Replies: 2 comments
-
@chun-chun123 Line 31 in 052b967 But I saw in the code that L1 loss was used, so I asked this question. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
As the title says, does the l1 loss have a better performance than the smooth l1 loss, is there any relevant data? Because in your paper, the regression loss uses a smooth l1 loss.
I am looking forward to someone who can answer me, thank you.
Beta Was this translation helpful? Give feedback.
All reactions