Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Convolutional Neural Networks

Jaribio la kernels za CNN zilizoshirikiwa, upunguzaji wa sampuli za anga, madaraja ya vipengele vilivyojifunza, historia ya AlexNet, hesabu za gridi ya pato, na ufunikaji mnene wa idhaa ya ingizo.

Njia za mwongozo zinazohusianaMitandao ya Neural ya Convolutional
Swali 1 ya 8

Ni nini kazi kuu ya kichungi (kernel) kwenye CNN?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Ni nini kazi kuu ya kichungi (kernel) kwenye CNN?
    • Ili kuhifadhi lebo ya mwisho ya uainishaji
    • Kuchanganya pikseli bila mpangilio kabla ya mafunzo
    • Ili kutelezesha kwenye picha na kugundua mchoro maalum wa kuona
    • Ili kubadilisha picha kuwa sauti
  2. How does spatial kernel sharing reduce parameter requirements compared with learning a separate kernel at every image location?
    • The same learned kernel weights are reused across locations
    • All input pixels are deleted
    • Every layer must use only grayscale data
    • The model avoids all training
  3. What does a spatial pooling layer commonly do to a CNN feature map?
    • Assign a final label to every object
    • Reduce its spatial resolution
    • Guarantee invariance to every possible image shift
    • Always increase the number of input channels
  4. Katika CNN ya kina, vipengele hubadilikaje kwa ujumla kutoka kwa tabaka za mapema hadi tabaka za baadaye?
    • Kutoka kwa vitu vizima hadi saizi moja
    • Wanakaa sawa katika kila safu
    • Kutoka kwa maandishi hadi nambari pekee
    • Kutoka kingo na rangi rahisi hadi sehemu changamano kama vile macho au magurudumu
  5. Which named CNN is associated with the influential 2012 ImageNet classification result?
    • AlexNet
    • ResNet
    • Vision Transformer
    • SqueezeNet
  6. Ni operesheni gani ya nambari hufanyika wakati kichujio kinatumika kwenye kiraka cha picha?
    • Pikseli zimepangwa kutoka nyeusi hadi angavu zaidi
    • Kiraka kinafutwa kutoka kwa picha
    • Kila uzito unazidishwa na pikseli yake inayopishana, na bidhaa zinajumlishwa
    • Pikseli hubadilishwa kuwa herufi
  7. With a 6-by-6 input and 3-by-3 kernel at stride one, no padding, and no dilation, what is the CNN output-grid size?
    • 6 by 6
    • 3 by 3
    • 2 by 2
    • 4 by 4
  8. In dense ungrouped convolution on a three-channel input, which channels does one filter span?
    • Only the first channel by definition
    • All three input channels
    • No input channels because kernels contain only output labels
    • Exactly one channel in every convolution configuration