functional.py 文件源码

def softmax(input, dim=None, _stacklevel=3):
    r"""Applies a softmax function.

    Softmax is defined as:

    :math:`softmax(x) = \frac{exp(x_i)}{\sum_j exp(x_j)}`

    It is applied to all slices along dim, and will rescale them so that the elements
    lie in the range `(0, 1)` and sum to 1.

    See :class:`~torch.nn.Softmax` for more details.

    Arguments:
        input (Variable): input
        dim (int): A dimension along which softmax will be computed.

    .. note::
        This function doesn't work directly with NLLLoss,
        which expects the Log to be computed between the Softmax and itself.
        Use log_softmax instead (it's faster and has better numerical properties).

    """
    if dim is None:
        dim = _get_softmax_dim('softmax', input.dim(), _stacklevel)
    return torch._C._nn.softmax(input, dim)