search

cvlab-stonybrook / DM-Count

Code for NeurIPS 2020 paper: Distribution Matching for Crowd Counting.
MIT License
218 stars 52 forks source link

Confusing Definition of the OT Loss #23

Closed Yiming-M closed 2 years ago

Yiming-M commented 3 years ago

Hi Boyu,

I really appreciate your and your team's contribution to crowd counting. It seems that the proposed DM-Count loss can improve the performance a lot.

However, I found the OT loss defined in ot_loss.py very confusing. There are many notations without proper comments or documentations. Could you please standardise the code so that it only takes the predicted density map & the ground-truth density map as inputs?

Many thanks, Yiming