You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Sorry for the delay. This is a good question, the scale of 60 is directly adopted from the previous paper, CounTR (example in this line).
Basically, it will scale up the gt by 60, and when calculating the metric the scale will be canceled out. Therefore, we believe it will not affect the performance as long as the same scale is applied for training and inference (and there is no numerical instability). However, we did not experiment with other scales and you may try how different scale may affect the model.
how did you determine that the scaling factor is equal to 60? Does this have any significance?
The text was updated successfully, but these errors were encountered: