fscore

F-Score Metrics API

This module contains additional metrics for F-Score.

Classes

Name	Description
MultiF1Score	A wrapper around keras.metrics.F1Score to handle multi-dimensional data.

Machine-readable model

• MultiF1ScoreclassA wrapper around keras.metrics.F1Score to handle multi-dimensional data.

class

MultiF1Score

Python

A wrapper around keras.metrics.F1Score to handle multi-dimensional data.

helia_edge/metrics/fscore.py:16

MultiF1Score()

A wrapper around keras.metrics.F1Score to handle multi-dimensional data. This class collapses down to 2D and treats last dimension as classes.

Example:

import helia_edge as helia

f1 = helia.metrics.MultiF1Score(average='macro')
y_true = np.array([[0, 1, 0], [1, 0, 1]])
y_pred = np.array([[0, 1, 0], [1, 0, 0]])
f1.update_state(y_true, y_pred)
print(f1.result().numpy())

method

update_state

Python

helia_edge/metrics/fscore.py:34

update_state(y_true, y_pred, sample_weight=None)