As with every one of these networks, data is life. Without good data, there's no way our network will be effective. In this case, we'll take advantage of data sources from the authors of the aforementioned paper to experiment with this network.
We always need to ensure that we're building the right structure in our repository. A tidy workspace will lead to cleaner code—trust me! The following tree is in our
Pix2Pix folder at our
$HOME directory in Ubuntu:
├── docker │ ├── build.sh │ ├── clean.sh │ └── Dockerfile ├── README.md ├── run.sh └── src | ├──
Create placeholders for all of the shell scripts in the
docker folder; go ahead and make the
src directory, which we'll use throughout this book.