-
Notifications
You must be signed in to change notification settings - Fork 2.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug] Yolo Performance Drop When Using OV2022.1 #17044
Comments
Hi Jan, thanks for reporting the issue. Please give us some time to investigate. In the meantime could you please share your HW configuration used for the tests? |
Hi @tomdol , |
@HonzaCuhel Thank you for great description! Since #7588 we are representing fp16 constants in such a way so it is expected (that shouldn't affect performance, because those Converts will be removed by plugins). Note that |
I've measured provided yolo models using benchmark_app (you can find it in
I have a few questions/tips:
Thanks, |
@mbencer Thank you very much for your answer! FPS was measured using our custom version inspired by the benchmark_app, it should give the same results.
Best, |
@HonzaCuhel Could you elaborate more about this blob conversion? Do you mean exporting compiled model into binary representation like compile tool ? |
Hi @mbencer, I apologize for my delayed response. I've measured provided yolo models using benchmark_app from master and these are the results:
I've measure it on my laptop with following specification:
Yes, something like that. We have our own tool. [link][repository] Best, |
Hello @HonzaCuhel , Could you please try the 2023.1 latest pre-release to check if issue is still visible for you? |
Hi @andrei-kochin , I'll try it. Best, |
I just wanna ask you, will the MX be supported in 2023.1? |
The OpenVINO 2022.3.2 LTS supports MyriadX (Intel® Neural Compute Stick 2 and Intel® Vision Accelerator Design with Intel® Movidius™ VPUs (HDDL)), check the LTS release notes for more information. OpenVINO v2023.1 does not support MX devices. Closing this, I hope previous responses were sufficient to help you proceed. Feel free to reopen to ask any questions related to this topic. |
Hello,
we are experiencing a drop in performance with the converted YoloV7 using our tools.luxonis.com since we switched to using OpenVINO in version
2022.1.0
(before we were using version2021.4.2
). Initially, we were experiencing performance drop also with YoloV6 R3 and YoloV8 models, but after switching to exporting models to IR format with--use_legacy_frontend
flag, the performance for YoloV6 R3 and YoloV8 was comparable as before.These are the measured fps that we measured with the generated .blob files:
--use_legacy_frontend
We investigated the exported .xml files, looked at the operations and their total count and found out that models exported with version 2022.1.0 use less unique operations, but the total number of all ops is greater. Here is a link to the table containing all the findings.
The models were exported with these commands:
mo --input_model yolov6nr3-simplified.onnx --output_dir "output/" --model_name yolov6nr3 --data_type FP16 --reverse_input_channels --scale 255 --output "output1_yolov6r2,output2_yolov6r2,output3_yolov6r2"
mo --input_model yolov7t-simplified.onnx --output_dir "output/" --model_name yolov7t --data_type FP16 --reverse_input_channels --scale 255 --output "output1_yolov7,output2_yolov7,output3_yolov7"
mo --input_model yolov8n-simplified.onnx --output_dir "output_yolov8n/" --model_name yolov8n --data_type FP16 --reverse_input_channels --scale 255 --output "output1_yolov6r2,output2_yolov6r2,output3_yolov6r2"
Here are the model files.
System information (version)
Our questions
2022.1.0
? Because not all model performances were effected, e.g. YoloV5 and YoloV6 R2 models were not.--use_legacy_frontend
flag, the performance of YoloV7 is still worse?Convert
layers in exported models using OpenVINO2022.1.0
?Thank you very much!
Best
Jan
The text was updated successfully, but these errors were encountered: