ViT CLS Concat

Problem

Prepend a CLS token to a sequence of patch embeddings.

Return [cls_token] + patches, converting every entry to a list. An empty patch list returns just the CLS token.

case 1

in: [[[1,2],[3,4]],[9,9]]

expected: [[9,9],[1,2],[3,4]]

case 2

in: [[[5]],[0]]

expected: [[0],[5]]

case 3

in: [[],[7,7]]

expected: [[7,7]]

Starter codePython

def prepend_cls(patches, cls_token):
    # Your code here
    pass

3 test cases · run your code against them in the editor