Closed hhaAndroid closed 3 years ago
Hi, thanks for your interest.
In the uniform_matcher
, we mark the indexes of both topk anchors and topk predict boxes as positives, which gives stable and slightly higher performance than only use the topk anchors(37.7 vs. 37.1).
We implement the code for thresholds in the loss
function. You can find it here(L344-L365).
Hi. thank you for your reply.
Thanks, I get it. I think this step is more critical. Have you considered updating the paper about uniform_matcher
?
Thanks for your advice.
Although I don't agree with the idea that the step is more critical
, I will update the paper with this part.
Thank you for your reply. Looking forward to your future work!
Very good job, but I don't know why The Uniform Matching part of the paper and the code are inconsistent?
paper:
code:
Looking forward to your answer!