Dense Class Scores

Problem

Compute class scores from a flattened feature vector.

W has shape num_classes x len(x) and b has length num_classes. Return W @ x + b as the raw logits for each class.

Hint

The classifier head is a single matrix-vector product plus bias.

case 1

in: [[1,2],[[1,0],[0,1]],[0,0]]

expected: [1,2]

case 2

in: [[0.5],[[2]],[1]]

expected: [2]

case 3

in: [[1,-1],[[1,1]],[0]]

expected: [0]

case 4

in: [[1,2,3],[[1,0,1]],[0.5]]

expected: [4.5]

Starter codePython

def dense_scores(x, W, b):
    # Your code here
    pass

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