Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix the output of cnn in DSSM. #534

Merged
merged 4 commits into from
Dec 12, 2017

Conversation

peterzhang2029
Copy link
Contributor

resolve #526

@peterzhang2029 peterzhang2029 changed the title Fix the output of cnn in Dssm. Fix the output of cnn in DSSM. Dec 11, 2017
@@ -151,7 +151,7 @@ def create_conv(context_len, hidden_size, prefix):
logger.info("create a sequence_conv_pool which context width is 4")
conv_4 = create_conv(4, self.dnn_dims[1], "cnn")

return conv_3, conv_4
return paddle.layer.concat(input=[conv_3, conv_4])
Copy link
Collaborator

@lcy-seso lcy-seso Dec 11, 2017

Choose a reason for hiding this comment

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

  • Could you please also help to fix the logging information in line 151:
    logger.info("create a sequence_conv_pool whose context width is 4.")
  • Could you please confirm with @ChunweiYan , is concat or addto needed here as his original design.

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

@Superjomn Superjomn left a comment

Choose a reason for hiding this comment

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

LGTM

@peterzhang2029 peterzhang2029 merged commit cc30fad into PaddlePaddle:develop Dec 12, 2017
@peterzhang2029 peterzhang2029 deleted the dssm_fix branch December 12, 2017 01:57
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.

bug in cnn-rank-dssm
3 participants