Skip to content
An attempt to train a Tensorflow convnet to provide machine guided image aesthetics
Jupyter Notebook Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
notebooks
pysrc/tfaesthetics
.gitignore
LICENSE
README.md

README.md

Getting up and running with TensorFlow

Installation

sudo apt install nvidia-cuda-toolkit
  • Get cuDNN v4 from https://developer.nvidia.com/cudnn -- this will require signing up to the developer program. Use locate cuda.h and locate libcuda.so to find the right place to copy these. The following works on Ubuntu 16.04.
tar xvzf cudnn-7.*
sudo cp cuda/include/cudnn.h /usr/include/cuda
sudo cp cuda/lib64/libcudnn* /usr/lib/x86_64-linux-gnu/
sudo chmod a+r /usr/include/cudnn.h /usr/lib/x86_64-linux-gnu/libcudnn*
  • Install using conda
conda create -n tensorflow-gpu python=3.5 anaconda
source activate tensorflow-gpu
pip install jupyter pandas tables matplotlib
export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow-0.10.0rc0-cp35-cp35m-linux_x86_64.whl
pip install --ignore-installed --upgrade ${TF_BINARY_URL}
  • Test that the install has been successful
python -c "import tensorflow"
  • Install bazel: see here
echo "deb [arch=amd64] http://storage.googleapis.com/bazel-apt stable jdk1.8" | sudo tee /etc/apt/sources.list.d/bazel.list
curl https://storage.googleapis.com/bazel-apt/doc/apt-key.pub.gpg | sudo apt-key add -
sudo apt update
sudo apt install bazel swig
You can’t perform that action at this time.