Skip to content
ml-recall

#vgg

10 questions from Landmark Architectures, Transfer Learning, Computer Vision Basics

Timed test

10 questions · 10 min · score and explanations at the end

Take a test
Q 1 / 10Score 0 / 0

Question 1: Short answer

mediumAI-checkedLandmark Architectures

d2l's VGG-11 turns a 1×224×2241 \times 224 \times 224 image into a 512×7×7512 \times 7 \times 7 feature map, flattens it, and feeds it to a fully connected layer with 4096 outputs. How many parameters (weights and biases) does this first fully connected layer have?

a whole number