quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz CNNs bu lalu ci gox yi

Test gox propositions, bokk man-mani convolution, jëfandikoo RoI, mask, ak njub-gaawaay kompromis ci detektër yu am ñaari etap.

Yooni njiit yu jëm ciCnns yu bawoo ci gox yi
Laaj 1 de 8

Lan mooy xalaatu CNN bu lalu ci gox?

Xoolaatal laaj bu nekk8 laaj

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

  1. Lan mooy xalaatu CNN bu lalu ci gox?
    • Xalaatal gox yi nga bëgga tànn, ba noppi nga xaaj mbir yi ci bu nekk
    • Defar benn etiketu nataal bi yépp
    • Komprimeel nataal bi balaa ngay liggéey
    • Soppi nataal bi ci grayscale njëkk
  2. Why was the original R-CNN computationally expensive?
    • It trained without image pixels
    • It ran a CNN separately on each proposed region
    • It required one human label per test image
    • It computed only one shared feature map
  3. Lan la Faster R-CNN dugal ngir wecci Seetug Tanneef?
    • CNN bu gëna mag
    • Jéego buy soppi grayscale
    • Reseau proposition régional (RPN)
    • Reseau neuronal buy baaxoo
  4. Lu RoI pooling di def?
    • Dafay efaase gox yi am poñ yu néew
    • Dafay yokk dayo nataal bi
    • Dafay boole gox yépp ñu nekk benn
    • Dafay dagg ak soppali dayo màndarga yi ci kàrtu màndarga yiñ bokk ngir gox bu nekk
  5. Ban mën mën la Mask R-CNN yokk?
    • Masku segmentaasioŋ ci niveau pixel ngir bépp mbir buñ gis
    • Transkripsioŋ audio
    • Tekki làkku mbind
    • xóotaayu 3D ci benn pixel
  6. What training objective does Mask R-CNN use for its classification, box, and mask branches?
    • Only a pixelwise mask loss with no classification
    • A multi-task loss that combines classification, bounding-box regression, and mask losses
    • A language-model next-token loss
    • A region-proposal loss with no object classification
  7. What alignment problem does RoIAlign address compared with RoI pooling?
    • It replaces the Region Proposal Network with Selective Search
    • It removes all need for a shared feature map
    • It avoids the coordinate quantization that can misalign extracted region features
    • It predicts a class label before processing the image
  8. How should two-stage and single-stage detector speed/accuracy be compared?
    • Two-stage models are always more accurate and faster
    • Single-stage models cannot detect multiple objects
    • The architectures have identical pipelines
    • Using a specified benchmark and implementation, because the tradeoff is not universal