LostTech.TensorFlow : API Documentation

Type BinaryCrossentropy

Namespace tensorflow.keras.losses

Parent LossFunctionWrapper

Interfaces IBinaryCrossentropy

Computes the cross-entropy loss between true labels and predicted labels.

Use this cross-entropy loss when there are only two label classes (assumed to be 0 and 1). For each example, there should be a single floating-point value per prediction.

In the snippet below, each of the four examples has only a single floating-pointing value, and both `y_pred` and `y_true` have the shape `[batch_size]`.

Usage: Usage with the tf.keras API:
Show Example
bce = tf.keras.losses.BinaryCrossentropy()
            loss = bce([0., 0., 1., 1.], [1., 1., 1., 0.])
            print('Loss: ', loss.numpy())  # Loss: 11.522857 


Public properties

object fn get; set;

bool from_logits get; set;

string name get; set;

object PythonObject get;

string reduction get; set;