Quiz buy yokk waxtu test

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

1. At inference time, what does test-time augmentation do with a single input?
   • Doxal model bu takku bi ci kaw ay kopi yuñ soppi ci benn dugal ak boole ay genn
   • Taxawaat xeetu model bi ci done yuñ yokk saa yu ñu ko laajee
   • Yokk bruit ci diisaayu model bi laataa ñuy wax luy waaja am
   • kompresse model bi suko defee mu gëna gaaw ci inference
2. When can pooling predictions from transformed views reduce prediction variance?
   • When every view changes the true class
   • When the transforms preserve the label and the view errors are at least partly uncorrelated
   • When all predictions are identical by design
   • When the model is retrained on each transformed copy
3. Lan mooy njëgu jëfandikoo TTA?
   • Dafay laaj done test yuñ etikete
   • Dafay soppi ba fàww poid yiñ tàggat
   • Dafay yokk xayma inference ndax model bi dafay daw yoon yu bari ci misaal bu nekk
   • Dafay wàññi njubte model ci dugal yu sell
4. Ban tanneef ci yokkute moo mëna gaañ benn klassifikatëru sifar?
   • Coppite yu ndaw ci leeraay bi
   • Ay mbay yu ndaw
   • Yokk tuuti bruit Gaussian
   • Xalaat '6' ci anam wu tëdd suko defee mu niru ak '9'
5. Ci segmentation, ban jéego bu gëna am solo lañu soxla balaa ñuy jël moyenne yi ci TTA yi?
   • Delloosi coppite geometrik bu nekk suko defee mask yi ñu séentu ñu méngoo ak pixel yi njëkk
   • Taxawaat dekodeer bi ngir gis-gis bu nekk
   • sànni bépp gis-gis buñ wëlbati
   • Soppi mask yi def ko boîte de bounding
6. For a classification model, what may be aggregated across test-time views?
   • The model’s training labels
   • The predicted probabilities or logits from the views
   • The input image file names
   • The optimizer momentum buffers
7. Does standard test-time augmentation require retraining the model on new labels?
   • Yes; each view needs a newly trained model
   • Yes; it requires extra class labels for every view
   • No; it reuses fixed weights and evaluates transformed inputs at inference
   • No; it replaces the model with a lookup table
8. A segmentation model predicts masks on flipped and cropped views. What must happen before pixelwise pooling?
   • Average masks before undoing the transforms
   • Discard the original image coordinates
   • Apply a different label to each pixel view
   • Invert the geometric transforms so all masks align with the original image coordinates