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.
yolov5_ti_lite模型PC端推理结果（13.565ms）：
yolov5_ti_lite模型板端推理结果（9.700ms）：
请问TI专家，什么原因导致两种方式的测得的误差较大。
两种方式测得的精度是否一致？
已咨询e2e英文论坛产品线工程师，请关注下面帖子的回复。https://e2e.ti.com/support/processors-group/processors/f/processors-forum/1304676/tda4vm-different-delay-time-between-board-emulation-and-pc-emulation
请看下面e2e工程师的回复。
To benchmark any network we recommend to run the inference on Target EVM.
The benchmark number reproduced through Host Emulation run are prone to other facts like, DDR latency/ register reads latencies etc
One can use them for reference but we highly recommend EVM inference for benchmarking the models.
好的 多谢！
