RPN Objectness

Problem

Convert RPN objectness logits to probabilities with the sigmoid function.

Return each value 1 / (1 + exp(-x)) rounded to 4 decimal places.

case 1

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

expected: [0.5,0.7311,0.2689]

case 2

in: [[2,-2]]

expected: [0.8808,0.1192]

case 3

in: [[0.5]]

expected: [0.6225]

Starter codePython

def rpn_objectness(logits):
    # Your code here
    pass

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