Does OpenCV-OpenVINO version supports Yolo v3 network?

asked 2019-07-01 08:52:10 -0600

AlexB
76 ●2 ●4 ●7

updated 2020-10-23 02:04:36 -0600

sturkmen

6772 ●3 ●48 ●79 https://github.com/stu...

As known OpenVINO can be used as backend for OpenCV-dnn module, and OpenCV-dnn module support Yolo v3 object dtection.

OpenCV can use OpenVNIO backend: https://github.com/opencv/opencv/wiki...

Intel's Deep Learning Inference Engine (DL IE) is a part of Intel® OpenVINO™ toolkit. You can use it as a computational backend for OpenCV deep learning module.

OpenCV-dnn supports Yolo v3: https://github.com/opencv/opencv/blob...

I installed OpenVINO with integretaed OpenCV-4.1.0-openvion, but there is no yolo in samples.
Also there is no yolo v3 models in zoo: https://github.com/opencv/open_model_...

It seems that OpenCV should support Yolo v3 by using Path-2: https://www.learnopencv.com/using-ope...

image description

Does OpenCV-OpenVINO version supports Yolo v3 object detection to run on Intel VPU (Myriad X) - NCS2?

Comments

There is the release notes and the forum where you can also ask.

Eduardo ( 2019-07-03 12:25:13 -0600 )edit

add a comment

answered 2019-07-02 07:56:58 -0600

kbarni

4134 ●1 ●13 ●49

OpenCV is a generic image processing library (with DNN support), OpenVINO is a kind of DNN compiler for Intel VPUs.

"OpenCV can use OpenVINO backend" means that OpenVINO has some OpenCV compatibility, so it can take OpenCV Mats and process them in the VPU. It doesn't mean that it can take OpenCV deep neural networks.

The problem with OpenVINO is that it needs to "translate" the Caffe/TF networks to a Myriad-compatible format. As OpenVINO is not complete yet, it can't understand every kind of DNN layer or parameter; so it will give a compilation error for some complex networks (as YoloV3).

The solution would be to use a similar network that OpenVINO understands: The ...-coco networks can be used as YOLO alternatives.

edit flag offensive delete link

Comments

Thanks! ""OpenCV can use OpenVINO backend" means that OpenVINO has some OpenCV compatibility, so it can take OpenCV Mats and process them in the VPU. It doesn't mean that it can take OpenCV deep neural networks." Does it mean that OpenCV with net.setPreferableBackend(DNN_BACKEND_INFERENCE_ENGINE); and net.setPreferableTarget(DNN_TARGET_MYRIAD); can accelerate OpenCV-dnn modul by using VPU Myriad? And how much, if I use CPU Atom or Raspbery + VPU Myriad?

AlexB ( 2019-07-02 17:54:07 -0600 )edit

add a comment

Does OpenCV-OpenVINO version supports Yolo v3 network?

Comments

1 answer

Comments

Links

Question Tools

Stats

Related questions

Does OpenCV-OpenVINO version supports Yolo v3 network? edit

Comments

1 answer

Comments

Links

Question Tools

Stats

Related questions

Does OpenCV-OpenVINO version supports Yolo v3 network?