tf.compat.v1.math.maximum  |  TensorFlow v2.16.1 (original) (raw)

tf.compat.v1.math.maximum

Stay organized with collections Save and categorize content based on your preferences.

Returns the max of x and y (i.e. x > y ? x : y) element-wise.

tf.compat.v1.math.maximum(
    x: Annotated[Any, tf.raw_ops.Any],
    y: Annotated[Any, tf.raw_ops.Any],
    name=None
) -> Annotated[Any, tf.raw_ops.Any]

Example:

x = tf.constant([0., 0., 0., 0.]) y = tf.constant([-2., 0., 2., 5.]) tf.math.maximum(x, y) <tf.Tensor: shape=(4,), dtype=float32, numpy=array([0., 0., 2., 5.], dtype=float32)>

Note that maximum supports broadcast semantics for x and y.

x = tf.constant([-5., 0., 0., 0.]) y = tf.constant([-3.]) tf.math.maximum(x, y) <tf.Tensor: shape=(4,), dtype=float32, numpy=array([-3., 0., 0., 0.], dtype=float32)>

The reduction version of this elementwise operation is tf.math.reduce_max