I trained an AI to generate German placenames

Book your summer vacation in Mörchstedt/Inbach

Last week, while on vacation, I read Dan Hon’s post on generating British placenames using a Torch RNN.

I trained an A.I. to generate British placenames

“I can do this, too” or more accurately “das kann ich auch”, I thought and resolved to try this as soon as I got home from my trip (packing too much computing power and relaxation do not mix).

Looks great, sounds great, doesn’t exist.

The instructions in Dan’s post are quite easy to follow, I just went with the docker image (remember to set -gpu -1 at the end of every command line).

Fake Towns

The biggest challenge, as in so many deep learning projects was to find a good data set. Fortunately the German statistics office offers the aptly-named Gemeindeverzeichnis-Informationssystem GV-ISys des Statistischen Bundesamtes der Bundesrepublik Deutschland.

Want to go there? It’s still fake, I’m sorry.

You can download the Excel or plain text data files (not CSV, but easy enough to clean up with a little bit of sed-fu and then train your RNN. In the next step, you can then generate long lists of German-sounding place names like this one.

To make things even more believable, create little postcards for each of the towns using Adobe Spark.