Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Hanuuninta Bilaashka ah Kala Soocida

Dib u eeg hanuuninta xorta ah ee kala soocida, ka tagista shuruuda leh, kala duwanaanta tayada tayada, kharashyada soo jeedinta, iyo qiyaasta hagida. Hubi baaxadda iyo malo-awaalka.

Wadooyinka haga ee la xidhiidhaKala soocida Hagidda Xorta ah
Su'aal 1 ee 8

Why do diffusion models apply classifier-free guidance?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Why do diffusion models apply classifier-free guidance?
    • Si loo xoojiyo sida ugu dhow ee wax soo saarku ula socdaan degdegga qaboojinta
    • Si loo cadaadiyo qaabka cabbir ka yar
    • Si aad gabi ahaanba meesha uga saarto codeeyaha qoraalka
    • Si sawirada loogu badalo maqal
  2. Sidee buu mooduhu u bartaa samaynta saadaalin shuruud la'aan ah ee hagitaan-free-classifier?
    • Iyadoo la tababarayo kala-saar labaad oo gaar ah
    • Adigoo si aan kala sooc lahayn u tuuraya qaboojinta xilliga tababarka
    • Adigoo isticmaalaya sawirro madow oo keliya
    • Adigoo curyaaminaya GPU-da
  3. Waa maxay kordhinta miisaanka hagitaanku guud ahaan?
    • Had iyo jeer waxay hagaajisaa kala duwanaanshaha
    • Waxay meesha ka saartaa saamaynta degdegta ah
    • Waxay xoojisaa u hoggaansanaanta degdegga ah laakiin waxay keeni kartaa dhereg badan
    • Sawirka waxa uu ka dhigaa mid cawlan
  4. Qiyaastii imisa baas oo horudhac ah halkii tilaabo diidmo ah ayay u baahan tahay hagitaan bilaash ah classifier?
    • Eber
    • Toban
    • boqol
    • Laba (hal shuruud, mid shuruud la'aan ah)
  5. Faa'iido intee le'eg ayay hagista-free-classifier ka leedahay hagidda kala soocida?
    • Uma baahna kalasaar si gaar ah u tababaran
    • Waxay u baahan tahay xog tababar oo badan
    • Waxay ku shaqeysaa kaliya moodooyinka qoraalka
    • Waxay meesha ka saartaa habka fidinta
  6. In the common classifier-free guidance formula, what does guidance scale s=0 produce?
    • The conditional prediction with extra amplification
    • The unconditional model prediction without conditioning
    • A prediction from a separately trained classifier
    • A sample with all denoising removed
  7. How does classifier-free guidance combine model outputs at inference?
    • It combines two image classifiers
    • It removes the conditional prompt
    • It combines conditional and unconditional score estimates
    • It adds a learned reward model after decoding
  8. What does a guidance scale of 1 generally correspond to in the common formulation?
    • The unconditional prediction only
    • A classifier-based gradient
    • A zero-noise image
    • The conditional prediction without extra guidance amplification