Skip to content

Comments

Add python api for lstmp operator#7888

Merged
kuke merged 5 commits intoPaddlePaddle:developfrom
kuke:add_lstmp_doc
Jan 29, 2018
Merged

Add python api for lstmp operator#7888
kuke merged 5 commits intoPaddlePaddle:developfrom
kuke:add_lstmp_doc

Conversation

@kuke
Copy link
Contributor

@kuke kuke commented Jan 25, 2018

Resolve #7813

@kuke kuke requested review from luotao1, pkuyym and qingqing01 January 28, 2018 08:54
@kuke
Copy link
Contributor Author

kuke commented Jan 28, 2018

2018-01-28 5 03 13


r_t & = \overline{act_h}(W_{rh}h_t)

where the :math:`W` terms denote weight matrices (e.g. :math:`W_{xi}` is
Copy link
Contributor

Choose a reason for hiding this comment

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

Please reorganize these description like:

  • :math:W_{fc}: {description}
  • :math:W_{oc}: {description}

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Done

mini-batch, D is the hidden size.
size(int): 4 * hidden size.
proj_size(int): The size of projection output.
param_attr(ParamAttr|None): The parameter attribute for the learnable
Copy link
Contributor

Choose a reason for hiding this comment

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

Please add some attribution examples.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Done

Copy link
Contributor Author

@kuke kuke left a comment

Choose a reason for hiding this comment

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

All done, thx


r_t & = \overline{act_h}(W_{rh}h_t)

where the :math:`W` terms denote weight matrices (e.g. :math:`W_{xi}` is
Copy link
Contributor Author

Choose a reason for hiding this comment

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

Done

mini-batch, D is the hidden size.
size(int): 4 * hidden size.
proj_size(int): The size of projection output.
param_attr(ParamAttr|None): The parameter attribute for the learnable
Copy link
Contributor Author

Choose a reason for hiding this comment

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

Done

@kuke
Copy link
Contributor Author

kuke commented Jan 29, 2018

2018-01-29 12 08 03

Copy link
Contributor

@pkuyym pkuyym left a comment

Choose a reason for hiding this comment

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

LGTM

@kuke kuke merged commit 0311fd1 into PaddlePaddle:develop Jan 29, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants