quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz buy tegtal bu amul benn klassifikatër

Xoolaat tegtal bu amul benn klassifikatër, bàyyi njàng ci anam wu am sart, njaayum kalite-diversite, njëgu inferensi, ak balansu tegtal. Saytu yaatuwaayam ak xalaat yi.

Yooni njiit yu jëm ciNjàngale bu amul fayda
Laaj 1 de 8

Lan moo waral xeetu diffusion yi di jëfandikoo tegtal bu amul benn klassifikatër?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lan moo waral xeetu diffusion yi di jëfandikoo tegtal bu amul benn klassifikatër?
    • Ngir gëna dooleel ni génne gi di toppee conditionnement bi
    • ngir kompresse model bi ci dayo bu gëna ndaw
    • Ngir dindi enkoderu mbind mi lëmm
    • Ngir soppi nataal yi def ko audio
  2. Naka lay def ba ab model di jàngee wax luy waaja am te amul benn waruwaay ngir am tegtal bu amul benn classifier?
    • Ni ñu tàggate ñaareelu klassifikatër bu wuute
    • Sooy bàyyi kondisioneer bi ci diiru tàggat yaram
    • Jëfandikoo nataal yu ñuul kese
    • Soo dindi GPU bi
  3. Lan mooy yokk balansu tegtal bi?
    • Saa yu nekk dafay yokk wuute gi
    • Dindi influens bu laaj bi
    • Dafay gëna dooleel topp gi ci saasi waaye mën na jur saturation bu ëpp
    • Defal nataal bi gray
  4. Lu tollu ci ñaata paas ci kanam ci jéego bu nekk ci denoising la tegtal bu amul classifier bi soxla?
    • Zéro
    • Fukk
    • Téeméer
    • Ñaar (benn bu am sart, beneen bu amul sart)
  5. Lan mooy njariñu tegtal bu amul klassifikatër ci tegtal bu am klassifikatër?
    • Soxlawul benn classificateur buñu tàggat
    • Dafay laaj done yu bari ci wàllu tàggat yaram
    • Du dox ludul ci modelu bind
    • Dafay dindi diffusion bi
  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