I am Guru, Software Developer from India. I have the following systems, Ubuntu 16.04, Intel® Core™ i3-5005U CPU @ 2.00GHz × 4 processor and Intel® HD Graphics 5500 (Broadwell GT2) graphics. I know its a fifth generation processor, still can i install OpenVINO, as I work on core Computer Vision using OpenCV and Caffe or OpenCV, TensorFlow, SSD Mobilenet. as per the notes, I know its good on sixth generation processors.
Can you please let me know, would it be effective to install OpenVINO to increase the performance of my systems.
These are our target platform from " https://software.intel.com/en-us/openvino-toolkit "
Looks like, you are talking about 2 different things.
* OpenVINO provides multiple inference engine plugins for each compute device.
. CPU: mklDNN (Intel math kernel library)
. GPU: clDNN (Intel OpenCL)
. MYRIAD: Movidius VPU plugin
. FPGA: FPGA plugin
You can get performance advantage through each Intel plugins.
* Python is one of "framework"s, which it does not related to deep learning performance itself.
OpenVINO provides a python wrapper but still need to be improved.
Please check inference engine samples also.
Thanks again for the detailed response Peter.
One last question, its reg.Intel FPGA, while googling i figured out that OpenCV can be used in FPGAs, Can you please let me know, If I would have the liberty to code and deploy Deep Learning models like OpenCV DNN using Cafee, Tensorflow(using python) in FPGAs, just like an Intel powered PC.
Have you actually tried running OpenVINO? 6-8 generation is officially tested configuration, but in reality there should be nothing limiting you from running on Broadwell CPU. Given that there are SSE optimizations, you may benefit in terms of performance.