Skip to content

abs

abs

Compute the absolute value of a tensor.

This method can be used with Numpy data: 

n = np.array([-2, 7, -19])
b = fe.backend.abs(n)  # [2, 7, 19]

This method can be used with TensorFlow tensors: 

t = tf.constant([-2, 7, -19])
b = fe.backend.abs(t)  # [2, 7, 19]

This method can be used with PyTorch tensors: 

p = torch.tensor([-2, 7, -19])
b = fe.backend.abs(p)  # [2, 7, 19]

Parameters:

Name Type Description Default
tensor Tensor

The input value.

 required

Returns:

Type Description
Tensor

The absolute value of tensor.

Raises:

Type Description
ValueError

If tensor is an unacceptable data type.
Source code in fastestimator\fastestimator\backend\abs.py 
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
def abs(tensor: Tensor) -> Tensor:
    """Compute the absolute value of a tensor.

    This method can be used with Numpy data:
    ```python
    n = np.array([-2, 7, -19])
    b = fe.backend.abs(n)  # [2, 7, 19]
    ```

    This method can be used with TensorFlow tensors:
    ```python
    t = tf.constant([-2, 7, -19])
    b = fe.backend.abs(t)  # [2, 7, 19]
    ```

    This method can be used with PyTorch tensors:
    ```python
    p = torch.tensor([-2, 7, -19])
    b = fe.backend.abs(p)  # [2, 7, 19]
    ```

    Args:
        tensor: The input value.

    Returns:
        The absolute value of `tensor`.

    Raises:
        ValueError: If `tensor` is an unacceptable data type.
    """
    if tf.is_tensor(tensor):
        return tf.abs(tensor)
    elif isinstance(tensor, torch.Tensor):
        return torch.abs(tensor)
    elif isinstance(tensor, np.ndarray):
        return np.abs(tensor)
    else:
        raise ValueError("Unrecognized tensor type {}".format(type(tensor)))