quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz buy wax ci konvolusioŋ yu yaatu ak yu atrous

Saytu diggante yaatuwaayu yaatuwaayu, barab yiy jot, xaaj, WaveNet, griy, ak muy nuru ay eskaal yu bari ci biir convolution atrous.

Laaj 1 de 8

Lan la dilatation bu ëpp 1 di def ci kernel buy convolution?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lan la dilatation bu ëpp 1 di def ci kernel buy convolution?
    • Dafay dugal ay bërëb ci digganté kernel bi ngir ñu mëna muur barab bu gëna yaatu
    • Dafay yokk yeneen poid yuñ mëna jàng ci kernel bi
    • Dafay wàññi kernel bi ci benn poñ
    • Dafay soppi kernel bi ci ab jëfandikoo pooling
  2. Kernel 3x3 ak dilatation rate 2 mën na yam ci gox bu yaatu?
    • 3x3
    • 5x5
    • 7x7
    • 9x9
  3. Lan moo waral konvolusioŋ yu yaatu yi am njariñ ci segmentasioŋ semantik?
    • Dañuy wàññi nataal bi mu nekk benn etiket
    • Dañu baña soxla benn done tàggat yaram
    • Dañuy yaatal barabu jot gi, boole ci tëye dayo kàrtu man-man bi
    • Dañuy liggéey ci nataal yu grayscale
  4. Lan la baat atrous bawoo?
    • Baatu latin buy tekki couche
    • ab akronim ngir ab anamu taggat
    • Tur ki ko defar
    • Français trous, muy tekki ay pax
  5. Ci WaveNet, lu tax ay convolusioŋ yu yaatu yuñ dajale am solo?
    • Dañuy defar ay nataal ci barabu audio
    • Dañuy jàpp dependence yu sori lool ci forme onde audio bi
    • Dañuy dindi bépp noppi ci enregistrement yi
    • Dañuy soppi audio bi ci mbind ci saasi
  6. Lan mooy jafe-jafe bi mëna xew sudee dangay jël ay convolution yu yaatu ak benn taux buñu tann bu baax?
    • Reseau bi dafa tuuti lool ngir tàggat
    • Nataal bi dafay wëlbatiku ba fàww
    • Artefakt yu griy, fu yenn position yuñ dugal duñu musa jël misaal
    • poids yépp nekk nul
  7. How does Atrous Spatial Pyramid Pooling combine multiple scales in DeepLab?
    • It runs several dilation rates in parallel and fuses their outputs
    • It chooses one fixed dilation rate and discards the rest
    • It converts the image into a single global class before convolution
    • It replaces every convolution with a larger dense kernel
  8. For one input channel and one output channel, how many kernel weights does a dilated 3×3 filter contain, excluding a bias?
    • 25, because dilation 2 spans a 5×5 region
    • 5, one for each position along the expanded width
    • 18, because dilation 2 doubles the number of weights
    • 9, because dilation changes spacing rather than the 3×3 weight count