Training accuracy gap #11650
Unanswered
1781686573
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Why is the difference between the mAP values trained on the public dataset and the results in other people's papers so large?
For example, the mAP0.5 I trained on the VisDrone dataset was only 36%, but the one in the paper reached 49%
Beta Was this translation helpful? Give feedback.
All reactions