Closed Leo63963 closed 2 years ago
Hi! Thanks for your great work, really appreciate that. Just kindly ask, could you please tell, for the training of the network, when calculating the regression loss, the smooth L1 loss, why you multiple 9.0, as shown below
https://github.com/pjl1995/CTracker/blob/e0af0e1244a464ba45f2ed62e614dc3fe26ff462/losses.py#L159
Thanks.
Hi! Thanks for your great work, really appreciate that. Just kindly ask, could you please tell, for the training of the network, when calculating the regression loss, the smooth L1 loss, why you multiple 9.0, as shown below
https://github.com/pjl1995/CTracker/blob/e0af0e1244a464ba45f2ed62e614dc3fe26ff462/losses.py#L159
Thanks.