quiz bu lëkkale ak tegtal · Diggante Niveau

DDPM ak DDIM

Teg ci DDPM ak DDIM jël misaal, boole ci tàggat buñ bokk, saytu stochasticity, jël waxtu, ak xayma nataal bu sell.

Yooni njiit yu jëm ciDdpm Ak Ddim
Laaj 1 de 8

Lan mooy njariñ li gëna mag ci DDIM ci kaw DDPM?

Xoolaatal laaj bu nekk8 laaj

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

  1. Lan mooy njariñ li gëna mag ci DDIM ci kaw DDPM?
    • Mën na defar nataal yu nuróo ci jéego yu néew
    • Dafay laaj reso buñ tàggat bu wuute lool
    • Dafay yokk bruit bu bari ci jéego bu nekk ngir gëna baax
    • Ci nataal yu weex ak yu ñuul kese lay dox
  2. Lan la reso neuronal bu modelu diffusion di jàng ngir xam luy waaja am ci diiru tàggat yaram?
    • Kapsioŋ bu mujj bi ci nataal bi
    • Bruit biñ yokk ci benn nataal ci benn jéego buñ jox
    • Rasio kompresioŋu nataal bi
    • jekkal kamera bi nga jëfandikoo ngir jël nataal bi
  3. Lan moo tax DDIM mëna defar benn nataal ci benn bruit biy tàmbali saa yu nekk?
    • Ndax dafay cache nataal yiñ njëkka defar
    • Ndax dafay faral di jëfandikoo ab laaj bu takku
    • Ndax anam wi ñuy jëlee misaal dafay deterministik te amul benn njuumte buñu dugal
    • Ndax dafay boole daw yu bari
  4. Ci DDIM, ban valeur ci parametre eta mooy defaraat doxalinu DDPM stochastic bi njëkk?
    • eta = 0
    • eta = -1
    • eta = 100
    • eta = 1
  5. Lu tollu ci ñaata jéego la DDPM bi njëkk soxla ngir am misaal yu baax?
    • Téemeeri jéego wala junniy jéego
    • jéego
    • Benn jéego
    • Lu ëpp benn milioŋ ciy jéego
  6. Ci yii, yan ci ñoom mooy limu gëna am solo ci diggante DDIM balaa ñuy jëm kanam?
    • Dayo fichier biy génne
    • Nataal bu sell biñ séentu x0
    • Guddaayi fiil bi jëfandikukat bi di laaj
    • Tàngooru GPU bi
  7. What does DDIM change compared with DDPM when using a model trained with the DDPM procedure?
    • It replaces the network with a text classifier
    • It changes the training data from images to audio
    • It changes the sampling trajectory while reusing the trained denoising network
    • It removes the need to estimate noise
  8. Why can DDIM skip selected diffusion timesteps during sampling?
    • The training process never added noise
    • Each skipped timestep is replaced by a larger image
    • It copies an earlier generated image from a cache
    • Its non-Markovian sampling path can connect noise levels without visiting every training step