提交 f2c9c33f 编写于 作者: D dzhwinter

"fix lrn"

上级 541ddf7e
...@@ -839,9 +839,9 @@ def linear_chain_crf(input, label, param_attr=None): ...@@ -839,9 +839,9 @@ def linear_chain_crf(input, label, param_attr=None):
param_attr(ParamAttr): The attribute of the learnable parameter. param_attr(ParamAttr): The attribute of the learnable parameter.
Returns: Returns:
${log_likelihood_comment} output(${emission_exps_type}): ${emission_exps_comment} \n
${transitionexps_comment} output(${transition_exps_type}): ${transition_exps_comment} \n
${emissionexps_comment} output(${log_likelihood_type}): ${log_likelihood_comment}
""" """
helper = LayerHelper('linear_chain_crf', **locals()) helper = LayerHelper('linear_chain_crf', **locals())
...@@ -4210,7 +4210,7 @@ def lrn(input, n=5, k=1.0, alpha=1e-4, beta=0.75, name=None): ...@@ -4210,7 +4210,7 @@ def lrn(input, n=5, k=1.0, alpha=1e-4, beta=0.75, name=None):
.. math:: .. math::
Output(i, x, y) = Input(i, x, y) / \left( \\ Output(i, x, y) = Input(i, x, y) / \left( \\
k + \alpha \sum\limits^{\min(C, c + n/2)}_{j = \max(0, c - n/2)} \\ k + \alpha \sum\limits^{\min(C, c + n/2)}_{j = \max(0, c - n/2)} \\
(Input(j, x, y))^2\right)^{\beta} (Input(j, x, y))^2\right)^{\beta}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册