Marta RevueltaHEAD — Haute école d'Art et de Design Genève · Media Design
Marta Revuelta
Designer, Artist, Migrant & Researcher
About
2
Publications
55,994
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
0
Citations
Citations since 2017
Introduction
Marta Revuelta is graduated with a Master's degree in Media Design from the Geneva University of Art and Design — HEAD. She is currently doing research in facial profiling and machine learning. Her work explores technology as a set of new structures of control, highlighting their potential drifts and analyzing their impacts on our lives.
Her current projects include complex algorithmic processes and bring her to integrate the techniques of artificial intelligence into mechatronic constructions, thus revealing its computational mechanisms. She is interesting in installation art as an immersive medium. Her interdisciplinary works lie on the thin line that separates technology and the human, halfway between critical design and art, engineering and data science.
Education
September 2016 - June 2018
Haute école d'art et de design Genève — HEAD
Field of study
- Media Design
Publications
Publications (2)
Les technologies de l’intelligence artificielle (IA) sont en phase de développement rapide et sont largement adoptées. Les algorithmes déterminent ce que nous achetons sur les plates-formes d’achats en ligne, choisissent les publications que nous voyons sur le fil d’actualité de nos réseaux sociaux, suggèrent les résultats dans nos moteurs de reche...
Les technologies de l’intelligence artificielle (IA) sont en phase de développement rapide et sont largement adoptées. Les algorithmes déterminent ce que nous achetons sur les plates-formes d’achats en ligne, choisissent les publications que nous voyons sur le fil d’actualité de nos réseaux sociaux, suggèrent les résultats dans nos moteurs de reche...
Questions
Questions (3)
Hi all, I have a neural network that I want to train (keras, python...) and a big dataset of images divided into two classes following this architecture:
.../dataset/
| ClassName1/
| | img1.jpg
| | img2.jpg
| | ...
| ClassName2/
| img1.jpg
| ....
I know how to train my network with a dataset that fits in memory but in this case it is far too big.
I spent quite a bit of time looking for tutorials or examples but I could not find any really satisfying example on how to create a dataset with h5py and then feed it to the neural net.
Would anyone know of a good code example or could anyone point me in the right direction please ?
Thank you all for your esteemed help
Cheers
Hi everyone,
I downloaded the VGG facial dataset from here http://www.robots.ox.ac.uk/~vgg/data/vgg_face2/
but when you decompress the tar.gz file you only get one big 39 GB file. I would like to extract each picture from this dataset but I could not find any way to do it.
They provide a piece of matlab code with the dataset but I could not make it work, and not for the lack of trying.
If anyone could help me with this I would greatly appreciate.
I don't need to use the matlab code nor to train a neural net using the provided code, I simply need to rebuild the set of images out of the big binary file.
Thank you all for your help
Hi, I'm looking for a large dataset (+3000) of faces of common people to train a neural network for an artistic installation. Does anyone know of a downloadable large faces dataset ? thank you for your help.
