Notebook for O'Reilly's "Deep Convolutional Generative Adversarial Networks"
In this tutorial, we will try to build a GAN that is able to generate human faces with TensorFlow. Sounds scary, doesn’t it?
This repository contains source code corresponding to our article "Deep Convolutional Generative Adversarial Networks with TensorFlow".
Go to your home directory by opening your terminal and entering cd ~
Clone the repository by entering
git clone https://github.com/dmonn/dcgan-oreilly.git
After cloning the repo to your machine, enter
docker build -t dcgan_<image_type> -f ./dockerfiles/Dockerfile.<image_type> ./dockerfiles/
where <image_type>
is either gpu
or cpu
. (Note that, in order to run these files on your GPU, you'll need to have a compatible GPU, with drivers installed and configured properly as described in TensorFlow's documentation.)
Run the Docker image by entering
docker run -it -p 8888:8888 -v <path to repo>:/root dcgan_<image_type>
where <image_type>
is either gpu
or cpu
, depending on the image you built in the last step.
After building, starting, and attaching to the appropriate Docker container, run the provided Jupyter notebooks by entering
jupyter notebook --ip 0.0.0.0
and navigate to http://0.0.0.0:8888 in your browser.
Choose DCGANs with Tensorflow.ipynb
to open the Notebook.
If you receive an error of the form:
WARNING: Error loading config file:/home/rp/.docker/config.json - stat /home/rp/.docker/config.json: permission denied
Got permission denied while trying to connect to the Docker daemon socket at unix:///var/run/docker.sock: Get http://%2Fvar%2Frun%2Fdocker.sock/v1.26/images/json: dial unix /var/run/docker.sock: connect: permission denied
It's most likely because you installed Docker using sudo permissions with a packet manager such as brew
or apt-get
. To solve this permission denied
simply run docker with sudo
(ie. run docker
commands with sudo docker <command and options>
instead of just docker <command and options>
).
If you don't have or don't want to use Docker, you can follow these steps to setup the notebook.
Install miniconda using one of the installers and the miniconda installation instructions. Use Python3.6.
After the installation, create a new virtual environment, using this command.
$ conda create -n dcgan
$ source activate venv
You are now in a virtual environment. Next up, install TensorFlow by following the instructions.
To install the rest of the dependenies, navigate into your repository and run
$ pip install -r dockerfiles/requirements.txt
Now you can run
jupyter notebook
to finally start up the notebook. A browser should open automatically. If not, navigate to http://127.0.0.1:8888 in your browser.
Choose DCGANs with Tensorflow.ipynb
to open the Notebook.
A helper function will download the CelebA dataset to your machine. This will need up to 3GB of disk space!