Kedis ku xidhan hagaha · Dhexdhexaad Heerka

LaMa xallinta- Kediska Rinjiyeynta adag

Baro sida ay LaMa isugu geyso iskudhafyada Fourier, khasaaraha garoonka soo dhaweynta sare leh, iyo maaskaro waaweyn oo sawir gelinta iyo xadka la soo sheegay.

Wadooyinka haga ee la xidhiidhaRinjiyeynta adag ee qaraarka Lama
Su'aal 1 ee 8

Waa maxay qaybta qaab dhismeedka saxeexa ee siinaya LaMa aragtideeda caalamiga ah ee sawirka?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Waa maxay qaybta qaab dhismeedka saxeexa ee siinaya LaMa aragtideeda caalamiga ah ee sawirka?
    • Isbeddellada Fourier Fast
    • Transformer blocks is-fiirsashada
    • Lakabyada LSTM ee soo noqnoqda
    • Shabakadaha kaabsal
  2. Muxuu LaMa u maareeyaa waji-xidho waaweyn si ka wanaagsan noocyo badan oo hore oo rinjiyeyn ah?
    • Waxay ku shaqeysaa sawirro yaryar oo keliya
    • Goobteeda soo dhawayneed ee caalamiga ah waxay u oggolaanaysaa inay sii waddo qaabdhismeedka godadka waaweyn
    • Waxay si aan kala sooc lahayn uga koobiyaysa cidhifyada pixels
    • Waxay diidaysaa inay buuxiso maaskaro ka sarreeya cabbir go'an
  3. What resolution behavior did the LaMa paper report?
    • It only works at one exact training resolution
    • It works only below the training resolution
    • It generalized to some resolutions higher than those used during training in the evaluated settings
    • It accepts no image input
  4. Nooc noocee ah oo textures ah ayuu LaMa si gaar ah u maareeyaa iyada oo ay ugu wacan tahay habaynteeda soo noqnoqoshada?
    • Sawaxan random
    • Midab keliya oo adag
    • Xarfaha qoraalka oo gaar ah
    • Soo noqnoqoshada, textures xilliyeed sida leben ama tile
  5. Compared with large diffusion-based inpainting systems, how is LaMa commonly positioned?
    • As a comparatively efficient convolutional inpainting method
    • As a much slower model that requires a data center
    • As a video-only model
    • As a tool that never needs an image
  6. Waa kuwee khasaaraha ka caawiya LaMa in ay soo saarto buuxinta muuqaal dhab ah halkii ay ka ahaan lahayd celcelis ahaan blur?
    • Khaladaad fudud oo pixel-ku-meel-gaadh ah oo lumay oo keliya
    • Khasaare iska soo horjeeda oo ay weheliso khasaare maskaxeed
    • Wax shaqo ah oo khasaare ahi ma jirto
    • Khasaare cabbiraya cabbirka faylka
  7. What additional loss component does the LaMa paper emphasize for large-mask inpainting?
    • Luminta hadalka-aqoonsiga
    • A bitrate-only loss
    • A perceptual loss with a high receptive field
    • A loss that ignores image structure
  8. Who introduced LaMa in the 2021 paper?
    • Jonathan Frankle and Michael Carbin
    • Cees Taal and colleagues
    • Timothy Dozat and Christopher Manning
    • Roman Suvorov and colleagues