016 19:47
Caffe solver for learning inception-resnet-v2 - 2ndtry
net: "/inception_resnet_v2_train_test_2ndtry.prototxt"
test_iter: 25000
test_interval: 40000
test_initialization: false
iter_size: 1
type: "RMSProp"
rms_decay: 0.9
delta: 1.0
display: 500
average_loss: 1000
@revilokeb
revilokeb / inception_resnet_v2_train_val_2ndtry.txt
Created April 24, 2016 19:44
Caffe train_val for learning inception-resnet-v2 - 2ndtry
name: "Inception_Resnet2_Imagenet"
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
@revilokeb
revilokeb / dede.json
Created April 3, 2016 17:57
Packer template to automatically create AMI deepdetect_revilokeb_TIMESTAMP
{
"variables": {
"aws_access_key": "",
"aws_secret_key": ""
},
"builders": [{
"type": "amazon-ebs",
"access_key": "{{user `aws_access_key`}}",
"secret_key": "{{user `aws_secret_key`}}",
"region": "eu-west-1",