This is the official repository for "Drop The GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models" (paper, project page).

Please create environment as follows:

conda create -f environment.yml

To run the code, please do as follows:

conda activate dropthegan
python main.py <application> [<options>]

For example:

python main.py generation \
  --input-path="data/generation/balloons.png" \
  --output-path="out/generation/balloons.png"

You can list the applications by running:

python main.py --help

and to list the options for a given application by:

python main.py <application> --help

• Consider tuning parameters such as pyramid depth, alpha (i.e., completeness level), and noise standard-deviation for optimal results1.
• By default, the first GPU in the machine will be used, unless there are no GPUs and then it will run on CPU. You can override this default by providing the --device flag (cuda:X for GPU #X, or cpu for CPU)2.

Footnotes

1. A fixed set of parameters was used for the quantitative experiments in the paper. ↩

2. The runtime reported in the paper (2 seconds per generation) is for 250x180 images, running the generation application on a Tesla-V100 GPU. ↩