Score threshold's effect on different eval metrics
Below are plotted precision, recall and mAP for both train and test data for different score threshold values (calibration parameter of the inference model). Score threshold values above 0.1 seem to give better trade off between precision and recall for both data sets.
Created on December 29|Last edited on December 29
Comment
Section 1
Add markdown, images, and LaTeX\LaTeX
Sweep: lw526gt7 1
20
Sweep: lw526gt7 2
0
Add a comment