Corrected wrongly used "training" with "testing"
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
parent
452d97b4b2
commit
a336a9ad58
|
@ -14,5 +14,5 @@ Both results from macro and micro averaging are presented.
|
|||
|
||||
Results show a significant improvement of the object detection performance
|
||||
with a higher confidence threshold. The usage of non-maximum suppression
|
||||
improves performance as well. Usage of dropout layers during training does
|
||||
improves performance as well. Usage of dropout layers during testing does
|
||||
not provide a better result, a lower keep ratio decreases the performance.
|
||||
|
|
Loading…
Reference in New Issue