Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Vibadilishaji Maono

Chunguza viraka na umakini wa ViT, pamoja na matokeo ya awali ya utafiti, maelezo ya nafasi, hesabu za viraka, na chaguo za hali ya uainishaji.

Njia za mwongozo zinazohusianaVision Transfoma
Swali 1 ya 8

How does the original plain ViT convert an image into input tokens for its encoder?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. How does the original plain ViT convert an image into input tokens for its encoder?
    • It must read one raw pixel per recurrent step
    • It linearly embeds flattened non-overlapping patches
    • It converts the whole image into a mandatory single scalar
    • It removes all learned input projections
  2. Which mechanism supports direct interactions between allowed patch tokens in the original dense ViT encoder?
    • Kujitazama
    • Only a fixed local max-pooling operation
    • Only alphabetical ordering of patch labels
    • Only a random image crop
  3. Which architectural difference did the original ViT study discuss relative to convolutional networks?
    • A guarantee that it contains fewer parameters than every CNN
    • An inability to process color images
    • A guarantee that every vision task needs the same huge dataset
    • Fewer convolution-style locality and translation-equivariance biases
  4. Madhumuni ya usimbaji wa nafasi katika Kigeuzi cha Maono ni nini?
    • Ili kubana saizi ya faili ya picha
    • Kuchanganya kwa nasibu viraka kwa uongezaji
    • Kuambia mfano ambapo kila kiraka kilikuwa kwenye picha ya asili
    • Kubadilisha picha za rangi kuwa kijivu
  5. Upungufu wa vitendo wa kujishughulisha juu ya viraka vingi vya picha ni kwamba gharama yake inakua:
    • Mara kwa mara na idadi ya viraka
    • Linearly na idadi ya patches
    • Sio kwa ukubwa wa picha
    • Tu na idadi ya njia za rangi
  6. What conclusion is supported by the original ViT classification experiments under their stated pretraining and transfer conditions?
    • Every transformer must outperform every CNN on every dataset
    • A pure patch transformer could perform competitively with compared CNNs
    • All convolutional operations are invalid for image recognition
    • No training data is needed for image classification
  7. For a 224-by-224 image divided into non-overlapping 16-by-16 patches, how many patch tokens are there before adding a class token?
    • 197
    • 224
    • 196
    • 256
  8. In the original ViT classification design, which encoder state supplies the classification head?
    • Only an unembedded raw input pixel
    • A required random token not processed by the encoder
    • Only the first patch’s original filename
    • The final state of the learned class token