confusion about the err metrics

[Wei-kang-Wang]

Hello! Nice work! I have a question about the err metric you used in the paper. The definition is equation 11 in the arxiv version of your paper. But in the code, I found that from line 86-87 in the correspondence.py file, it actually computed the squared distance rather than the real distance stated in the equation 11. Could you please make it more clear? Thanks!