One NCS device run MTCNN is so slow

Intel® Distribution of OpenVINO™ Toolkit

Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

One NCS device run MTCNN is so slow

921 Views

I wanna implement face detect in NCS, and I found this github: github.com/movidius/ncappzoo/tree/master/tensorflow/MTCNN,which implement faca detect use MTCNN model, but I just have one NCS device , so I change the code to suit my device. But, it detected a picture just one face, took 2 seconds, it is so slow to video face detect.

could anyone tell me is this normal? how to increase detection speed？

this is a script of I change tow NCS to one NCS for MTCNN.https://blog.csdn.net/lcandtt/article/details/82714360

Link Copied

0 Replies

Community support is provided during standard business hours (Monday to Friday 7AM - 5PM PST). Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.