Ikibazo gihuza ibibazo · Biroroshye Urwego

Ikibazo GANs Ikibazo

Reba uburyo inyongeramusaruro zisabwa ziyobora imiyoboro yombi ya GAN, uburyo ivangura risuzuma ibice byombi, nuburyo inshinge zishobora guterwa.

Inzira zijyanye no kuyoboraGAN
Ikibazo 1 Bya 8

Ni irihe tandukaniro nyamukuru riri hagati ya GAN isabwa na GAN isanzwe?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Ni irihe tandukaniro nyamukuru riri hagati ya GAN isabwa na GAN isanzwe?
    • Igaburira amakuru yinyongera nkurwego rwicyiciro mumirongo yombi kugirango igenzure ibisohoka
    • Ikoresha amashanyarazi abiri
    • Ikuraho ivangura
    • Ikora gusa ku nyandiko, ntabwo ari amashusho
  2. Muri cGAN yatojwe kumibare yanditseho, niki wakora ko GAN isanzwe idashobora?
    • Kwiruka nta rusaku rwinjiza
    • Saba imibare yihariye nka '7'
    • Hunga ivangura burundu
    • Kora urusaku rwirabura-na-rwera gusa
  3. Niki cGAN ivangura igomba kugenzura, birenze niba ishusho isa nukuri?
    • Imiterere ya dosiye
    • Imyanzuro muri megapixels
    • Niba ishusho ihuye na label yatanzwe
    • Igipimo cyo kwiga
  4. Nubuhe buryo busanzwe bwo gutanga ibimenyetso bya generator?
    • Gusiba urusaku
    • Amahugurwa nta kirango na kimwe
    • Ukoresheje sensor yumubiri itandukanye
    • Guhuza ikirango kumajwi yinjira
  5. GANs zishyirwaho zashizeho urufatiro nubushobozi ki nyuma?
    • Inyandiko-ku-shusho hamwe n-ishusho-ku-bisekuruza
    • CPU yihuta
    • Akayunguruzo ka imeri
    • Kwerekana Ububikoshingiro
  6. Muburyo bugezweho bwo gukwirakwiza, igitekerezo cya cGAN cyo gutondeka gikunze kugaragara nkubuhe buryo?
    • Gukuramo ibiro bisanzwe
    • Kwambukiranya ibitekerezo ku nyandiko
    • Intoki ya pigiseli gusa
    • Guhagarika gahunda y'urusaku
  7. Why must a conditional discriminator see both the generated image and its conditioning label?
    • It uses the label to choose the learning-rate schedule
    • It converts the label into a random noise seed only
    • It needs to judge whether the image is realistic and whether it matches the requested condition
    • It prevents the generator from receiving noise
  8. Besides concatenating a class label to the noise vector, which conditioning method is described in the guide?
    • A spectral-radius constraint
    • An inverse Hessian update
    • A sequence-level BLEU reward
    • A projection layer that scores compatibility between label and image features