Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya CNN ya Mikoa

Mapendekezo ya eneo la majaribio, vipengele vya kubadilishana vilivyoshirikiwa, utendakazi wa RoI, vinyago, na upatanishi wa kasi wa usahihi wa vigunduzi vya hatua mbili.

Njia za mwongozo zinazohusianaCnns za Mkoa
Swali 1 ya 8

Je, wazo kuu la CNN yenye makao yake ni lipi?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Je, wazo kuu la CNN yenye makao yake ni lipi?
    • Pendekeza maeneo ya walioteuliwa, kisha uainisha na uweke vipengee kwenye kila moja
    • Tengeneza lebo moja kwa picha nzima
    • Finyaza picha kabla ya kuchakata
    • Badilisha picha kuwa kijivu kwanza
  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. Je! Faster R-CNN ilianzisha nini ili kuchukua nafasi ya Utafutaji Teule?
    • Uti wa mgongo mkubwa zaidi wa CNN
    • Hatua ya ubadilishaji wa rangi ya kijivu
    • Mtandao wa Mapendekezo ya Mkoa (RPN)
    • Mtandao wa neva unaojirudia
  4. Je, kuunganisha kwa RoI kunafanikisha nini?
    • Inafuta maeneo yenye alama za chini
    • Inaongeza azimio la picha
    • Inaunganisha mikoa yote kuwa moja
    • Hupunguza na kubadilisha ukubwa wa vipengele kutoka kwa ramani ya vipengele vilivyoshirikiwa kwa kila eneo
  5. Je, Mask R-CNN inaongeza uwezo gani wa ziada?
    • Vinyago vya kugawanya kiwango cha pikseli kwa kila kitu kilichotambuliwa
    • Unukuzi wa sauti
    • Tafsiri ya maandishi
    • Kina cha 3D kutoka kwa pikseli moja
  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