Skip to content
ml-recall

#patch-embedding

2 questions from Attention & Transformers

Timed test

2 questions · 2 min · score and explanations at the end

Take a test
Q 1 / 2Score 0 / 0

Question 1: Short answer

mediumAI-checkedAttention & Transformers

A ViT turns 224×224224 \times 224 RGB images into patch embeddings with nn.Conv2d(in_channels=3, out_channels=768, kernel_size=16, stride=16), which embeds each 16×1616 \times 16 patch into a 768-dimensional vector. How many parameters does this layer have?

a whole number