tf.keras.metrics.binary_accuracy

TensorFlow 1 version View source on GitHub

Calculates how often predictions matches binary labels.

tf.keras.metrics.binary_accuracy(
    y_true, y_pred, threshold=0.5
)

Standalone usage:

y_true = [[1], [1], [0], [0]] y_pred = [[1], [1], [0], [0]] m = tf.keras.metrics.binary_accuracy(y_true, y_pred) assert m.shape == (4,) m.numpy() array([1., 1., 1., 1.], dtype=float32)

y_true Ground truth values. shape = [batch_size, d0, .. dN].
y_pred The predicted values. shape = [batch_size, d0, .. dN].
threshold (Optional) Float representing the threshold for deciding whether prediction values are 1 or 0.

Binary accuracy values. shape = [batch_size, d0, .. dN-1]