Precision
It represents the positive samples that are correctly predicted from the total predicted samples. It is defined as:
precision = tp/(tp + fp)
Example
from odin.classes import Metrics
my_metric = Metrics.PRECISION_SCORE
# use my_metric as 'metric' parameter in the analyses
Tasks supported
| Binary Classification | Single-label Classification | Multi-label Classification | Object Detection | Instance Segmentation |
|---|---|---|---|---|
| yes | yes | yes | yes | yes |