tensorrtx
tensorrtx copied to clipboard
yolov5 nms支持CUDA加速
您好, 是否考虑在yolov5中增加nms使用cuda加速推理?
意义不大,yololayer已经对输出做了过滤,nms计算的bbox很少
感谢您的回复,可能在密集样本中,当obj多的时候,nms还是会有1ms左右的耗时
1ms在大多数应用场景可以忽略了
也可以尝试手动添加nms plugin试试
感谢您的回复,可能在密集样本中,当obj多的时候,nms还是会有1ms左右的耗时
https://github.com/upczww/YoLov5-TensorRT-NMS可以参考这个,然后做个pr
感谢你的回复,我尝试一下
---原始邮件--- 发件人: @.> 发送时间: 2024年5月7日(周二) 下午3:21 收件人: @.>; 抄送: @.@.>; 主题: Re: [wang-xinyu/tensorrtx] yolov5 nms支持CUDA加速 (Issue #1500)
感谢您的回复,可能在密集样本中,当obj多的时候,nms还是会有1ms左右的耗时
https://github.com/upczww/YoLov5-TensorRT-NMS可以参考这个,然后做个pr
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.