Guide-yakabatana mibvunzo · Pakati Nhanho

U-Net Architecture Quiz

Test U-Net encoder-decoder symmetry, skip connections, biomedical segmentation, diffusion noise prediction, and alternatives.

Nzira dzekutungamira dzinoenderanaU Net Architecture
Mubvunzo 1 ye 8

Chii chinopa U-Net chimiro chayo 'U'?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Chii chinopa U-Net chimiro chayo 'U'?
    • Iyo encoder inodzika masamples uye symmetric decoder inokwira sampuli
    • Imwe chete yakatwasuka stack ye convolutions
    • Manetiweki maviri anoenderana pasina chinongedzo
    • A recurrent loop nekufamba kwenguva matanho
  2. Chii chinangwa cheU-Net's skip connections?
    • Kuderedza huwandu hwema parameters kusvika zero
    • Kupfuudza zvakanatsa zvemamiriro ekunze kubva kune encoder layer zvakananga kuenda kunoenderana nedhikodha layer
    • Kushandura chifananidzo kuita grayscale
    • Kurega kudzidzira zvachose
  3. U-Net yakatanga kugadzirirwa chii?
    • Kuzivikanwa kwekutaura
    • Kufanotaura kwemutengo wemasheya
    • Biomedical image segmentation
    • Kushandura mashoko
  4. MuStable Diffusion, U-Net inofanotaura chii padanho rega rega?
    • Chinyorwa chekupedzisira chemufananidzo
    • The compression ratio
    • Iko kamera angle
    • Ruzha rwekubvisa kubva kune ruzha rwakanyarara
  5. Chii chinoitika kune ruzivo rwenzvimbo senge encoder downsamples?
    • Inobvisa 'chii' chiripo asi inorasikirwa neiyo 'kupi' ruzivo
    • Iyo inowana chaiyo pixel nzvimbo
    • Inoshandura chifananidzo kuva chinyorwa
    • Inowedzera chisarudzo
  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