DeepDream

ディープドリーム / 2015– / 기법 / 디지털 아트

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

DeepDream — AI가 생성한 해석 이미지 — AI가 생성한 해석 이미지입니다. 참고 작품이 아닙니다

사전 항목

적합한 용도: 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
타이포그래피: Add type after processing, keeping it short, bold and simple enough not to fight the detail.
구성: Preserve the source's large composition and amplify related features at several scales to create recursion into depth.
재료: Choose layers in a trained vision model and iteratively increase their activation through gradient ascent.
주의: It is not a swirl filter or pasted dog faces. Preserve which layer and feature were amplified and how they bind to the source.
더 읽을거리: Feature visualization and layer selection / Iterative zoom and octave scales / GoogLeNet ImageNet feature bias

이 항목을 인용하기

사전은 링크되기 위해 있다. 글을 쓰는 자리에 맞는 형식을 그대로 가져가면 된다.

Link: https://indexstyle.org/ko/styles/deepdream
Markdown: [DeepDream — IndexStyle](https://indexstyle.org/ko/styles/deepdream)
HTML: <a href="https://indexstyle.org/ko/styles/deepdream">DeepDream — IndexStyle</a>

색인의 원래 위치로

사전 항목

관련 항목

이 항목을 인용하기