-
Prerequisite
💬 Describe the reimplementation questionsHello, I found that the map value has been very low during the training of target detection of a category, and it seems that the recall rate is normal. What is the reason for this?
EnvironmentPyhon3.7 Expected resultsNo response Additional informationNo response |
Beta Was this translation helpful? Give feedback.
Answered by
ZwwWayne
Oct 31, 2022
Replies: 1 comment 1 reply
-
|
This is because the model predicts too many objects. You may consider increase the score_thr in the test_cfg. |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
test_cfg In which file is this modified? Thank you |
Beta Was this translation helpful? Give feedback.
Answer selected by
ZwwWayne
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This is because the model predicts too many objects. You may consider increase the score_thr in the test_cfg.