Skip to content

_reduce_min

reduce_min

Compute the min value along a given axis of a tensor.

This method can be used with Numpy data: 

n = np.array([[[1.0, 2.0], [3.0, 4.0]], [[5.0, 6.0], [7.0, 8.0]]])
b = fe.backend.reduce_min(n)  # 1
b = fe.backend.reduce_min(n, axis=0)  # [[1, 2], [3, 4]]
b = fe.backend.reduce_min(n, axis=1)  # [[1, 2], [5, 6]]
b = fe.backend.reduce_min(n, axis=[0,2])  # [1, 3]

This method can be used with TensorFlow tensors: 

t = tf.constant([[[1.0, 2.0], [3.0, 4.0]], [[5.0, 6.0], [7.0, 8.0]]])
b = fe.backend.reduce_min(t)  # 1
b = fe.backend.reduce_min(t, axis=0)  # [[1, 2], [3, 4]]
b = fe.backend.reduce_min(t, axis=1)  # [[1, 2], [5, 6]]
b = fe.backend.reduce_min(t, axis=[0,2])  # [1, 3]

This method can be used with PyTorch tensors: 

p = torch.tensor([[[1.0, 2.0], [3.0, 4.0]], [[5.0, 6.0], [7.0, 8.0]]])
b = fe.backend.reduce_min(p)  # 1
b = fe.backend.reduce_min(p, axis=0)  # [[1, 2], [3, 4]]
b = fe.backend.reduce_min(p, axis=1)  # [[1, 2], [5, 6]]
b = fe.backend.reduce_min(p, axis=[0,2])  # [1, 3]

Parameters:

Name Type Description Default
tensor Tensor

The input value.

 required
axis Union[None, int, Sequence[int]]

Which axis or collection of axes to compute the min along.

 None
keepdims bool

Whether to preserve the number of dimensions during the reduction.

 False

Returns:

Type Description
Tensor

The min values of tensor along axis.

Raises:

Type Description
ValueError

If tensor is an unacceptable data type.
Source code in fastestimator/fastestimator/backend/_reduce_min.py 
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
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
def reduce_min(tensor: Tensor, axis: Union[None, int, Sequence[int]] = None, keepdims: bool = False) -> Tensor:
    """Compute the min value along a given `axis` of a `tensor`.

    This method can be used with Numpy data:
    ```python
    n = np.array([[[1.0, 2.0], [3.0, 4.0]], [[5.0, 6.0], [7.0, 8.0]]])
    b = fe.backend.reduce_min(n)  # 1
    b = fe.backend.reduce_min(n, axis=0)  # [[1, 2], [3, 4]]
    b = fe.backend.reduce_min(n, axis=1)  # [[1, 2], [5, 6]]
    b = fe.backend.reduce_min(n, axis=[0,2])  # [1, 3]
    ```

    This method can be used with TensorFlow tensors:
    ```python
    t = tf.constant([[[1.0, 2.0], [3.0, 4.0]], [[5.0, 6.0], [7.0, 8.0]]])
    b = fe.backend.reduce_min(t)  # 1
    b = fe.backend.reduce_min(t, axis=0)  # [[1, 2], [3, 4]]
    b = fe.backend.reduce_min(t, axis=1)  # [[1, 2], [5, 6]]
    b = fe.backend.reduce_min(t, axis=[0,2])  # [1, 3]
    ```

    This method can be used with PyTorch tensors:
    ```python
    p = torch.tensor([[[1.0, 2.0], [3.0, 4.0]], [[5.0, 6.0], [7.0, 8.0]]])
    b = fe.backend.reduce_min(p)  # 1
    b = fe.backend.reduce_min(p, axis=0)  # [[1, 2], [3, 4]]
    b = fe.backend.reduce_min(p, axis=1)  # [[1, 2], [5, 6]]
    b = fe.backend.reduce_min(p, axis=[0,2])  # [1, 3]
    ```

    Args:
        tensor: The input value.
        axis: Which axis or collection of axes to compute the min along.
        keepdims: Whether to preserve the number of dimensions during the reduction.

    Returns:
        The min values of `tensor` along `axis`.

    Raises:
        ValueError: If `tensor` is an unacceptable data type.
    """
    if tf.is_tensor(tensor):
        return tf.reduce_min(tensor, axis=axis, keepdims=keepdims)
    elif isinstance(tensor, torch.Tensor):
        if axis is None:
            axis = list(range(len(tensor.shape)))
        axis = to_list(axis)
        axis = reversed(sorted(axis))
        for ax in axis:
            tensor = tensor.min(dim=ax, keepdim=keepdims)[0]
        return tensor
    elif isinstance(tensor, np.ndarray):
        if isinstance(axis, list):
            axis = tuple(axis)
        return np.min(tensor, axis=axis, keepdims=keepdims)
    else:
        raise ValueError("Unrecognized tensor type {}".format(type(tensor)))