Skip to content
ml-recall

#strided-convolution

1 question from Generative Adversarial 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-checkedGenerative Adversarial Networks

A DCGAN discriminator for 32×32×332 \times 32 \times 3 images has three convolutions with kernel_size=4, stride=2, padding=1 and 32, 64 and 128 output channels, then flattens the result into one nn.Linear(?, 1) layer. How many input features does that linear layer need?

a whole number