Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Qotada dheer ee Fiditaanka Marigold

Hubi sida Marigold uu dib ugu isticmaalo Stable Diffusion horudhacyadii daahsoonaa ee qoto dheer ee qaraabo ah oo u maareeyo is-bedbeddelka affine, muunad, iyo faahfaahinta wax soo saarka.

Wadooyinka haga ee la xidhiidhaQiyaasta Qoto dheer ee Faafinta Marigold
Su'aal 1 ee 8

Qaabkee horay loo tababaray ayuu Marigold ku dhisayaa?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Qaabkee horay loo tababaray ayuu Marigold ku dhisayaa?
    • Stable Diffusion
    • GPT-4
    • YOLOv8
    • ResNet-50
  2. Sidee buu Marigold u qaabeeyaa hawsha qiyaasitaanka qoto dheer?
    • Sida dhibaatada kala saarista
    • Sida jiilka shardiga ah ee khariidad qoto dheer
    • Sida xoojinta barashada
    • Sida dhibaato kooxeed
  3. Maxaa la yaabay xogta tababarka Marigold?
    • Waxay isticmaashay balaayiin baaritaan qoto dheer oo dhab ah
    • Wax tababbar ah uma baahna haba yaraatee
    • Si fiican ayaa loo habeeyay inta badan xogta kaydinta synthetic-ka ah ee haddana la soo koobay sawirada dhabta ah
    • Waxay isticmaashay xogta maqalka ah oo keliya
  4. Waa maxay sababta Marigold caadi ahaan uga gaabiyaa moodooyinka qoto dheer ee horay loo sii wado?
    • Waxay ku shaqeysaa CPU kaliya
    • Waxay soo dejisaa xogta internetka mar kasta
    • Waxay dib u tababartaa sawir kasta
    • Waxay adeegsataa loop muunad ah oo ku celcelin ah
  5. Meelkee ayay Marigold ku qabataa habka fidinta?
    • Meesha qarsoon ee VAE ee xasilloon
    • Meel pixel ceeriin
    • Inta jeer/Baaxadda Afaraad
    • Meel dhibic-daruur ah
  6. Sidee Marigold u wanaajin kartaa xasiloonida qoto dheer ee orodka?
    • Adigoo hoos u dhigaya xallinta sawirka
    • Iyadoo la isku duba ridayo saadaalo badan oo muunad ah
    • Adigoo curyaaminaya VAE
    • Adigoo u beddelaya miisaan cawl
  7. What does affine-invariant relative depth mean for a Marigold prediction?
    • Every pixel gives exact distance in meters without calibration
    • The output contains color labels instead of depth
    • Depth ordering is useful, but the output's absolute scale and offset need not equal real-world measurements
    • Only the nearest object receives a depth value
  8. Which pair of inputs does Marigold encode with the same VAE during its latent diffusion process?
    • The camera pose and a 3D mesh
    • The text prompt and a CLIP score
    • Two stereo images from separate cameras
    • The input image and the depth map