My model is based on mobilenet. The inference time on fpga platform is three times over that of on cpu platform. Why?

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.

My model is based on mobilenet. The inference time on fpga platform is three times over that of on cpu platform. Why?

358 Views

testing environment:

openvino version: 2018 R4

inference engine: classification_sample

parameter of running on fpga paltform: -d HETERO:FPGA,CPU (and IR's precision is FP16)

parameter of running on fpga paltform: -d CPU (and IR's precision is FP32)

batchsize: 1 to 32

Link Copied

0 Replies

Community support is provided Monday to Friday. 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.