Ikibazo gihuza ibibazo · Hagati Urwego

Ikigereranyo cya Marigold Diffusion Ikigereranyo Cyimbitse

Reba uburyo Marigold yongeye gukoresha Stable Diffusion yibanga ryambere ryimbitse kandi ikemura affine invariance, icyitegererezo, nibisohoka birambuye.

Inzira zijyanye no kuyoboraIkigereranyo cyimbitse ya Marigold
Ikibazo 1 Bya 8

Ni ubuhe buryo bwateganijwe Marigold yubakiyeho?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Ni ubuhe buryo bwateganijwe Marigold yubakiyeho?
    • Stable Diffusion
    • GPT-4
    • YOLOv8
    • ResNet-50
  2. Nigute Marigold akora umurimo wo kugereranya ubujyakuzimu?
    • Nkikibazo cyo gutondeka
    • Nkibisekuruza bisabwa ikarita yimbitse
    • Nukwiga gushimangira
    • Nkikibazo cyo guhuriza hamwe
  3. Niki cyatangaje amakuru yamahugurwa ya Marigold?
    • Yakoresheje amamiliyaridi yubushakashatsi bwimbitse
    • Ntabwo yari ikeneye imyitozo namba
    • Byakosowe neza cyane cyane kuri dataseti yubukorikori nyamara yashyizwe mumashusho nyayo
    • Yakoresheje gusa amajwi
  4. Ni ukubera iki Marigold itinda cyane kuruta kugaburira-ubujyakuzimu bwimbitse?
    • Ikora kuri CPU gusa
    • Ikuramo amakuru kuri enterineti buri gihe
    • Irongera imyitozo kuri buri shusho
    • Ikoresha itera itera kwerekana icyitegererezo
  5. Ni uwuhe mwanya Marigold akora inzira yo gukwirakwiza?
    • Umwanya uhamye wa Diffusion ya VAE umwanya wihishe
    • Umwanya muto wa pigiseli
    • Umwanya wa Frequency / Umwanya wa Fourier
    • Umwanya-Igicu
  6. Nigute Marigold yatezimbere ubujyakuzimu bwimbitse?
    • Mugabanye imiterere yishusho
    • Muguhuza ibyitegererezo byinshi byahanuwe
    • Muguhagarika VAE
    • Muguhindura ibara
  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