Skip to content
ml-recall

#separable-convolution

1 question from Convolutional Neural Networks

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

mediumAI-checkedConvolutional Neural Networks

The 2D Gaussian factorizes, G(x,y)=G(x) G(y)G(x, y) = G(x)\,G(y), so a 7×77 \times 7 Gaussian blur can be applied as a 7×17 \times 1 convolution followed by a 1×71 \times 7 one. Ignoring the image borders, how many times fewer multiplications per output pixel does the separable version need?

a number