pengzhao-intel commented on issue #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#issuecomment-371026517 @wkcn thanks for the detail profiling data. Regarding sorting, you can use MKL sort in case the library is set to MKL. It will be much faster than sequential sort. https://software.intel.com/en-us/mkl-developer-reference-c-lasrt Regarding calculating nms, the current implementation is not very good for the better performance. @xinyu-intel will do several experiments in local and back to you later.
---------------------------------------------------------------- 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