Error Rate
It represents the ratio of misclassified samples to the total number of samples. It is the complement of the accuracy and it is defined as:
error_rate = (fp + fn)/(tp + tn + fp + fn)
Example
from odin.classes import Metrics
my_metric = Metrics.ERROR_RATE
# 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 | no | no |