yongwww commented on pull request #7137: URL: https://github.com/apache/tvm/pull/7137#issuecomment-750765455
> With the fix in this PR applied and using `rpn_pre_nms_top_n_test` = 200, on GTX 1070 ti > > Torch GPU: 0.093 sec > TVM GPU: 0.39 sec (no tuning or cudnn) How about the perf numbers with default value of `rpn_pre_nms_top_n_test`? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
