Pearson Correlation Loss in paper or code
Opened this issue · 4 comments
yanjh97 commented
Hi, I found that the Pearson Correlation Loss of paper and code is inconsistent.
in paper:
in code:
Lines 105 to 108 in 8c2e181
ShaohuaL commented
Yes it makes me confused.
HkDzl commented
I am also curious about this.
zhanghaoyu816 commented
The author has answered this question in issues/1
Master-cai commented
Hi guys, I'm still confused.
- the inverse depth means if the real depths is 50m, the inverse depth will be 1/50; but why - midas_depth in the code?
- the equation in the paper is: Corr(D_ras, D_est), which is implemented by pearson_corrcoef. The pearson_corr_coef is the same as the eq in the paper.
but the code is 1 - pearson_corrcoef.
cc @zehaozhu @henrypearce4D @zhiwenfan