quiz bu lëkkale ak tegtal · Yomb Niveau

Quiz yokk ay done

Xoolaat pexe yokk done ngir nataal ak bind, boole ci coppite yiy baña yàq etiketu, jaxase ak sàrt yiñ jàng.

Yooni njiit yu jëm ciYokkateg done
Laaj 1 de 8

Lan mooy jubluwaay bu njëkk ci yokk done?

Xoolaatal laaj bu nekk8 laaj

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

  1. Lan mooy jubluwaay bu njëkk ci yokk done?
    • Yaatalal ak wuutale ay done ci tàggat yaram suko defee xeetu gëna mëna yamale
    • Gaawaale gis-gis ci model buñ tàggat
    • Ngir wàññi dayo done yi ci disk bi
    • Ngir etikete ci saasi misaal yiñ etiketewul
  2. Ci yii, ban ci ñoom mooy pexem yokk nataal biñ gëna xam?
    • Wàcci degrade
    • Flipping horizontal bu bari
    • Tokenisasioŋ
    • Dàddu
  3. Lan mooy tekki làkk ci yokk mbind?
    • Dafay soppi doxalinu kàddu yi ci biir frase
    • Dindi bépp baat stop ci mbind mi
    • Tekki mbind ci beneen làkk ak dellu ngir sos ay paraphrase
    • Dafay soppi mbind mu nekk ay lim
  4. Lan moo tax augmentation yi wara nekk 'etiketu baña yàq'?
    • Ngir tëye dayo fichier dataset bi
    • Ngir tàggat yaram gëna gaaw
    • Ndax model yi mënu ñu jàng etiket yi
    • Ndax soppi etiket bi dina jàngal xeetu mbootaay bu jaarul yoon
  5. Lu pexem Mixup di def?
    • Dafay boole ñaari misaal ak seeni etiket ci benn misaalu tàggat
    • Maske ab gox rektangul ci ab nataal
    • Seetug politiku yokkute bi gëna baax ci saasi
    • Yokk bruit bu bari ci diisaayu model
  6. Kañ la yokk done am solo?
    • Soo amee ay done yuñ etikete te amul àpp
    • Sudee done yiñ etikete bariwul, dajale lu gëna bari lu jafe la
    • Soo tàggatee model bi bamu mat
    • Ngir done yi ci këyitu xayma yi kese
  7. What does CutMix do to an image and its training label?
    • It adds a random word to a sentence without changing the label
    • It swaps only class names in the dataset
    • It replaces a patch with a patch from another image and mixes labels by the replaced area
    • It blurs every input and keeps a single label unchanged
  8. How does AutoAugment select augmentation policies in its original paper?
    • It chooses transformations from a fixed human-written list without evaluation
    • It uses test labels to relabel training images
    • It selects operations from inference-time confidence only
    • It searches for policies using validation performance as a reward signal