Ikibazo gihuza ibibazo · Hagati Urwego

U-Net Ubwubatsi Ikibazo

Gerageza U-Net encoder-decoder ihuza, gusimbuka guhuza, gutandukanya ibinyabuzima, guhanura urusaku, hamwe nubundi buryo.

Inzira zijyanye no kuyoboraU Ubwubatsi
Ikibazo 1 Bya 8

Niki gitanga U-Net imiterere yacyo 'U'?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niki gitanga U-Net imiterere yacyo 'U'?
    • Kodegisi yerekana urugero hamwe na decoder ya simmetrike yerekana urugero
    • Igice kimwe kigororotse cyo kwemeza
    • Imiyoboro ibiri ibangikanye ntaho ihuriye
    • Gusubiramo inshuro nyinshi mugihe cyintambwe
  2. Niyihe ntego yo gusimbuka U-Net?
    • Kugabanya umubare wibipimo kuri zeru
    • Kugirango utambike neza ahantu hatandukanye kuva kodegisi igana kuri decoder
    • Guhindura ishusho kumurongo
    • Kureka imyitozo burundu
  3. Ni iki U-Net yari igenewe mbere?
    • Kumenyekanisha imvugo
    • Guhanura ibiciro byimigabane
    • Igice cyibishusho cyibinyabuzima
    • Guhindura inyandiko
  4. Muri Diffusion Stable, U-Net iteganya iki kuri buri ntambwe?
    • Ibisobanuro byanyuma byishusho
    • Ikigereranyo cyo kwikuramo
    • Inguni ya kamera
    • Urusaku rwo gukuraho urusaku rwihishwa
  5. Bigenda bite kumakuru yumwanya nkuko kodegisi yamanutse?
    • Ikuramo 'iki' gihari ariko itakaza neza 'aho' ibisobanuro
    • Yunguka pigiseli nyayo
    • Ihindura ishusho kumyandiko
    • Bikubye kabiri imyanzuro
  6. Which augmentation did the original U-Net paper use to learn invariance from limited annotated biomedical images?
    • Replacing every image with a random label
    • Elastic deformations of the training images
    • Training only on unmodified test images
    • Removing the decoder path before training
  7. How did the original U-Net paper process large images beyond the network’s input size?
    • By discarding all image borders
    • By resizing every image to one pixel
    • By predicting on overlapping tiles and extrapolating context at tile borders
    • By running the model once on a text prompt
  8. What did the original U-Net paper’s weighted loss emphasize?
    • Only background pixels, regardless of distance
    • The most common image color
    • Noise prediction at a diffusion timestep
    • Border pixels between touching cells to help separate adjacent objects