categorical_crossentropy¶

dragon.vm.tensorflow.keras.losses.categorical_crossentropy(
  y_true,
  y_pred,
  axis=- 1,
  reduction='mean'
)[source]¶

Compute the categorical cross entropy with contiguous targets.

Examples:

y_true = tf.constant([[0., 1.], [1., 0.]])
y_pred = tf.constant([[0.5, 0.5], [0.3, 0.7]])
print(tf.keras.cost.categorical_crossentropy(y_true, y_pred))  # 0.8030813

Parameters:

• y_true (dragon.Tensor) – The ground truth tensor.
• y_pred (dragon.Tensor) – The logits tensor.
• axis (int, optional, default=-1) – The reduction axis.
• reduction ({'none', 'sum', 'mean'}, optional) – The reduction method.

Returns:

dragon.Tensor – The loss.