DeepDream
ディープドリーム / 2015– / Technique / Art numérique
Google's visualization technique repeatedly amplifies features learned by an image-recognition network, making eyes, animals and towers emerge excessively from clouds, rocks and leaves until misrecognition becomes a recursive hallucinatory surface.
Eyes and animal faces repeated across the frame / Swirling texture multiplying along source contours / Multi-scale repetition that reveals new figures when viewed closer / Saturated blue, yellow and violet rolling continuously
Entrée du dictionnaire
- Usages idéaux
- Exhibits and critical images that make machine misrecognition immediately visible · Music video and cover imagery that keeps a source landscape beneath a multi-scale hallucination
- Typographie
- Add type after processing, keeping it short, bold and simple enough not to fight the detail.
- Composition
- Preserve the source's large composition and amplify related features at several scales to create recursion into depth.
- Matière
- Choose layers in a trained vision model and iteratively increase their activation through gradient ascent.
- Précaution
- It is not a swirl filter or pasted dog faces. Preserve which layer and feature were amplified and how they bind to the source.
- Pour approfondir
- Feature visualization and layer selection / Iterative zoom and octave scales / GoogLeNet ImageNet feature bias
Entrées liées
Citer cette entrée
Le dictionnaire est fait pour être lié. Prenez la forme qui convient là où vous écrivez.
- Link
- https://indexstyle.org/fr/styles/deepdream
- Markdown
- [DeepDream — IndexStyle](https://indexstyle.org/fr/styles/deepdream)
- HTML
- <a href="https://indexstyle.org/fr/styles/deepdream">DeepDream — IndexStyle</a>