dwofk/fast-depth

the metrics RMSE

Opened this issue · 2 comments

hi,thanks for sharing such a interesting work,
when i train and validate the FastDepth acording to your method,the metric RMSE is always about 600,far from your ~0.60 in your paper,i wonder if there is anything worng in your method of caculating RMSE but i can't find it out

dwofk commented

Hi @hfutfl

The RMSE in our evaluation code is reported in millimeters [mm]. The RMSE in our paper is reported in meters [m]. So your observed RMSE of ~600 mm equals ~0.60 m.

Thanks for pointing out that this is a source of confusion; I will clarify the metric units in the README.

hi,can you elaborate on how to train fastepth? I trained the code according to the github given by the author, and the result was not good. Thank you very much!!