[Bug]: use igpu in nuc, yolov10 output is weird
OpenVINO Version
2024
Operating System
Ubuntu 20.04 (LTS)
Device used for inference
GPU
Framework
PyTorch
Model used
Yolov10
Issue description
model yolo v10 int8 [test on cpu]
when use cpu, result is good
[test on igpu]
Step-by-step reproduction
i think if "GPU" in device.value or "NPU" in device.value: pass ov_model.reshape({0: [1, 3, 640, 640]}) this code has problem
when i use fp32 model with openvino, adapt with reshape({0: [1, 3, 640, 640]}) output result was weird but remove reshape case was good.
Relevant log output
plz check the bug at igpu
Issue submission checklist
- [X] I'm reporting an issue. It's not a question.
- [X] I checked the problem with the documentation, FAQ, open issues, Stack Overflow, etc., and have not found a solution.
- [X] There is reproducer code and related data files such as images, videos, models, etc.
Hi @ylab604 which OpenVINO demos/samples you are running?
Hi @ylab604 which OpenVINO demos/samples you are running?
convert yolov10 openvino tutorial https://docs.openvino.ai/2024/notebooks/yolov10-optimization-with-output.html#run-openvino-inference-on-auto-device-using-ultralytics-api
openvino ver ==2024.1 other version is not work at igpu(output is weird and dynamic shape not work)
@ylab604 I have validated the tutorial on GPU and CPU from OpenVINO 2024 and it is working fine.
Which other version is not working at igpu? For your information, this tutorial is only available and validated in the OpenVINO 2024 version. Can you explain how you run in the tutorial in other version and what version you are using?
@ylab604 I have validated the tutorial on GPU and CPU from OpenVINO 2024 and it is working fine.
Which other version is not working at igpu? For your information, this tutorial is only available and validated in the OpenVINO 2024 version. Can you explain how you run in the tutorial in other version and what version you are using?
did you check in igpu and os? i checked in intel nuc. unbuntu 20.04 2024.0 weird output 2024.1 right result 2024.2 weird output would you check in unbuntu or nuc?
Hi @ylab604 Yes. I have also validated with Ubuntu 20.04 (Intel NUC) and it is working fine from my end.
What is the specific Intel Processor you are using?
Hi @ylab604 Yes. I have also validated with Ubuntu 20.04 (Intel NUC) and it is working fine from my end.
What is the specific Intel Processor you are using?
would you tell me specific version of openvino? openvino==2024.??
and what is the os version of ubuntu? 20.04?
and how about int8 model?
@ylab604 I am running with OpenVINO 2024.0,2024.1 and 2024.2 for all precision with no issues.
@Aznie-Intel nuc 11 gen processor : 7 vendor_id : GenuineIntel cpu family : 6 model : 140 model name : 11th Gen Intel(R) Core(TM) i7-1185G7 @ 3.00GHz stepping : 1 microcode : 0xb6 cpu MHz : 3000.000 cache size : 12288 KB physical id : 0 siblings : 8 core id : 3 cpu cores : 4 apicid : 7 initial apicid : 7 fpu : yes fpu_exception : yes cpuid level : 27 wp : yes
============================================= i check the jupyter notebook
@Aznie-Intel
the problem is Ultralytics ver.
i used old version
thankyou