Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo cya CNNs

Gerageza ibyifuzo byakarere, gusangira ibintu byemejwe, ibikorwa bya RoI, masike, hamwe nubucuruzi bwihuse bwihuse bwibice bibiri.

Inzira zijyanye no kuyoboraIntara ishingiye kuri Cnns
Ikibazo 1 Bya 8

Niki gitekerezo cyibanze cya CNN ishingiye mukarere?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Niki gitekerezo cyibanze cya CNN ishingiye mukarere?
    • Tanga uturere twabakandida, hanyuma utondekane kandi usanduku ibintu muri buri
    • Kora ikirango kimwe kumashusho yose
    • Kanda ishusho mbere yo kuyitunganya
    • Hindura ishusho kuri graycale mbere
  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. Niki Byihuse R-CNN yazanye kugirango isimbuze Ishakisha ryatoranijwe?
    • Umugongo munini wa CNN
    • Intambwe yo guhinduka
    • Umuyoboro Uhuza Uturere (RPN)
    • Umuyoboro usubiramo
  4. Guhuza RoI gukora iki?
    • Isiba uturere dufite amanota make
    • Yongera imiterere yishusho
    • Ihuza uturere twose muri kamwe
    • Ihinga kandi igahindura ibiranga ikarita ihuriweho na buri karere
  5. Ni ubuhe bushobozi bw'inyongera Mask R-CNN yongeraho?
    • Pixel-urwego rwo gutandukanya ibice kuri buri kintu cyagaragaye
    • Kwandika amajwi
    • Guhindura inyandiko
    • Ubujyakuzimu bwa 3D kuva kuri pigiseli imwe
  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