wkcn commented on a change in pull request #9939: add multi proposal operator
(cpu version) and fix the bug in proposal op (gpu version)
URL: https://github.com/apache/incubator-mxnet/pull/9939#discussion_r171544927
##########
File path: src/operator/contrib/proposal.cu
##########
@@ -553,10 +553,10 @@ class ProposalGPUOp : public Operator{
cudaMemcpyHostToDevice));
// copy results after nms
- dimGrid.x = (rpn_post_nms_top_n + kMaxThreadsPerBlock - 1) /
kMaxThreadsPerBlock;
+ dimGrid.x = (param_.rpn_post_nms_top_n + kMaxThreadsPerBlock - 1) /
kMaxThreadsPerBlock;
Review comment:
@ZiyueHuang If `count_anchor` < `param_.rpn_post_nms_top_n`,
`rpn_post_nms_top_n` will be `count_anchor`,
and `rpn_post_nms_top_n` will be less than `param_.rpn_post_nms_top_n`.
https://github.com/apache/incubator-mxnet/blob/master/src/operator/contrib/proposal-inl.h#L119
It shows the `batch_size` of the output is `param_.rpn_post_nms_top_n`
instead of `rpn_post_nms_top_n`.
----------------------------------------------------------------
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
With regards,
Apache Git Services
