update softmax layer comment

fea/anakin-support-x86
fengjiayi 7 years ago
parent e7d8e16a66
commit 23aebf0ea7

@ -1313,13 +1313,16 @@ def sequence_softmax(input, param_attr=None, bias_attr=None, use_cudnn=True):
def softmax(input, param_attr=None, bias_attr=None, use_cudnn=True, name=None): def softmax(input, param_attr=None, bias_attr=None, use_cudnn=True, name=None):
""" """
The input of the softmax layer is a 2-D tensor with shape N x K (N is the The input of the softmax operator is a tensor of any rank. The output tensor
batch_size, K is the dimension of input feature). The output tensor has the has the same shape as the input.
same shape as the input tensor.
For each row of the input tensor, the softmax operator squashes the The input tensor will first be logically flattened to a 2-D matrix. The matrix's
K-dimensional vector of arbitrary real values to a K-dimensional vector of real second dimension(row length) is as same as the last dimension of the input
values in the range [0, 1] that add up to 1. tensor, and the first dimension(column length) is the product of all other
dimensions of the input tensor. For each row of the matrix, the softmax operator
squashes the K-dimensional(K is the width of the matrix, which is also the size
of the input tensor's last dimension) vector of arbitrary real values to a
K-dimensional vector of real values in the range [0, 1] that add up to 1.
It computes the exponential of the given dimension and the sum of exponential It computes the exponential of the given dimension and the sum of exponential
values of all the other dimensions in the K-dimensional vector input. values of all the other dimensions in the K-dimensional vector input.
@ -1327,7 +1330,7 @@ def softmax(input, param_attr=None, bias_attr=None, use_cudnn=True, name=None):
exponential values of all the other dimensions is the output of the softmax exponential values of all the other dimensions is the output of the softmax
operator. operator.
For each row :math:`i` and each column :math:`j` in Input(X), we have: For each row :math:`i` and each column :math:`j` in the matrix, we have:
.. math:: .. math::

Loading…
Cancel
Save