Image Experiment Training – StyleGAN trained on Forest + Faces Data Sets
Generative and creative new ML’s aesthetic representation
TEST PATTERN: BLACK FOREST is an auto generative video based on ML training on 2 datasets: Forest and Faces.
The idea was born during the recent lockdown in Italy thanks to a friend who sent me an audio file containing environmental sounds from the Black Forest to alleviate the stress caused by containment.
Using the media as an auto representative fact, I tried to develop a sort of recollection of the machine with regard to the external world – in particular about the Black Forest setting.
The datasets used are easily about Forest (1500 img) and people faces (1500 img) and after two hours training the architecture of the forest has been modified by the facial features – giving back a new machine’s imaginative setting. The real sounds of the Black Forest constitute the soundtrack recollecting generative image memories to reality.
CREDITS: StyleGAN
Thanks to Cristina Ohlmer for the Black Forest sounds
Alessandra Arnò is a multimedia artist since 2000. Her research is currently evolving into the new digital media aesthetic and philosophical scenarios based on media, plus art theories based on the visual culture working with video libraries and collective memories. The other path on which her research is theoretically focused is the representation of the media as “itself” via AI and also ML.
Distributed by VISUALCONTAINER
