关于mobilenet rknn模型的推理时间问题

slim 发表于 2019-2-15 11:20
@chuyee I got the same results. About ~0.7s for mobilenet_ssd.  rknn.eval_perf() is the simulator  ...

That's a critical issue. Can someone from RK confirm?

rknn.inference()这个接口耗时是有异常，rockchip工程师目前正在定位，估计下个版本rknn-toolkit会解决。
rknn.eval_perf()这个评估时间是准确的，记录了NPU在推理时的所有op的耗时情况。

One more information, seems like this is a Python specific bug. C API result is much faster. Below is my rknn_mobilenet running time:

rknn_init takes 0.068531s
rknn_query takes 0.000018s
rknn_inputs_set takes 0.001168s
rknn_run takes 0.000126s
rknn_outputs_get takes 0.000637s

perf_run.run_duration = 9993 us

Does anyone know how to map each rknn functions to the perf duration (~10ms)? I know rknn_run() is non-blocking call and rknn_outputs_get() is blocking. But it's only 0.6ms. What else does the 10ms include?

这是rknn-toolkit里面的问题，等待更新

啥时候能修好？

程子 发表于 2019-2-19 14:56
啥时候能修好？

下个发布版本就能解决，我这边拿到的内部版本简单测试结果如下：
mobilenet_v1: inference time:0.015120s
mobilenet-ssd：inference time: 0.030780s

slim 发表于 2019-2-15 11:20
@chuyee I got the same results. About ~0.7s for mobilenet_ssd.  rknn.eval_perf() is the simulator  ...

怎么确定是否使用NPU？有没有方法

slim 发表于 2019-2-15 11:20
@chuyee I got the same results. About ~0.7s for mobilenet_ssd.  rknn.eval_perf() is the simulator  ...

how can i  get the information inferance function using?is NPU or is CPU

MraxZhao 发表于 2019-2-21 12:39
how can i  get the information inferance function using?is NPU or is CPU

I don't know either. I guess it might be done by CPU because inference result is correct while the speed is much slower.

slim 发表于 2019-2-15 11:20
@chuyee I got the same results. About ~0.7s for mobilenet_ssd.  rknn.eval_perf() is the simulator  ...

rknn python推理慢的问题，后续更新版本解决。