how to speed up the run time performance?
mmxuan18 opened this issue · comments
i try the model on my dataset, the result is magic.
but in my nvidia 1070 gpu card, the python code time cost 170ms. did there anyway to speed up the performance?
You can reduce you input resolution to 320x240 or others.
I have already tried on server, iPhone and Android and worked.
But even the original size 384x512, single image will be 78 ms with 1080ti.
320x240 will be 35ms with same condition.
@CR-Ko how you convert it on mobile device? TF version + opencv::dnn?
@CR-Ko can you please share your converted model? Im trying to run this on ios but was not able to convert it.
@mlinxiang have you been able to improve the speed?