Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Convolutional nkankikan Networks adanwo

Test shared CNN kernels, spatial downsampling, learned feature hierarchies, AlexNet history, output-grid calculations, and dense input-channel coverage.

Jẹmọ itọsọna awọn ọnaConvolutional nkankikan Networks
Ibeere 1 ti 8

Kini iṣẹ akọkọ ti àlẹmọ (kernel) ni CNN kan?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. Kini iṣẹ akọkọ ti àlẹmọ (kernel) ni CNN kan?
    • Lati tọju aami isọdi ikẹhin
    • Lati dapọ awọn piksẹli laileto ṣaaju ikẹkọ
    • Lati rọra kọja aworan naa ki o rii apẹrẹ wiwo kan pato
    • Lati yi aworan pada si ohun afetigbọ
  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. Ninu CNN ti o jinlẹ, bawo ni awọn ẹya ṣe yipada ni gbogbogbo lati awọn ipele ibẹrẹ si awọn ipele nigbamii?
    • Lati gbogbo awọn nkan si awọn piksẹli ẹyọkan
    • Wọn duro aami ni gbogbo Layer
    • Lati ọrọ si awọn nọmba nikan
    • Lati awọn egbegbe ti o rọrun ati awọn awọ si awọn ẹya eka bi awọn oju tabi awọn kẹkẹ
  5. Which named CNN is associated with the influential 2012 ImageNet classification result?
    • AlexNet
    • ResNet
    • Vision Transformer
    • SqueezeNet
  6. Iṣiṣẹ nomba wo ni o ṣẹlẹ nigbati a ba lo àlẹmọ si alemo ti aworan naa?
    • Awọn piksẹli ti wa ni lẹsẹsẹ lati dudu julọ si imọlẹ julọ
    • Patch naa ti paarẹ lati aworan naa
    • Iwọn kọọkan jẹ isodipupo nipasẹ piksẹli agbekọja rẹ, ati pe awọn ọja naa ni akopọ
    • Awọn piksẹli ti yipada si awọn lẹta
  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 nipa 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