Muedzo-Nguva Yekuwedzera Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Panguva yekufungidzira, bvunzo-nguva yekuwedzera inoitei nekuisa kamwe chete?
   • Kumhanyisa iyo yakagadziriswa modhi pane akati wandei akashandurwa makopi ekuisa uye kubatanidza zvinobuda
   • Kudzidzirazve modhi pane yakawedzerwa data pese painobvunzwa
   • Kuwedzera ruzha kune huremu hwemuenzaniso pamberi pekufanotaura kwega kwega
   • Kudzvanya modhi kuitira kuti imhanye nekukurumidza pakufungidzira
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. Ndeipi mari huru yekushandisa TTA?
   • Inoda data rebvunzo rakanyorwa
   • Inoshandura zvachose zviyero zvakadzidziswa
   • Iyo inowedzera inference compute nekuti modhi inomhanya kakawanda pamuenzaniso
   • Inoderedza kurongeka kwemuenzaniso pane zvakachena zvinopinza
4. Ndeipi sarudzo yekuwedzera inogona KUKURUDZA dhijitari classifier?
   • Kupenya kudiki kunoshanduka
   • Zviyo zvidiki zvisina tsarukano
   • Kuwedzera karuzha kaGaussian
   • Kutenderedza '6' kuti iite senge '9'
5. Muchikamu, ndeipi nhanho yekuwedzera inodiwa usati waenzanisa zvabuda zveTTA?
   • Kutenderedza yega yega geometric shanduko kuitira kuti masks akafanotaurwa awirirane nemapikisi epakutanga
   • Kudzidzirazve decoder kune yega yega maonero
   • Kurasa maonero ese akapidiguka
   • Kushandura masiki kumabhokisi ekusungirira
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