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.

Openvino Custom YOLO Inference Issue

SANTHAKUMAR91
Beginner
3,069 Views

Hello, 

I have trained a custom darknet yolo for character recognition and successfully converted darket net model -> keras -> tensorflow -> IR <Openvino format>. I was able to do inference in openvino Yolov3 Async inference code with few custom changes on parsing yolo output. The results are same as original model. But when tried to replicated the same in c++, the results are wrong. I did small work around on the parsing output results.  I managed to get the results but they are not the same as Openvino python inference.  

Issues:

1. Predictions are deviated by little offset.

2. Certain bbox predictions are missing.

 

This issues are not seen in Python inference.

 

The Yolo Network Details: 

num = 2
coords = 4
classes = 35

anchors=  { 3.638, 5.409, 3.281, 4.764 }

 

Input 1 x 3 x 80 x 240 - NCHW

output = 10 x 30 x 80 - Blob Output

 

Kindly help me resolving the issue. Thanks  

 

0 Kudos
1 Solution
IntelSupport
Community Manager
2,959 Views

Hi Santhakumar,

Thanks for your patience. We have tested your inference code, however, we are unable to replicate the same result as yours on the C++ inference code. You might need to change your customer code. Meanwhile, I noticed that your yolodetector.cpp is similar to our main.cpp file in Multi-Channel Object Detection Yolov3 C++ Demo. I would advise you to use it as a reference for your customer inference code as it has been tested and validated for yolo-v3 model. Also, on why both platforms give different results while running the same model- it may due to some library and component availabilities on Phyton are well covered compared to C++.

 

Regards,

Aznie


View solution in original post

0 Kudos
14 Replies
IntelSupport
Community Manager
3,025 Views

Hello Santhakumar91,

Thanks for reaching out. We are investigating this issue and will update you with the information soon. Meanwhile, could you share your model and inference code for us to test it on our end?

 

Regards,

Aznie


0 Kudos
SANTHAKUMAR91
Beginner
3,012 Views

Hello, 

Thanks for the response. I have attached the model and code. 

I have used Openvino 2021.3.0 version.

0 Kudos
IntelSupport
Community Manager
2,983 Views

Hello Santhakumar91,

Could you please share the source of the OCR model that you used. Thanks.

 

Regards,

Aznie


0 Kudos
SANTHAKUMAR91
Beginner
2,973 Views

Hello,

Its a customized yolo v3 using the darknet source. Trained on custom dataset.

0 Kudos
IntelSupport
Community Manager
2,960 Views

Hi Santhakumar,

Thanks for your patience. We have tested your inference code, however, we are unable to replicate the same result as yours on the C++ inference code. You might need to change your customer code. Meanwhile, I noticed that your yolodetector.cpp is similar to our main.cpp file in Multi-Channel Object Detection Yolov3 C++ Demo. I would advise you to use it as a reference for your customer inference code as it has been tested and validated for yolo-v3 model. Also, on why both platforms give different results while running the same model- it may due to some library and component availabilities on Phyton are well covered compared to C++.

 

Regards,

Aznie


0 Kudos
IntelSupport
Community Manager
2,908 Views

Hi Santhakumar,

This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.


Regards,

Aznie



0 Kudos
Aznie_Intel
Moderator
2,869 Views

Hi Santhakumar,

The developer team is looking into your Yolov3 Async C++ inference performance issues. I will update you once we obtain feedback from them.

 

Regards,

Aznie

0 Kudos
IntelSupport
Community Manager
2,837 Views

Hi Santhakumar,

Did you train the model with yolo3? We found that the C++ code is based on yolo5 and the python code s based on yolo3.


Regards,

Aznie



0 Kudos
SANTHAKUMAR91
Beginner
2,820 Views

Hi Aznie,

Yes the model is trained on yolo v3 architecture. 

0 Kudos
IntelSupport
Community Manager
2,816 Views

Hi Santhakumar,

Could you provide us the compilation step for C++ compilation or CMAKE package so that we can directly compile?


Regards,

Aznie


0 Kudos
IntelSupport
Community Manager
2,764 Views

Hi Santhakumar,

Is it possible for you to share with us your Makefile or compilation step? We need it to determine the issue that happens with your C++ custom code.


Regards,

Aznie


0 Kudos
SANTHAKUMAR91
Beginner
2,751 Views

Hi , This is Visual Studio Project, i have used "security_barrier_camera_demo"  project from openvino for setup and execution. Thanks 

0 Kudos
IntelSupport
Community Manager
2,737 Views

Hi Santhakumar,

Thank you for your reply. Do you still need any help regarding this?

 

Regards,

Aznie


0 Kudos
IntelSupport
Community Manager
2,642 Views

Hi Santhakumar,

Thank you for your question. If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored.


Regards,

Aznie


0 Kudos
Reply