LambdaFunction¶

class probnum.functions.LambdaFunction(fn, input_shape, output_shape=())[source]¶

Bases: Function

Define a Function from a given callable.

Creates a Function from a given callable and in- and output shapes. This provides a convenient interface to define a Function.

Parameters:

fn (Callable[[np.ndarray], np.ndarray]) – Callable defining the function.
input_shape (ShapeLike) – Input shape.
output_shape (ShapeLike) – Output shape.

Examples

>>> import numpy as np
>>> from probnum.functions import LambdaFunction
>>> fn = LambdaFunction(fn=lambda x: 2 * x + 1, input_shape=(2,), output_shape=(2,))
>>> fn(np.array([[1, 2], [4, 5]]))
array([[ 3,  5],
       [ 9, 11]])

See also

Function: Callable with a fixed in- and output shape.

Attributes Summary

`input_ndim`	Syntactic sugar for `len(input_shape)`.
`input_shape`	Shape of the function's input.
`output_ndim`	Syntactic sugar for `len(output_shape)`.
`output_shape`	Shape of the function's output.

Methods Summary

__call__(x)

Evaluate the function at a given input.

Attributes Documentation

input_ndim¶: Syntactic sugar for len(input_shape).

input_shape¶

Shape of the function’s input.

For a scalar-input function, this is an empty tuple.

output_ndim¶: Syntactic sugar for len(output_shape).

output_shape¶

Shape of the function’s output.

For scalar-valued function, this is an empty tuple.

Methods Documentation

__call__(x)¶

Evaluate the function at a given input.

The function is vectorized over the batch shape of the input.

Parameters:: x (ArrayLike) – shape= batch_shape + input_shape – (Batch of) input(s) at which to evaluate the function.
Returns:: shape= batch_shape + output_shape – Function evaluated at the given (batch of) input(s).
Return type:: fx
Raises:: ValueError – If the shape of x does not match input_shape along its last dimensions.