Skip to content

to_number

to_number

Convert an input value into a Numpy ndarray.

This method can be used with Python and Numpy data: 

b = fe.backend.to_number(5)  # 5 (type==np.ndarray)
b = fe.backend.to_number(4.0)  # 4.0 (type==np.ndarray)
n = np.array([1, 2, 3])
b = fe.backend.to_number(n)  # [1, 2, 3] (type==np.ndarray)

This method can be used with TensorFlow tensors: 

t = tf.constant([1, 2, 3])
b = fe.backend.to_number(t)  # [1, 2, 3] (type==np.ndarray)

This method can be used with PyTorch tensors: 

p = torch.tensor([1, 2, 3])
b = fe.backend.to_number(p)  # [1, 2, 3] (type==np.ndarray)

Parameters:

Name Type Description Default
data Union[tf.Tensor, torch.Tensor, np.ndarray, int, float]

The value to be converted into a np.ndarray.

 required

Returns:

Type Description
np.ndarray

An ndarray corresponding to the given data.
Source code in fastestimator\fastestimator\backend\to_number.py 
22
23
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
def to_number(data: Union[tf.Tensor, torch.Tensor, np.ndarray, int, float]) -> np.ndarray:
    """Convert an input value into a Numpy ndarray.

    This method can be used with Python and Numpy data:
    ```python
    b = fe.backend.to_number(5)  # 5 (type==np.ndarray)
    b = fe.backend.to_number(4.0)  # 4.0 (type==np.ndarray)
    n = np.array([1, 2, 3])
    b = fe.backend.to_number(n)  # [1, 2, 3] (type==np.ndarray)
    ```

    This method can be used with TensorFlow tensors:
    ```python
    t = tf.constant([1, 2, 3])
    b = fe.backend.to_number(t)  # [1, 2, 3] (type==np.ndarray)
    ```

    This method can be used with PyTorch tensors:
    ```python
    p = torch.tensor([1, 2, 3])
    b = fe.backend.to_number(p)  # [1, 2, 3] (type==np.ndarray)
    ```

    Args:
        data: The value to be converted into a np.ndarray.

    Returns:
        An ndarray corresponding to the given `data`.
    """
    if isinstance(data, tf.Tensor):
        data = data.numpy()
    elif isinstance(data, torch.Tensor):
        if data.requires_grad:
            data = data.detach().numpy()
        else:
            data = data.numpy()
    return np.array(data)