Different inference performance on different training data

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.

Different inference performance on different training data

415 Views

Hi! I am developing vision related DNN using OpenVINO toolkit and Caffe.

I post this text because of one question. I am training the same DNN model on several different sets of training data.

Although the DNN model, Model-Optimizer parameters and test platform is always the same, inference speed of real data is different up to 2x depending on the training data.

In my opinion, it always has to be similar using the same environment. What is the reason ?

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.