README.md

cppn-gan-vae tensorflow

setup

Note: for matplotlib to work, use python standardlib venv instead of "virtualenv".

python3 -m venv ./venv3
source ./venv3/bin/activate
pip install -r requirements.txt
pip install -r requirements-dev.txt

colab tips

tensorboard_in_notebooks.ipynb - Colaboratory

# Load the TensorBoard notebook extension

%load_ext tensorboard

# start t-board:

%tensorboard --logdir logs

Working with external data:

from google.colab import drive
drive.mount('/content/drive')

reload imports:

%load_ext autoreload
%autoreload 2

Errors-and-Debugging.ipynb - Colaboratory

%debug

# or

%pdb on

tensorflow notes

tf.compat.v1.train.Saver  |  TensorFlow Core v2.4.1

datasets

zalandoresearch/fashion-mnist: A MNIST-like fashion product database. Benchmark

about

Train Compositional Pattern Producing Network as a Generative Model, using Generative Adversarial Networks and Variational Autoencoder techniques to produce high resolution images.

Run python train.py from the command line to train from scratch and experiment with different settings.

sampler.py can be used inside IPython to interactively see results from the models being trained.

See my blog post at blog.otoro.net for more details.

I tested the implementation on TensorFlow 0.60.

Used images2gif.py written by Almar Klein, Ant1, Marius van Voorden.

License

BSD - images2gif.py

MIT - everything else