Ikibazo gihuza ibibazo · Hagati Urwego

YOLO Ikibazo Cyukuri-Igihe cyo Kumenya

Ongera usuzume igishushanyo mbonera cya YOLO, igishushanyo mbonera cya gride, ibicuruzwa biva mu mahanga hamwe nimbibi zigihe nyacyo.

Inzira zijyanye no kuyoboraYolo Igihe Cyukuri
Ikibazo 1 Bya 8

Amagambo ahinnye YOLO ahagarariye iki muriki gice?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Amagambo ahinnye YOLO ahagarariye iki muriki gice?
    • Urareba rimwe gusa
    • Wiga rimwe gusa
    • Igikoresho cyawe Kumurongo
    • Yatanze Ikintu Ikirango Ibisohoka
  2. Which cross-domain evaluation did the original YOLO paper report?
    • Transcribing speech from noisy recordings
    • Generalizing from natural images to artwork datasets
    • Classifying satellite images with no labels
    • Estimating depth from stereo video only
  3. Ni ubuhe buryo bukuraho udusanduku twinshi, twuzuzanya mu dusanduku twa YOLO?
    • Ibisanzwe
    • Kureka
    • Kurengerwa ntarengwa
    • Kongera amakuru
  4. Mubishushanyo bya YOLO byumwimerere, nigute ishusho yinjiza igabanijwe kubihanura?
    • Mu bihingwa bidasanzwe
    • Mu miyoboro y'amabara
    • Mu karere kamwe
    • Muri gride ya selile
  5. Nuwuhe mubare buri grid selile iteganya kuruhande rwo guhuza agasanduku gahuza?
    • Amanota yicyizere amanota hamwe nibyiciro byamasomo
    • Igishusho
    • Uburebure bwa kamera
    • Ikigereranyo cyo guhagarika dosiye
  6. Kuki YOLO ikunzwe cyane cyane kuri videwo na kamera bizima?
    • Ntishobora gukora kuri GPUs
    • Umuvuduko wacyo umwe utuma ibiciro nyabyo bigerwaho
    • Nicyitegererezo cyonyine gikoresha ibara
    • Ntabwo bisaba imyitozo namba
  7. What accuracy tradeoff did the original YOLO paper report relative to leading detection systems?
    • It had no localization errors but missed every small object
    • It could detect only one class
    • It made more localization errors while being less likely to predict false detections where nothing existed
    • It required thousands of region-wise classifier runs
  8. Why can a real-time detector still be unsuitable for a particular deployment?
    • A real-time model cannot process images
    • Frame rate guarantees safety certification
    • A detector’s speed proves every object is found
    • Its measured speed does not establish adequate accuracy, latency or robustness for that setting