Easy

Implement patch embedding (conv or unfold ++ linear) converting an image tensor to patch

Multimodal / Vision-Language (Lighter) · Problem 1 of 3

Chapter 16Multimodal / Vision-Language (Lighter)

Implement patch embedding (conv or unfold ++ linear) converting an image tensor to patch

EasyProblem 1 / 3

Implement patch embedding (conv or unfold ++ linear) converting an image tensor to patch tokens.

Implement the function/class skeleton in the editor. Any correct approach is accepted.

Hints