DreamBooth Prior Loss

Problem

Compute the prior-preservation loss of DreamBooth: the mean squared error between the model's prediction on class images and the sampled noise/velocity target.

The signature is dreambooth_prior_loss(prior_pred, prior_target).

Hint

The prior loss keeps the class from drifting while the subject is learned.

Test cases

case 1

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

expected: 0

case 2

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

expected: 2.5

case 3

in: [[0.5],[1]]

expected: 0.25

case 4

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

expected: 0.6666666667

Starter codePython

def dreambooth_prior_loss(prior_pred, prior_target):
    # Your code here
    pass

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