# yolo cost function At the output of the final layer of yolo, a leaky-relu is applied to the output, so if we have negative values for the width and height, the cost function will return a null value since we would have square rooted a negative value at the second sum of the cost. Thus not able to update the weights using back prop.

Am I wrong about this or is there something I am missing here? If I am not wrong, how do we guarantee the width and height to be positive?

• You are summing squared values; The sum will be at worst 0, assuming lambdas are positive. Jan 10, 2018 at 8:25
• @VladislavsDovgalecs Sorry I don't see how that solves my problem, the square root would have still returned an imaginary value if the inside is negative, and if I do have an object in the cell, the term is not gonna become zero. Jan 10, 2018 at 8:33
• You asked "how do we guarantee the output to be positive" and I understood it that way, how to prove the expression you wrote is positive. I apologize for having misunderstood your question. Jan 10, 2018 at 19:11
• @VladislavsDovgalecs Thanks for your response, I will edit my question Jan 11, 2018 at 0:31

According to their source code, actually they use an exp operation to ensure $w$ and $h$ are non-negative values.

box get_region_box(float *x, float *biases, int n, int index, int i, int j, int w, int h, int stride)
{
box b;
b.x = (i + x[index + 0*stride]) / w;
b.y = (j + x[index + 1*stride]) / h;
b.w = exp(x[index + 2*stride]) * biases[2*n]   / w;
b.h = exp(x[index + 3*stride]) * biases[2*n+1] / h;
return b;
}


Here w and h are width and height of the network input, b.w and b.h are normalized width and height of the bonding box, x is last layer's output. It's not very clear what biases are though.

• That's actually the same trick used in getting the standard deviation of a variational autoencoder. I don't get why they don't just use a normal relu though Jan 10, 2018 at 13:36
• @ChesterCheng yes relu will do the same but it won't get any gradient if the input is negative, actually other functions that maps a real number to a positive number would work as well for example $x^2$ and $log(1+exp(x))$. Jan 10, 2018 at 13:58
• you are right! I guess they chose exp cus of the simple derivative Jan 10, 2018 at 14:35