Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo cya StyleGAN

Subiramo ikarita ya StyleGAN hamwe na synthesis, uburyo butandukanye bwo kuvanga, urusaku rukomeye, hamwe nimpinduka zubatswe muri StyleGAN2 na StyleGAN3.

Inzira zijyanye no kuyoboraImyubakire yububiko
Ikibazo 1 Bya 8

Niyihe ntego yo gushushanya ikarita ya StyleGAN?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niyihe ntego yo gushushanya ikarita ya StyleGAN?
    • Gutondekanya niba ishusho ari impamo cyangwa impimbano
    • Kugereranya amashusho kumurongo wo hejuru
    • Guhagarika ishusho yanyuma yo kubika
    • Guhindura ibyihishe z muburyo butandukanye hagati ya W.
  2. Muri StyleGAN yumwimerere, ni gute uburyo bwinjizwa mu ikarita iranga?
    • Muguhuza vector yihishe kuri buri pigiseli
    • Binyuze muri Adaptive Instance Normalisation (AdaIN)
    • Binyuze murwego rwanyuma rwa softmax
    • Gukoresha pisine
  3. Umuyoboro wa synthesis utangira iki aho kuba vector yihishe?
    • Kwiga guhoraho
    • Ifoto yo mumaso nyayo
    • Urusaku rwera rwera rufite ubunini busohoka
    • Ikarita
  4. Ni ubuhe buryo bwo guhindura uburyo bugaragara (buke-buke) bugenzura cyane cyane?
    • Uruhu rwiza rwuruhu
    • Ibara rya pigiseli imwe gusa
    • Urwego rwohejuru ruranga nka pose nuburyo bwo mumaso
    • Imiterere ya dosiye
  5. Ni ikihe kibazo StyleGAN2 yakemuye ugereranije numwimerere?
    • Yongeyeho inyandiko-ku-ishusho
    • Yakuyeho ibintu biranga blob nkibintu byatewe na AdaIN
    • Byakuyeho gukenera ivangura
    • Cyakoze imyitozo itagenzuwe neza kunshuro yambere
  6. Niki 'kuvanga uburyo' muri StyleGAN?
    • Guhuza imibare ibiri mbere yimyitozo
    • Kugereranya ibisubizo by'ivangura
    • Kuvanga amajwi nishusho yakozwe
    • Gukoresha w ibice bitandukanye mubice bitandukanye kugirango uhuze ibiranga amashusho abiri
  7. What role do separate per-layer noise inputs play in original StyleGAN synthesis?
    • They replace the mapping network's entire style representation
    • They determine the file's compression format
    • They supply stochastic fine detail, such as varying hair strands or freckles
    • They provide the discriminator's real-image labels
  8. What visual behavior did StyleGAN3's alias-free design target?
    • Texture sticking and aliasing that make details move unnaturally as image content changes
    • The absence of a text tokenizer in original StyleGAN
    • A requirement that every output be a grayscale photograph
    • The need to store generated images as audio waveforms