Skip to content

Conversation

@lcy-seso
Copy link
Contributor

@lcy-seso lcy-seso commented Sep 4, 2017

fixes #2246

@lcy-seso lcy-seso requested a review from guoshengCS September 4, 2017 06:30
@lcy-seso lcy-seso force-pushed the rename_mse_to_square_error branch from 6013af1 to fb49bc2 Compare September 4, 2017 06:49
@luotao1
Copy link
Contributor

luotao1 commented Sep 4, 2017

doc/ 下面还有一些mse_cost的,可以一起改掉

[luotao@m1-idl-gpu2-bak24: Paddle] develop -> $ grep -r mse_cost doc doc/api/v2/config/layer.rst:mse_cost doc/api/v2/config/layer.rst:.. autoclass:: paddle.v2.layer.mse_cost doc/getstarted/basic_usage/index_cn.rst: cost = mse_cost(input= ȳ, label=y) doc/getstarted/basic_usage/index_cn.rst: - **回归误差代价层**:回归误差代价层 `mse_cost` 是众多误差代价函数层的一种,它们在训练过程作为网络的出口,用来计算模型的误差,是模型参数优化的目标函数。 doc/getstarted/basic_usage/index_en.rst: cost = mse_cost(input=y_predict, label=y) doc/getstarted/concepts/src/train.py:cost = paddle.layer.mse_cost(input=y_predict, label=y) doc/getstarted/concepts/use_concepts_cn.rst: cost = paddle.layer.mse_cost(input=y_predict, label=y) doc/howto/usage/k8s/k8s_distributed_cn.md:[INFO 2016-11-16 09:10:17,239 networks.py:1289] The output order is [__mse_cost_0__] 
@lcy-seso
Copy link
Contributor Author

lcy-seso commented Sep 4, 2017

@luotao1 done. Thank you ~

cost = paddle.layer.mse_cost(input=y_predict, label=y)
cost = paddle.layer.square_error_cost(input=y_predict, label=y)
其中,x与y为之前描述的输入层;而y_predict是接收x作为输入,接上一个全连接层;cost接收y_predict与y作为输入,接上均方误差层。
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

均方误差建议修改

@lcy-seso lcy-seso force-pushed the rename_mse_to_square_error branch from 845e213 to 10eacac Compare September 4, 2017 08:22
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

3 participants