TensorFlow 2 version View source on GitHub

Computes the Poisson loss between y_true and y_pred.

The Poisson loss is the mean of the elements of the Tensor y_pred - y_true * log(y_pred).


loss = tf.keras.losses.poisson([1.4, 9.3, 2.2], [4.3, 8.2, 12.2])
print('Loss: ', loss.numpy())  # Loss: -0.8045559

y_true Tensor of true targets.
y_pred Tensor of predicted targets.

A Tensor with the mean Poisson loss.

InvalidArgumentError If y_true and y_pred have incompatible shapes.