numpy¶
NumPy implementation of Metrics.
Functions¶
Compute the classwise ECE for a categorical distribution via its class probabilities. |
|
Compute the confidence ECE for a categorical distribution via its class probabilities. |
|
Compute the classwise expected calibration error for NumPy arrays. |
|
Compute the confidence expected calibration error for NumPy arrays. |
|
Compute the log probabilities of a NumPy array. |
|
One-hot encode the first maximum of each probability vector of a NumPy array. |
|
Compute precision-recall curve along the last axis. |
|
Return a NumPy array of probabilities unchanged. |
|
Compute ROC curve along the last axis. |