GAN Discriminator BCE
~10 mincode completion
Implement discriminator_bce(y, d) returning a scalar.
Examples
Two reals at 0.8 and 0.9
- Input
- discriminator_bce([1, 1], [0.8, 0.9])
- Output
- 0.16425
Two fakes at 0.2 and 0.1 (symmetric of t1)
- Input
- discriminator_bce([0, 0], [0.2, 0.1])
- Output
- 0.16425
A mixed pair
- Input
- discriminator_bce([1, 0], [0.7, 0.4])
- Output
- 0.43375
Hints
Hint 1
bounds an array in one call.
Hint 2
Do not forget to the fake term. That step is easy to skip.
Requirements
y: labels, 1 for real and 0 for faked: predicted probabilities in (0, 1), same shape as yReturn scalar
Constraints
Allowed library: NumPy only
Time limit: 200 ms, Memory: 64 MB
Where this shows up
~10 min
••••••••••••••••
8 employers weight this skill
4 autonomy companies, 1 enterprise vendor, 1 defense company, 1 health and bio company, 1 AI product company. Top match scores 87.
Python
import numpy as np
def discriminator_bce(y, d):
"""
Mean binary cross-entropy of discriminator probabilities.
Args:
y: labels, 1 for real and 0 for fake
d: predicted probabilities in (0, 1), same shape as y
Returns:
scalar
"""
# YOUR CODE HERE
pass