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.

Run Layers in CPU and FPGA using OpenVINO

Malhar
Employee
446 Views

I am looking for the python code implementation / reference where we can infer the respective layers using OpenVINO ? For Example- 

after loading IR into Plugin

for l in net.layers.values():
    if l.name == "Layer1":
        l.affinity = "FPGA"

    if l.name == "Layer2":
        l.affinity = "CPU"

 

exec_net = plugin.load(network=net)
res = exec_net.infer(inputs={input_blob: image})
 

Is it possible to do ? 

0 Kudos
2 Replies
Shubha_R_Intel
Employee
446 Views

Under deployment_tools\inference_engine\samples\python_samples there is affinity_setting_demo.py which should give you a good starting point.

0 Kudos
Malhar
Employee
446 Views

Thank you for the response. How to read the inputs and output data passing for layers during inference ? Is there any API to check ?

0 Kudos
Reply