Skip to content
ml-recall

#cifar10

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

A CIFAR-10 CNN takes 32×32×332 \times 32 \times 3 images through three blocks of Conv2d(kernel 3, padding 1) + ReLU + MaxPool2d(2, 2), with 16, 32 and 64 output channels, then flattens and applies fc1 = nn.Linear(?, 500). How many parameters does fc1 have?

a whole number