From 23aebf0ea7a05b104894b0525525ac8748a06e3d Mon Sep 17 00:00:00 2001 From: fengjiayi Date: Wed, 1 Aug 2018 14:01:24 +0800 Subject: [PATCH] update softmax layer comment --- python/paddle/fluid/layers/nn.py | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py index 058acd4a5..12e7170fc 100644 --- a/python/paddle/fluid/layers/nn.py +++ b/python/paddle/fluid/layers/nn.py @@ -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): """ - The input of the softmax layer is a 2-D tensor with shape N x K (N is the - batch_size, K is the dimension of input feature). The output tensor has the - same shape as the input tensor. + The input of the softmax operator is a tensor of any rank. The output tensor + has the same shape as the input. - For each row of the input tensor, the softmax operator squashes the - K-dimensional vector of arbitrary real values to a K-dimensional vector of real - values in the range [0, 1] that add up to 1. + The input tensor will first be logically flattened to a 2-D matrix. The matrix's + second dimension(row length) is as same as the last dimension of the input + 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 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 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:: -- GitLab