binary_crossentropy

dragon.vm.tensorflow.keras.losses.binary_crossentropy(
  y_true,
  y_pred,
  reduction='valid'
)[source]

Compute the binary cross entropy with contiguous targets.

The CrossEntropy function is defined as:

\[\text{CrossEntropy}(p_{t}) = -\log(p_{t}) \]

Examples:

y_true = tf.constant([0., 0., 1., 1.])
y_pred = tf.constant([0.1, 0.2, 0.3, 0.4])
print(tf.keras.losses.binary_crossentropy(y_true, y_pred))  # 0.65247655
Parameters:
  • y_true (dragon.Tensor) – The ground truth tensor.
  • y_pred (dragon.Tensor) – The logits tensor.
  • reduction ({'none', 'sum', 'mean', 'valid'}, optional) – The reduction method.
Returns:

dragon.Tensor – The output tensor.