The yolov8n inference and post-processing time increases at the time of processing up to the 20th image and remains

[KY-wwang]

trafficstars

Env

• GPU, 1660Ti, laptop
• OS, win11
• Cuda 11.8
• TensorRT 8.6.1.6

About this repo

• which branch/tag/commit are you using? yolov5-v7.0
• which model? yolov8n

Your problem

In the detection of 72 pictures, in the detection of a certain number of pictures to start reasoning and post-processing time increased significantly, and finally remain in a picture 72ms. should not be a hardware problem, I changed to the server or will have this problem. 在检测72张图片的时候,在检测到某个数量的图片开始推理和后处理时间明显增加,最后保持在一张图片72ms.应该不是硬件的问题,我换成服务器还是会有这个问题

[wang-xinyu]

观测下GPU的频率和功耗有没有变化

[KY-wwang]

观测下GPU的频率和功耗有没有变化

我在cmd中用nvidia-smi -l 1看了下,整个过程中GPU的功率在4W到24W之间,GPU当前的使用率在1%到17%之间,应该不是gpu的限制引起的

[stale[bot]]

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.