Skip to content
ml-recall

#compression

3 questions from Autoencoders & VAEs, Diffusion Models, LLM Fundamentals & Prompting

Timed test

3 questions · 3 min · score and explanations at the end

Take a test
Q 1 / 3Score 0 / 0

Question 1: Short answer

mediumAI-checkedAutoencoders & VAEs

A convolutional autoencoder's encoder is:

x = F.relu(nn.Conv2d(1, 16, 3, padding=1)(x))   # input: 1 × 28 × 28
x = nn.MaxPool2d(2, 2)(x)
x = F.relu(nn.Conv2d(16, 4, 3, padding=1)(x))
x = nn.MaxPool2d(2, 2)(x)                        # compressed representation

How many numbers does the compressed representation of one image contain?

a whole number