Hi,
When using NCSDK for programming the original NCS (MYRIAD 2), the mvNCCompile command had a -'s' option to specify the number of SHAVEs (up to 12). I can't find anything similar in OpenVINO documentation, does it exist? If not, then does it automatically use the max # of SHAVEs (16 for NCS2)?
Thanks.
Link Copied
Dear Chris,
Great question. Perhaps this post will help you in the meantime while I research your answer ?
https://software.intel.com/en-us/forums/computer-vision/topic/806247
Thanks for using OpenVino !
Shubha
Hi Shubha,
Thanks for the link. I have been using the various performance checker options, which are helpful to gain insight on each layer in the network. I haven't seen any of them indicate anything about # SHAVEs though.
Thanks,
Chris
Chris this fine-grained control (i.e. "number of shaves") is no longer available. OpenVINO selects the most optimal configuration by default.
Hope it helps and thank you for using OpenVino !
Shubha
OK, thanks for looking into this.
-Chris
Hi Shubha,
As a follow up to this, just wondering if the performance enhancements of MX vs M2 I've seen using NCS and NCS2 sound reasonable. I was expecting ~6-8x for MX vs M2, but I see more like 2-4x.
HP laptop with Intel Core i5-4310U CPU, 2.00 GHz x4
8 GB RAM
Ubuntu 16.04 LTS
Test #1: Sample code provided in Openvino kit
Test #2: custom code (U-net CNN with conv2d, max_pool, and deconvolution/upsample):
For more complete information about compiler optimizations, see our Optimization Notice.