[ 
https://issues.apache.org/jira/browse/MXNET-40?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16392201#comment-16392201
 ] 

ASF GitHub Bot commented on MXNET-40:
-------------------------------------

wkcn commented on issue #9939: [MXNET-40]add multi proposal operator (cpu 
version) and fix the bug in proposal op (gpu version)
URL: https://github.com/apache/incubator-mxnet/pull/9939#issuecomment-370285916
 
 
   @pengzhao-intel @xinyu-intel 
   Thank you! I will have a try.
   The performance table
   
   name|time (ms)
   ------|----------
   BBoxTransformInv|268
   IoUTransformInv|Not used
   FilterBox|22
   CopyScore|18
   ReverseArgsort(unstable sort)|7303
   ReorderProposals|338
   nms(calculate area)|286
   nms(calcuate nms)|7547
   allocate memory for workspace|1
   copy anchor to workspace_proposal|0
   enumrate all shifted anchors|9
   copy workspace_proposals_base to workspace_proposals|162
   assign foreground scores for each anchor|45
   prepare output|3
   Total|16002
   
   Using stable sort to sort anchors (ReverseArgsort) will increase about 3000 
ms.
   Sorry, it seems that I counted the time of all threads. I will update the 
performance table.
   
   

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


> add multi proposal operator (cpu version) and fix the bug in proposal op (gpu 
> version)
> --------------------------------------------------------------------------------------
>
>                 Key: MXNET-40
>                 URL: https://issues.apache.org/jira/browse/MXNET-40
>             Project: Apache MXNet
>          Issue Type: Improvement
>            Reporter: Kan Wu
>            Priority: Major
>
> The multi_proposal operator ({{mxnet.sym.contrib.MultiProposal}}, CPU 
> version) is not implemented before.
> I wrote the code about it.
> And I found there was a bug in _proposal.cu_ and _multi_proposal.cu_.
> The {{batch_size}} of the output of _Proposal_ and _MultiProposal_ are both 
> {{param_.rpn_post_nms_top_n}}.
> When {{count_anchors < param_.rpn_post_nms_top_n}}, the variable 
> {{rpn_post_nms_top_n}} will be {{count_anchors}}, which is less than 
> {{param_.rpn_post_nms_top_n}}.
> [https://github.com/apache/incubator-mxnet/blob/master/src/operator/contrib/proposal.cu#L438]
> It will cause the problem that the output whose index is larger than 
> {{rpn_post_nms_top_n}} will be _not assigned_.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@mxnet.apache.org
For additional commands, e-mail: issues-h...@mxnet.apache.org

Reply via email to