mindspore.nn.Softmax2d

class mindspore.nn.Softmax2d[source]

Applies SoftMax over features to each spatial location.

When given a Tensor with shape of \((C, H, W)\) , it will apply Softmax to each location \((c, h, w)\).

Inputs:

x (Tensor) - Tensor of shape \((N, C_{in}, H_{in}, W_{in})\) or \((C_{in}, H_{in}, W_{in})\).

Outputs:

Tensor, which has the same type and shape as x with values in the range[0,1].

Raises

TypeError – If dtype of x is neither float16 nor float32.
ValueError – If data_format is neither ‘NCHW’ nor ‘CHW’.

Supported Platforms:: Ascend GPU CPU

Examples

>>> x = Tensor(np.array([[[[0.1, 0.2]], [[0.3, 0.4]], [[0.6, 0.5]]]]), mindspore.float32)
>>> softmax2d = nn.Softmax2d()
>>> output = softmax2d(x)
>>> print(output)
[[[[0.258, 0.28]], [[0.316, 0.342]], [[0.426, 0.378]]]