使用app_tidl_od demos,运行yolov5s6_384模型。官网提供模型为6GFlops,为什么c7x资源占用高达35%?
This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
使用app_tidl_od demos,运行yolov5s6_384模型。官网提供模型为6GFlops,为什么c7x资源占用高达35%?
非常抱歉回复晚了,下面是e2e工程师的回复。
Actual utilization depends on multiple factors including resolution, number of channels, types of layers etc. Right way would be to check the layer level performance to see where are the bottlenecks. You can refer the following to troubleshoot performance issues :
https://github.com/TexasInstruments/edgeai-tidl-tools/blob/master/docs/tidl_osr_debug.md#troubleshooting-for-performance-issues